Merge pull request #7560 from smarmau/patch-2

Update freqai-spice-rack.md

.github/workflows/ci.yml

@@ -24,7 +24,7 @@ jobs:
     strategy:
       matrix:
         os: [ ubuntu-18.04, ubuntu-20.04, ubuntu-22.04 ]
-        python-version: ["3.8", "3.9", "3.10"]
+        python-version: ["3.8", "3.9", "3.10.6"]
 
     steps:
     - uses: actions/checkout@v3
@@ -121,7 +121,7 @@ jobs:
     strategy:
       matrix:
         os: [ macos-latest ]
-        python-version: ["3.8", "3.9", "3.10"]
+        python-version: ["3.8", "3.9", "3.10.6"]
 
     steps:
     - uses: actions/checkout@v3
@@ -205,7 +205,7 @@ jobs:
     strategy:
       matrix:
         os: [ windows-latest ]
-        python-version: ["3.8", "3.9", "3.10"]
+        python-version: ["3.8", "3.9", "3.10.6"]
 
     steps:
     - uses: actions/checkout@v3
@@ -272,6 +272,16 @@ jobs:
         pip install pyaml
         python build_helpers/pre_commit_update.py
 
+  pre-commit:
+    runs-on: ubuntu-22.04
+    steps:
+    - uses: actions/checkout@v3
+
+    - uses: actions/setup-python@v4
+      with:
+        python-version: "3.10"
+    - uses: pre-commit/action@v3.0.0
+
   docs_check:
     runs-on: ubuntu-20.04
     steps:
@@ -302,7 +312,7 @@ jobs:
 
   # Notify only once - when CI completes (and after deploy) in case it's successfull
   notify-complete:
-    needs: [ build_linux, build_macos, build_windows, docs_check, mypy_version_check ]
+    needs: [ build_linux, build_macos, build_windows, docs_check, mypy_version_check, pre-commit ]
     runs-on: ubuntu-20.04
     # Discord notification can't handle schedule events
     if: (github.event_name != 'schedule')
@@ -327,7 +337,7 @@ jobs:
           webhookUrl: ${{ secrets.DISCORD_WEBHOOK }}
 
   deploy:
-    needs: [ build_linux, build_macos, build_windows, docs_check, mypy_version_check ]
+    needs: [ build_linux, build_macos, build_windows, docs_check, mypy_version_check, pre-commit ]
     runs-on: ubuntu-20.04
 
     if: (github.event_name == 'push' || github.event_name == 'schedule' || github.event_name == 'release') && github.repository == 'freqtrade/freqtrade'
@@ -397,15 +407,6 @@ jobs:
       run: |
         build_helpers/publish_docker_multi.sh
 
-    - name: Discord notification
-      uses: rjstone/discord-webhook-notify@v1
-      if: always() && ( github.event_name != 'pull_request' || github.event.pull_request.head.repo.fork == false) && (github.event_name != 'schedule')
-      with:
-          severity: info
-          details: Deploy Succeeded!
-          webhookUrl: ${{ secrets.DISCORD_WEBHOOK }}
-
-
   deploy_arm:
     needs: [ deploy ]
     # Only run on 64bit machines
@@ -433,3 +434,11 @@ jobs:
         BRANCH_NAME: ${{ steps.extract_branch.outputs.branch }}
       run: |
         build_helpers/publish_docker_arm64.sh
+
+    - name: Discord notification
+      uses: rjstone/discord-webhook-notify@v1
+      if: always() && ( github.event_name != 'pull_request' || github.event.pull_request.head.repo.fork == false) && (github.event_name != 'schedule')
+      with:
+          severity: info
+          details: Deploy Succeeded!
+          webhookUrl: ${{ secrets.DISCORD_WEBHOOK }}

.pre-commit-config.yaml

@@ -15,7 +15,7 @@ repos:
         additional_dependencies:
           - types-cachetools==5.2.1
           - types-filelock==3.2.7
-          - types-requests==2.28.9
+          - types-requests==2.28.11
           - types-tabulate==0.8.11
           - types-python-dateutil==2.8.19
         # stages: [push]
@@ -34,7 +34,9 @@ repos:
         exclude: |
             (?x)^(
                 tests/.*|
-                .*\.svg
+                .*\.svg|
+                .*\.yml|
+                .*\.json
             )$
       - id: mixed-line-ending
       - id: debug-statements

Dockerfile

@@ -1,4 +1,4 @@
-FROM python:3.10.6-slim-bullseye as base
+FROM python:3.10.7-slim-bullseye as base
 
 # Setup env
 ENV LANG C.UTF-8

build_helpers/install_windows.ps1

@@ -6,13 +6,13 @@ python -m pip install --upgrade pip wheel
 $pyv = python -c "import sys; print(f'{sys.version_info.major}.{sys.version_info.minor}')"
 
 if ($pyv -eq '3.8') {
-    pip install build_helpers\TA_Lib-0.4.24-cp38-cp38-win_amd64.whl
+    pip install build_helpers\TA_Lib-0.4.25-cp38-cp38-win_amd64.whl
 }
 if ($pyv -eq '3.9') {
-    pip install build_helpers\TA_Lib-0.4.24-cp39-cp39-win_amd64.whl
+    pip install build_helpers\TA_Lib-0.4.25-cp39-cp39-win_amd64.whl
 }
 if ($pyv -eq '3.10') {
-    pip install build_helpers\TA_Lib-0.4.24-cp310-cp310-win_amd64.whl
+    pip install build_helpers\TA_Lib-0.4.25-cp310-cp310-win_amd64.whl
 }
 pip install -r requirements-dev.txt
 pip install -e .

config_examples/config_freqai.example.json

@@ -53,7 +53,6 @@
     ],
     "freqai": {
         "enabled": true,
-        "startup_candles": 10000,
         "purge_old_models": true,
         "train_period_days": 15,
         "backtest_period_days": 7,
@@ -75,9 +74,11 @@
             "weight_factor": 0.9,
             "principal_component_analysis": false,
             "use_SVM_to_remove_outliers": true,
-            "stratify_training_data": 0,
-            "indicator_max_period_candles": 20,
-            "indicator_periods_candles": [10, 20]
+            "indicator_periods_candles": [
+                10,
+                20
+            ],
+            "plot_feature_importances": 0
         },
         "data_split_parameters": {
             "test_size": 0.33,

config_examples/config_full.example.json

@@ -64,8 +64,8 @@
         "stoploss_on_exchange_limit_ratio": 0.99
     },
     "order_time_in_force": {
-        "entry": "gtc",
-        "exit": "gtc"
+        "entry": "GTC",
+        "exit": "GTC"
     },
     "pairlists": [
         {"method": "StaticPairList"},
@@ -172,7 +172,24 @@
         "jwt_secret_key": "somethingrandom",
         "CORS_origins": [],
         "username": "freqtrader",
-        "password": "SuperSecurePassword"
+        "password": "SuperSecurePassword",
+        "ws_token": "secret_ws_t0ken."
+    },
+    "external_message_consumer": {
+        "enabled": false,
+        "producers": [
+          {
+            "name": "default",
+            "host": "127.0.0.2",
+            "port": 8080,
+            "ws_token": "secret_ws_t0ken."
+          }
+        ],
+        "wait_timeout": 300,
+        "ping_timeout": 10,
+        "sleep_time": 10,
+        "remove_entry_exit_signals": false,
+        "message_size_limit": 8
     },
     "bot_name": "freqtrade",
     "db_url": "sqlite:///tradesv3.sqlite",

docker/Dockerfile.freqai

@@ -6,4 +6,3 @@ FROM ${sourceimage}:${sourcetag}
 COPY requirements-freqai.txt /freqtrade/
 
 RUN pip install -r requirements-freqai.txt --user --no-cache-dir
-

docker/Dockerfile.jupyter

@@ -1,7 +1,8 @@
 FROM freqtradeorg/freqtrade:develop_plot
 
 
-RUN pip install jupyterlab --user --no-cache-dir
+# Pin jupyter-client to avoid tornado version conflict
+RUN pip install jupyterlab jupyter-client==7.3.4 --user --no-cache-dir
 
 # Empty the ENTRYPOINT to allow all commands
 ENTRYPOINT []

docker/docker-compose-jupyter.yml

@@ -10,7 +10,7 @@ services:
     ports:
       - "127.0.0.1:8888:8888"
     volumes:
-      - "./user_data:/freqtrade/user_data"
+      - "../user_data:/freqtrade/user_data"
     # Default command used when running `docker compose up`
     command: >
       jupyter lab --port=8888 --ip 0.0.0.0 --allow-root

docs/advanced-hyperopt.md

@@ -17,6 +17,7 @@ from typing import Any, Dict
 
 from pandas import DataFrame
 
+from freqtrade.constants import Config
 from freqtrade.optimize.hyperopt import IHyperOptLoss
 
 TARGET_TRADES = 600
@@ -31,7 +32,7 @@ class SuperDuperHyperOptLoss(IHyperOptLoss):
     @staticmethod
     def hyperopt_loss_function(results: DataFrame, trade_count: int,
                                min_date: datetime, max_date: datetime,
-                               config: Dict, processed: Dict[str, DataFrame],
+                               config: Config, processed: Dict[str, DataFrame],
                                backtest_stats: Dict[str, Any],
                                *args, **kwargs) -> float:
         """

docs/backtesting.md

@@ -107,7 +107,7 @@ Strategy arguments:
 
 ## Test your strategy with Backtesting
 
-Now you have good Buy and Sell strategies and some historic data, you want to test it against
+Now you have good Entry and exit strategies and some historic data, you want to test it against
 real data. This is what we call [backtesting](https://en.wikipedia.org/wiki/Backtesting).
 
 Backtesting will use the crypto-currencies (pairs) from your config file and load historical candle (OHLCV) data from `user_data/data/<exchange>` by default.
@@ -215,7 +215,7 @@ Sometimes your account has certain fee rebates (fee reductions starting with a c
 To account for this in backtesting, you can use the `--fee` command line option to supply this value to backtesting.
 This fee must be a ratio, and will be applied twice (once for trade entry, and once for trade exit).
 
-For example, if the buying and selling commission fee is 0.1% (i.e., 0.001 written as ratio), then you would run backtesting as the following:
+For example, if the commission fee per order is 0.1% (i.e., 0.001 written as ratio), then you would run backtesting as the following:
 
 ```bash
 freqtrade backtesting --fee 0.001
@@ -252,41 +252,41 @@ The most important in the backtesting is to understand the result.
 A backtesting result will look like that:
 
 ```
-========================================================= BACKTESTING REPORT ==========================================================
-| Pair     |   Buys |   Avg Profit % |   Cum Profit % |   Tot Profit BTC |   Tot Profit % | Avg Duration |  Wins Draws Loss   Win%  |
-|:---------|-------:|---------------:|---------------:|-----------------:|---------------:|:-------------|-------------------------:|
-| ADA/BTC  |     35 |          -0.11 |          -3.88 |      -0.00019428 |          -1.94 | 4:35:00      |    14     0    21   40.0 |
-| ARK/BTC  |     11 |          -0.41 |          -4.52 |      -0.00022647 |          -2.26 | 2:03:00      |     3     0     8   27.3 |
-| BTS/BTC  |     32 |           0.31 |           9.78 |       0.00048938 |           4.89 | 5:05:00      |    18     0    14   56.2 |
-| DASH/BTC |     13 |          -0.08 |          -1.07 |      -0.00005343 |          -0.53 | 4:39:00      |     6     0     7   46.2 |
-| ENG/BTC  |     18 |           1.36 |          24.54 |       0.00122807 |          12.27 | 2:50:00      |     8     0    10   44.4 |
-| EOS/BTC  |     36 |           0.08 |           3.06 |       0.00015304 |           1.53 | 3:34:00      |    16     0    20   44.4 |
-| ETC/BTC  |     26 |           0.37 |           9.51 |       0.00047576 |           4.75 | 6:14:00      |    11     0    15   42.3 |
-| ETH/BTC  |     33 |           0.30 |           9.96 |       0.00049856 |           4.98 | 7:31:00      |    16     0    17   48.5 |
-| IOTA/BTC |     32 |           0.03 |           1.09 |       0.00005444 |           0.54 | 3:12:00      |    14     0    18   43.8 |
-| LSK/BTC  |     15 |           1.75 |          26.26 |       0.00131413 |          13.13 | 2:58:00      |     6     0     9   40.0 |
-| LTC/BTC  |     32 |          -0.04 |          -1.38 |      -0.00006886 |          -0.69 | 4:49:00      |    11     0    21   34.4 |
-| NANO/BTC |     17 |           1.26 |          21.39 |       0.00107058 |          10.70 | 1:55:00      |    10     0     7   58.5 |
-| NEO/BTC  |     23 |           0.82 |          18.97 |       0.00094936 |           9.48 | 2:59:00      |    10     0    13   43.5 |
-| REQ/BTC  |      9 |           1.17 |          10.54 |       0.00052734 |           5.27 | 3:47:00      |     4     0     5   44.4 |
-| XLM/BTC  |     16 |           1.22 |          19.54 |       0.00097800 |           9.77 | 3:15:00      |     7     0     9   43.8 |
-| XMR/BTC  |     23 |          -0.18 |          -4.13 |      -0.00020696 |          -2.07 | 5:30:00      |    12     0    11   52.2 |
-| XRP/BTC  |     35 |           0.66 |          22.96 |       0.00114897 |          11.48 | 3:49:00      |    12     0    23   34.3 |
-| ZEC/BTC  |     22 |          -0.46 |         -10.18 |      -0.00050971 |          -5.09 | 2:22:00      |     7     0    15   31.8 |
-| TOTAL    |    429 |           0.36 |         152.41 |       0.00762792 |          76.20 | 4:12:00      |   186     0   243   43.4 |
+========================================================= BACKTESTING REPORT =========================================================
+| Pair     | Entries |   Avg Profit % |   Cum Profit % |   Tot Profit BTC |   Tot Profit % | Avg Duration |  Wins Draws Loss   Win%  |
+|:---------|--------:|---------------:|---------------:|-----------------:|---------------:|:-------------|-------------------------:|
+| ADA/BTC  |      35 |          -0.11 |          -3.88 |      -0.00019428 |          -1.94 | 4:35:00      |    14     0    21   40.0 |
+| ARK/BTC  |      11 |          -0.41 |          -4.52 |      -0.00022647 |          -2.26 | 2:03:00      |     3     0     8   27.3 |
+| BTS/BTC  |      32 |           0.31 |           9.78 |       0.00048938 |           4.89 | 5:05:00      |    18     0    14   56.2 |
+| DASH/BTC |      13 |          -0.08 |          -1.07 |      -0.00005343 |          -0.53 | 4:39:00      |     6     0     7   46.2 |
+| ENG/BTC  |      18 |           1.36 |          24.54 |       0.00122807 |          12.27 | 2:50:00      |     8     0    10   44.4 |
+| EOS/BTC  |      36 |           0.08 |           3.06 |       0.00015304 |           1.53 | 3:34:00      |    16     0    20   44.4 |
+| ETC/BTC  |      26 |           0.37 |           9.51 |       0.00047576 |           4.75 | 6:14:00      |    11     0    15   42.3 |
+| ETH/BTC  |      33 |           0.30 |           9.96 |       0.00049856 |           4.98 | 7:31:00      |    16     0    17   48.5 |
+| IOTA/BTC |      32 |           0.03 |           1.09 |       0.00005444 |           0.54 | 3:12:00      |    14     0    18   43.8 |
+| LSK/BTC  |      15 |           1.75 |          26.26 |       0.00131413 |          13.13 | 2:58:00      |     6     0     9   40.0 |
+| LTC/BTC  |      32 |          -0.04 |          -1.38 |      -0.00006886 |          -0.69 | 4:49:00      |    11     0    21   34.4 |
+| NANO/BTC |      17 |           1.26 |          21.39 |       0.00107058 |          10.70 | 1:55:00      |    10     0     7   58.5 |
+| NEO/BTC  |      23 |           0.82 |          18.97 |       0.00094936 |           9.48 | 2:59:00      |    10     0    13   43.5 |
+| REQ/BTC  |       9 |           1.17 |          10.54 |       0.00052734 |           5.27 | 3:47:00      |     4     0     5   44.4 |
+| XLM/BTC  |      16 |           1.22 |          19.54 |       0.00097800 |           9.77 | 3:15:00      |     7     0     9   43.8 |
+| XMR/BTC  |      23 |          -0.18 |          -4.13 |      -0.00020696 |          -2.07 | 5:30:00      |    12     0    11   52.2 |
+| XRP/BTC  |      35 |           0.66 |          22.96 |       0.00114897 |          11.48 | 3:49:00      |    12     0    23   34.3 |
+| ZEC/BTC  |      22 |          -0.46 |         -10.18 |      -0.00050971 |          -5.09 | 2:22:00      |     7     0    15   31.8 |
+| TOTAL    |     429 |           0.36 |         152.41 |       0.00762792 |          76.20 | 4:12:00      |   186     0   243   43.4 |
 ========================================================= EXIT REASON STATS ==========================================================
-| Exit Reason        |   Sells |  Wins |  Draws |  Losses |
+| Exit Reason        |   Exits |  Wins |  Draws |  Losses |
 |:-------------------|--------:|------:|-------:|--------:|
 | trailing_stop_loss |     205 |   150 |      0 |      55 |
 | stop_loss          |     166 |     0 |      0 |     166 |
 | exit_signal        |      56 |    36 |      0 |      20 |
 | force_exit         |       2 |     0 |      0 |       2 |
 ====================================================== LEFT OPEN TRADES REPORT ======================================================
-| Pair     |   Buys |   Avg Profit % |   Cum Profit % |   Tot Profit BTC |   Tot Profit % | Avg Duration   |  Win Draw Loss Win% |
-|:---------|-------:|---------------:|---------------:|-----------------:|---------------:|:---------------|--------------------:|
-| ADA/BTC  |      1 |           0.89 |           0.89 |       0.00004434 |           0.44 | 6:00:00        |    1    0    0  100 |
-| LTC/BTC  |      1 |           0.68 |           0.68 |       0.00003421 |           0.34 | 2:00:00        |    1    0    0  100 |
-| TOTAL    |      2 |           0.78 |           1.57 |       0.00007855 |           0.78 | 4:00:00        |    2    0    0  100 |
+| Pair     |  Entries |   Avg Profit % |   Cum Profit % |   Tot Profit BTC |   Tot Profit % | Avg Duration   |  Win Draw Loss Win% |
+|:---------|---------:|---------------:|---------------:|-----------------:|---------------:|:---------------|--------------------:|
+| ADA/BTC  |        1 |           0.89 |           0.89 |       0.00004434 |           0.44 | 6:00:00        |    1    0    0  100 |
+| LTC/BTC  |        1 |           0.68 |           0.68 |       0.00003421 |           0.34 | 2:00:00        |    1    0    0  100 |
+| TOTAL    |        2 |           0.78 |           1.57 |       0.00007855 |           0.78 | 4:00:00        |    2    0    0  100 |
 ================== SUMMARY METRICS ==================
 | Metric                      | Value               |
 |-----------------------------+---------------------|
@@ -356,7 +356,7 @@ The column `Avg Profit %` shows the average profit for all trades made while the
 The column `Tot Profit %` shows instead the total profit % in relation to the starting balance.
 In the above results, we have a starting balance of 0.01 BTC and an absolute profit of 0.00762792 BTC - so the `Tot Profit %` will be `(0.00762792 / 0.01) * 100 ~= 76.2%`.
 
-Your strategy performance is influenced by your buy strategy, your exit strategy, and also by the `minimal_roi` and `stop_loss` you have set.
+Your strategy performance is influenced by your entry strategy, your exit strategy, and also by the `minimal_roi` and `stop_loss` you have set.
 
 For example, if your `minimal_roi` is only `"0":  0.01` you cannot expect the bot to make more profit than 1% (because it will exit every time a trade reaches 1%).
 
@@ -515,7 +515,7 @@ You can then load the trades to perform further analysis as shown in the [data a
 Since backtesting lacks some detailed information about what happens within a candle, it needs to take a few assumptions:
 
 - Exchange [trading limits](#trading-limits-in-backtesting) are respected
-- Buys happen at open-price
+- Entries happen at open-price
 - All orders are filled at the requested price (no slippage, no unfilled orders)
 - Exit-signal exits happen at open-price of the consecutive candle
 - Exit-signal is favored over Stoploss, because exit-signals are assumed to trigger on candle's open
@@ -612,11 +612,11 @@ There will be an additional table comparing win/losses of the different strategi
 Detailed output for all strategies one after the other will be available, so make sure to scroll up to see the details per strategy.
 
 ```
-=========================================================== STRATEGY SUMMARY =========================================================================
-| Strategy    |   Buys |   Avg Profit % |   Cum Profit % |   Tot Profit BTC |   Tot Profit % | Avg Duration   |  Wins |  Draws | Losses | Drawdown % |
-|:------------|-------:|---------------:|---------------:|-----------------:|---------------:|:---------------|------:|-------:|-------:|-----------:|
-| Strategy1   |    429 |           0.36 |         152.41 |       0.00762792 |          76.20 | 4:12:00        |   186 |      0 |    243 |       45.2 |
-| Strategy2   |   1487 |          -0.13 |        -197.58 |      -0.00988917 |         -98.79 | 4:43:00        |   662 |      0 |    825 |     241.68 |
+=========================================================== STRATEGY SUMMARY ===========================================================================
+| Strategy    |  Entries |   Avg Profit % |   Cum Profit % |   Tot Profit BTC |   Tot Profit % | Avg Duration   |  Wins |  Draws | Losses | Drawdown % |
+|:------------|---------:|---------------:|---------------:|-----------------:|---------------:|:---------------|------:|-------:|-------:|-----------:|
+| Strategy1   |      429 |           0.36 |         152.41 |       0.00762792 |          76.20 | 4:12:00        |   186 |      0 |    243 |       45.2 |
+| Strategy2   |     1487 |          -0.13 |        -197.58 |      -0.00988917 |         -98.79 | 4:43:00        |   662 |      0 |    825 |     241.68 |
 ```
 
 ## Next step

docs/configuration.md

@@ -58,9 +58,20 @@ This is similar to using multiple `--config` parameters, but simpler in usage as
 
 !!! Tip "Use multiple configuration files to keep secrets secret"
     You can use a 2nd configuration file containing your secrets. That way you can share your "primary" configuration file, while still keeping your API keys for yourself.
+    The 2nd file should only specify what you intend to override.
+    If a key is in more than one of the configurations, then the "last specified configuration" wins (in the above example, `config-private.json`).
+
+    For one-off commands, you can also use the below syntax by specifying multiple "--config" parameters.
+
+    ``` bash
+    freqtrade trade --config user_data/config1.json --config user_data/config-private.json <...>
+    ```
+
+    The below is equivalent to the example above - but having 2 configuration files in the configuration, for easier reuse.
 
     ``` json title="user_data/config.json"
     "add_config_files": [
+        "config1.json",
         "config-private.json"
     ]
     ```
@@ -69,17 +80,6 @@ This is similar to using multiple `--config` parameters, but simpler in usage as
     freqtrade trade --config user_data/config.json <...>
     ```
 
-    The 2nd file should only specify what you intend to override.
-    If a key is in more than one of the configurations, then the "last specified configuration" wins (in the above example, `config-private.json`).
-
-    For one-off commands, you can also use the below syntax by specifying multiple "--config" parameters.
-
-    ``` bash
-    freqtrade trade --config user_data/config.json --config user_data/config-private.json <...>
-    ```
-
-    This is equivalent to the example above - but `config-private.json` is specified as cli argument.
-
 ??? Note "config collision handling"
     If the same configuration setting takes place in both `config.json` and `config-import.json`, then the parent configuration wins.
     In the below case, `max_open_trades` would be 3 after the merging - as the reusable "import" configuration has this key overwritten.
@@ -111,6 +111,8 @@ This is similar to using multiple `--config` parameters, but simpler in usage as
     }
     ```
 
+    If multiple files are in the `add_config_files` section, then they will be assumed to be at identical levels, having the last occurrence override the earlier config (unless a parent already defined such a key).
+
 ## Configuration parameters
 
 The table below will list all configuration parameters available.
@@ -223,14 +225,16 @@ Mandatory parameters are marked as **Required**, which means that they are requi
 | `webhook.webhookexitcancel` | Payload to send on exit order cancel. Only required if `webhook.enabled` is `true`. See the [webhook documentation](webhook-config.md) for more details. <br> **Datatype:** String
 | `webhook.webhookexitfill` | Payload to send on exit order filled. Only required if `webhook.enabled` is `true`. See the [webhook documentation](webhook-config.md) for more details. <br> **Datatype:** String
 | `webhook.webhookstatus` | Payload to send on status calls. Only required if `webhook.enabled` is `true`. See the [webhook documentation](webhook-config.md) for more details. <br> **Datatype:** String
-| | **Rest API / FreqUI**
+| | **Rest API / FreqUI / Producer-Consumer**
 | `api_server.enabled` | Enable usage of API Server. See the [API Server documentation](rest-api.md) for more details. <br> **Datatype:** Boolean
 | `api_server.listen_ip_address` | Bind IP address. See the [API Server documentation](rest-api.md) for more details. <br> **Datatype:** IPv4
 | `api_server.listen_port` | Bind Port. See the [API Server documentation](rest-api.md) for more details. <br>**Datatype:** Integer between 1024 and 65535
 | `api_server.verbosity` | Logging verbosity. `info` will print all RPC Calls, while "error" will only display errors. <br>**Datatype:** Enum, either `info` or `error`. Defaults to `info`.
 | `api_server.username` | Username for API server. See the [API Server documentation](rest-api.md) for more details. <br>**Keep it in secret, do not disclose publicly.**<br> **Datatype:** String
 | `api_server.password` | Password for API server. See the [API Server documentation](rest-api.md) for more details. <br>**Keep it in secret, do not disclose publicly.**<br> **Datatype:** String
+| `api_server.ws_token` | API token for the Message WebSocket. See the [API Server documentation](rest-api.md) for more details.  <br>**Keep it in secret, do not disclose publicly.** <br> **Datatype:** String
 | `bot_name` | Name of the bot. Passed via API to a client - can be shown to distinguish / name bots.<br> *Defaults to `freqtrade`*<br> **Datatype:** String
+| `external_message_consumer` | Enable [Producer/Consumer mode](producer-consumer.md) for more details. <br> **Datatype:** Dict
 | | **Other**
 | `initial_state` | Defines the initial application state. If set to stopped, then the bot has to be explicitly started via `/start` RPC command. <br>*Defaults to `stopped`.* <br> **Datatype:** Enum, either `stopped` or `running`
 | `force_entry_enable` | Enables the RPC Commands to force a Trade entry. More information below. <br> **Datatype:** Boolean
@@ -525,21 +529,28 @@ It means if the order is not executed immediately AND fully then it is cancelled
 It is the same as FOK (above) except it can be partially fulfilled. The remaining part
 is automatically cancelled by the exchange.
 
-The `order_time_in_force` parameter contains a dict with buy and sell time in force policy values.
+**PO (Post only):**
+
+Post only order. The order is either placed as a maker order, or it is canceled.
+This means the order must be placed on orderbook for at at least time in an unfilled state.
+
+#### time_in_force config
+
+The `order_time_in_force` parameter contains a dict with entry and exit time in force policy values.
 This can be set in the configuration file or in the strategy.
 Values set in the configuration file overwrites values set in the strategy.
 
-The possible values are: `gtc` (default), `fok` or `ioc`.
+The possible values are: `GTC` (default), `FOK` or `IOC`.
 
 ``` python
 "order_time_in_force": {
-    "entry": "gtc",
-    "exit": "gtc"
+    "entry": "GTC",
+    "exit": "GTC"
 },
 ```
 
 !!! Warning
-    This is ongoing work. For now, it is supported only for binance and kucoin.
+    This is ongoing work. For now, it is supported only for binance, gate, ftx and kucoin.
     Please don't change the default value unless you know what you are doing and have researched the impact of using different values for your particular exchange.
 
 ### What values can be used for fiat_display_currency?
@@ -650,17 +661,7 @@ You should also make sure to read the [Exchanges](exchanges.md) section of the d
 
 ### Using proxy with Freqtrade
 
-To use a proxy with freqtrade, add the kwarg `"aiohttp_trust_env"=true` to the `"ccxt_async_kwargs"` dict in the exchange section of the configuration.
-
-An example for this can be found in `config_examples/config_full.example.json`
-
-``` json
-"ccxt_async_config": {
-    "aiohttp_trust_env": true
-}
-```
-
-Then, export your proxy settings using the variables `"HTTP_PROXY"` and `"HTTPS_PROXY"` set to the appropriate values
+To use a proxy with freqtrade, export your proxy settings using the variables `"HTTP_PROXY"` and `"HTTPS_PROXY"` set to the appropriate values.
 
 ``` bash
 export HTTP_PROXY="http://addr:port"
@@ -668,6 +669,20 @@ export HTTPS_PROXY="http://addr:port"
 freqtrade
 ```
 
+#### Proxy just exchange requests
+
+To use a proxy just for exchange connections (skips/ignores telegram and coingecko) - you can also define the proxies as part of the ccxt configuration.
+
+``` json
+"ccxt_config": {
+    "aiohttp_proxy": "http://addr:port",
+    "proxies": {
+        "http": "http://addr:port",
+        "https": "http://addr:port"
+    },
+}
+```
+
 ## Next step
 
 Now you have configured your config.json, the next step is to [start your bot](bot-usage.md).

docs/data-download.md

@@ -25,9 +25,8 @@ usage: freqtrade download-data [-h] [-v] [--logfile FILE] [-V] [-c PATH]
                                [--include-inactive-pairs]
                                [--timerange TIMERANGE] [--dl-trades]
                                [--exchange EXCHANGE]
-                               [-t {1m,3m,5m,15m,30m,1h,2h,4h,6h,8h,12h,1d,3d,1w,2w,1M,1y} [{1m,3m,5m,15m,30m,1h,2h,4h,6h,8h,12h,1d,3d,1w,2w,1M,1y} ...]]
-                               [--erase]
-                               [--data-format-ohlcv {json,jsongz,hdf5}]
+                               [-t TIMEFRAMES [TIMEFRAMES ...]] [--erase]
+                               [--data-format-ohlcv {json,jsongz,hdf5,feather,parquet}]
                                [--data-format-trades {json,jsongz,hdf5}]
                                [--trading-mode {spot,margin,futures}]
                                [--prepend]
@@ -37,7 +36,8 @@ optional arguments:
   -p PAIRS [PAIRS ...], --pairs PAIRS [PAIRS ...]
                         Limit command to these pairs. Pairs are space-
                         separated.
-  --pairs-file FILE     File containing a list of pairs to download.
+  --pairs-file FILE     File containing a list of pairs. Takes precedence over
+                        --pairs or pairs configured in the configuration.
   --days INT            Download data for given number of days.
   --new-pairs-days INT  Download data of new pairs for given number of days.
                         Default: `None`.
@@ -50,18 +50,18 @@ optional arguments:
                         as --timeframes/-t.
   --exchange EXCHANGE   Exchange name (default: `bittrex`). Only valid if no
                         config is provided.
-  -t {1m,3m,5m,15m,30m,1h,2h,4h,6h,8h,12h,1d,3d,1w,2w,1M,1y} [{1m,3m,5m,15m,30m,1h,2h,4h,6h,8h,12h,1d,3d,1w,2w,1M,1y} ...], --timeframes {1m,3m,5m,15m,30m,1h,2h,4h,6h,8h,12h,1d,3d,1w,2w,1M,1y} [{1m,3m,5m,15m,30m,1h,2h,4h,6h,8h,12h,1d,3d,1w,2w,1M,1y} ...]
+  -t TIMEFRAMES [TIMEFRAMES ...], --timeframes TIMEFRAMES [TIMEFRAMES ...]
                         Specify which tickers to download. Space-separated
                         list. Default: `1m 5m`.
   --erase               Clean all existing data for the selected
                         exchange/pairs/timeframes.
-  --data-format-ohlcv {json,jsongz,hdf5}
+  --data-format-ohlcv {json,jsongz,hdf5,feather,parquet}
                         Storage format for downloaded candle (OHLCV) data.
                         (default: `json`).
   --data-format-trades {json,jsongz,hdf5}
                         Storage format for downloaded trades data. (default:
                         `jsongz`).
-  --trading-mode {spot,margin,futures}
+  --trading-mode {spot,margin,futures}, --tradingmode {spot,margin,futures}
                         Select Trading mode
   --prepend             Allow data prepending. (Data-appending is disabled)
 
@@ -76,7 +76,7 @@ Common arguments:
                         `userdir/config.json` or `config.json` whichever
                         exists). Multiple --config options may be used. Can be
                         set to `-` to read config from stdin.
-  -d PATH, --datadir PATH
+  -d PATH, --datadir PATH, --data-dir PATH
                         Path to directory with historical backtesting data.
   --userdir PATH, --user-data-dir PATH
                         Path to userdata directory.
@@ -179,9 +179,11 @@ freqtrade download-data --exchange binance --pairs ETH/USDT XRP/USDT BTC/USDT --
 
 Freqtrade currently supports 3 data-formats for both OHLCV and trades data:
 
-* `json` (plain "text" json files)
-* `jsongz` (a gzip-zipped version of json files)
-* `hdf5` (a high performance datastore)
+* `json` -  plain "text" json files
+* `jsongz` - a gzip-zipped version of json files
+* `hdf5` - a high performance datastore
+* `feather` - a dataformat based on Apache Arrow
+* `parquet` - columnar datastore
 
 By default, OHLCV data is stored as `json` data, while trades data is stored as `jsongz` data.
 
@@ -200,38 +202,74 @@ If the default data-format has been changed during download, then the keys `data
 !!! Note
     You can convert between data-formats using the [convert-data](#sub-command-convert-data) and [convert-trade-data](#sub-command-convert-trade-data) methods.
 
+#### Dataformat comparison
+
+The following comparisons have been made with the following data, and by using the linux `time` command.
+
+```
+Found 6 pair / timeframe combinations.
++----------+-------------+--------+---------------------+---------------------+
+|     Pair |   Timeframe |   Type |                From |                  To |
+|----------+-------------+--------+---------------------+---------------------|
+| BTC/USDT |          5m |   spot | 2017-08-17 04:00:00 | 2022-09-13 19:25:00 |
+| ETH/USDT |          1m |   spot | 2017-08-17 04:00:00 | 2022-09-13 19:26:00 |
+| BTC/USDT |          1m |   spot | 2017-08-17 04:00:00 | 2022-09-13 19:30:00 |
+| XRP/USDT |          5m |   spot | 2018-05-04 08:10:00 | 2022-09-13 19:15:00 |
+| XRP/USDT |          1m |   spot | 2018-05-04 08:11:00 | 2022-09-13 19:22:00 |
+| ETH/USDT |          5m |   spot | 2017-08-17 04:00:00 | 2022-09-13 19:20:00 |
++----------+-------------+--------+---------------------+---------------------+
+```
+
+Timings have been taken in a not very scientific way with the following command, which forces reading the data into memory.
+
+``` bash
+time freqtrade list-data --show-timerange --data-format-ohlcv <dataformat>
+```
+
+|  Format | Size | timing |
+|------------|-------------|-------------|
+| `json` | 149Mb | 25.6s |
+| `jsongz` | 39Mb | 27s |
+| `hdf5` | 145Mb | 3.9s |
+| `feather` | 72Mb | 3.5s |
+| `parquet` | 83Mb | 3.8s |
+
+Size has been taken from the BTC/USDT 1m spot combination for the timerange specified above.
+
+To have a best performance/size mix, we recommend the use of either feather or parquet.
+
 #### Sub-command convert data
 
 ```
 usage: freqtrade convert-data [-h] [-v] [--logfile FILE] [-V] [-c PATH]
                               [-d PATH] [--userdir PATH]
                               [-p PAIRS [PAIRS ...]] --format-from
-                              {json,jsongz,hdf5} --format-to
-                              {json,jsongz,hdf5} [--erase]
-                              [-t {1m,3m,5m,15m,30m,1h,2h,4h,6h,8h,12h,1d,3d,1w,2w,1M,1y} [{1m,3m,5m,15m,30m,1h,2h,4h,6h,8h,12h,1d,3d,1w,2w,1M,1y} ...]]
+                              {json,jsongz,hdf5,feather,parquet} --format-to
+                              {json,jsongz,hdf5,feather,parquet} [--erase]
                               [--exchange EXCHANGE]
+                              [-t TIMEFRAMES [TIMEFRAMES ...]]
                               [--trading-mode {spot,margin,futures}]
-                              [--candle-types {spot,,futures,mark,index,premiumIndex,funding_rate} [{spot,,futures,mark,index,premiumIndex,funding_rate} ...]]
+                              [--candle-types {spot,futures,mark,index,premiumIndex,funding_rate} [{spot,futures,mark,index,premiumIndex,funding_rate} ...]]
 
 optional arguments:
   -h, --help            show this help message and exit
   -p PAIRS [PAIRS ...], --pairs PAIRS [PAIRS ...]
                         Limit command to these pairs. Pairs are space-
                         separated.
-  --format-from {json,jsongz,hdf5}
+  --format-from {json,jsongz,hdf5,feather,parquet}
                         Source format for data conversion.
-  --format-to {json,jsongz,hdf5}
+  --format-to {json,jsongz,hdf5,feather,parquet}
                         Destination format for data conversion.
   --erase               Clean all existing data for the selected
                         exchange/pairs/timeframes.
-  -t {1m,3m,5m,15m,30m,1h,2h,4h,6h,8h,12h,1d,3d,1w,2w,1M,1y} [{1m,3m,5m,15m,30m,1h,2h,4h,6h,8h,12h,1d,3d,1w,2w,1M,1y} ...], --timeframes {1m,3m,5m,15m,30m,1h,2h,4h,6h,8h,12h,1d,3d,1w,2w,1M,1y} [{1m,3m,5m,15m,30m,1h,2h,4h,6h,8h,12h,1d,3d,1w,2w,1M,1y} ...]
-                        Specify which tickers to download. Space-separated
-                        list. Default: `1m 5m`.
   --exchange EXCHANGE   Exchange name (default: `bittrex`). Only valid if no
                         config is provided.
-  --trading-mode {spot,margin,futures}
+  -t TIMEFRAMES [TIMEFRAMES ...], --timeframes TIMEFRAMES [TIMEFRAMES ...]
+                        Specify which tickers to download. Space-separated
+                        list. Default: `1m 5m`.
+  --trading-mode {spot,margin,futures}, --tradingmode {spot,margin,futures}
                         Select Trading mode
-  --candle-types {spot,,futures,mark,index,premiumIndex,funding_rate} [{spot,,futures,mark,index,premiumIndex,funding_rate} ...]
+  --candle-types {spot,futures,mark,index,premiumIndex,funding_rate} [{spot,futures,mark,index,premiumIndex,funding_rate} ...]
                         Select candle type to use
 
 Common arguments:
@@ -245,7 +283,7 @@ Common arguments:
                         `userdir/config.json` or `config.json` whichever
                         exists). Multiple --config options may be used. Can be
                         set to `-` to read config from stdin.
-  -d PATH, --datadir PATH
+  -d PATH, --datadir PATH, --data-dir PATH
                         Path to directory with historical backtesting data.
   --userdir PATH, --user-data-dir PATH
                         Path to userdata directory.
@@ -267,20 +305,24 @@ freqtrade convert-data --format-from json --format-to jsongz --datadir ~/.freqtr
 usage: freqtrade convert-trade-data [-h] [-v] [--logfile FILE] [-V] [-c PATH]
                                     [-d PATH] [--userdir PATH]
                                     [-p PAIRS [PAIRS ...]] --format-from
-                                    {json,jsongz,hdf5} --format-to
-                                    {json,jsongz,hdf5} [--erase]
+                                    {json,jsongz,hdf5,feather,parquet}
+                                    --format-to
+                                    {json,jsongz,hdf5,feather,parquet}
+                                    [--erase] [--exchange EXCHANGE]
 
 optional arguments:
   -h, --help            show this help message and exit
   -p PAIRS [PAIRS ...], --pairs PAIRS [PAIRS ...]
-                        Show profits for only these pairs. Pairs are space-
+                        Limit command to these pairs. Pairs are space-
                         separated.
-  --format-from {json,jsongz,hdf5}
+  --format-from {json,jsongz,hdf5,feather,parquet}
                         Source format for data conversion.
-  --format-to {json,jsongz,hdf5}
+  --format-to {json,jsongz,hdf5,feather,parquet}
                         Destination format for data conversion.
   --erase               Clean all existing data for the selected
                         exchange/pairs/timeframes.
+  --exchange EXCHANGE   Exchange name (default: `bittrex`). Only valid if no
+                        config is provided.
 
 Common arguments:
   -v, --verbose         Verbose mode (-vv for more, -vvv to get all messages).
@@ -293,7 +335,7 @@ Common arguments:
                         `userdir/config.json` or `config.json` whichever
                         exists). Multiple --config options may be used. Can be
                         set to `-` to read config from stdin.
-  -d PATH, --datadir PATH
+  -d PATH, --datadir PATH, --data-dir PATH
                         Path to directory with historical backtesting data.
   --userdir PATH, --user-data-dir PATH
                         Path to userdata directory.
@@ -318,9 +360,9 @@ This command will allow you to repeat this last step for additional timeframes w
 usage: freqtrade trades-to-ohlcv [-h] [-v] [--logfile FILE] [-V] [-c PATH]
                                  [-d PATH] [--userdir PATH]
                                  [-p PAIRS [PAIRS ...]]
-                                 [-t {1m,3m,5m,15m,30m,1h,2h,4h,6h,8h,12h,1d,3d,1w,2w,1M,1y} [{1m,3m,5m,15m,30m,1h,2h,4h,6h,8h,12h,1d,3d,1w,2w,1M,1y} ...]]
+                                 [-t TIMEFRAMES [TIMEFRAMES ...]]
                                  [--exchange EXCHANGE]
-                                 [--data-format-ohlcv {json,jsongz,hdf5}]
+                                 [--data-format-ohlcv {json,jsongz,hdf5,feather,parquet}]
                                  [--data-format-trades {json,jsongz,hdf5}]
 
 optional arguments:
@@ -328,12 +370,12 @@ optional arguments:
   -p PAIRS [PAIRS ...], --pairs PAIRS [PAIRS ...]
                         Limit command to these pairs. Pairs are space-
                         separated.
-  -t {1m,3m,5m,15m,30m,1h,2h,4h,6h,8h,12h,1d,3d,1w,2w,1M,1y} [{1m,3m,5m,15m,30m,1h,2h,4h,6h,8h,12h,1d,3d,1w,2w,1M,1y} ...], --timeframes {1m,3m,5m,15m,30m,1h,2h,4h,6h,8h,12h,1d,3d,1w,2w,1M,1y} [{1m,3m,5m,15m,30m,1h,2h,4h,6h,8h,12h,1d,3d,1w,2w,1M,1y} ...]
+  -t TIMEFRAMES [TIMEFRAMES ...], --timeframes TIMEFRAMES [TIMEFRAMES ...]
                         Specify which tickers to download. Space-separated
                         list. Default: `1m 5m`.
   --exchange EXCHANGE   Exchange name (default: `bittrex`). Only valid if no
                         config is provided.
-  --data-format-ohlcv {json,jsongz,hdf5}
+  --data-format-ohlcv {json,jsongz,hdf5,feather,parquet}
                         Storage format for downloaded candle (OHLCV) data.
                         (default: `json`).
   --data-format-trades {json,jsongz,hdf5}
@@ -351,7 +393,7 @@ Common arguments:
                         `userdir/config.json` or `config.json` whichever
                         exists). Multiple --config options may be used. Can be
                         set to `-` to read config from stdin.
-  -d PATH, --datadir PATH
+  -d PATH, --datadir PATH, --data-dir PATH
                         Path to directory with historical backtesting data.
   --userdir PATH, --user-data-dir PATH
                         Path to userdata directory.
@@ -371,7 +413,7 @@ You can get a list of downloaded data using the `list-data` sub-command.
 ```
 usage: freqtrade list-data [-h] [-v] [--logfile FILE] [-V] [-c PATH] [-d PATH]
                            [--userdir PATH] [--exchange EXCHANGE]
-                           [--data-format-ohlcv {json,jsongz,hdf5}]
+                           [--data-format-ohlcv {json,jsongz,hdf5,feather,parquet}]
                            [-p PAIRS [PAIRS ...]]
                            [--trading-mode {spot,margin,futures}]
                            [--show-timerange]
@@ -380,13 +422,13 @@ optional arguments:
   -h, --help            show this help message and exit
   --exchange EXCHANGE   Exchange name (default: `bittrex`). Only valid if no
                         config is provided.
-  --data-format-ohlcv {json,jsongz,hdf5}
+  --data-format-ohlcv {json,jsongz,hdf5,feather,parquet}
                         Storage format for downloaded candle (OHLCV) data.
                         (default: `json`).
   -p PAIRS [PAIRS ...], --pairs PAIRS [PAIRS ...]
                         Limit command to these pairs. Pairs are space-
                         separated.
-  --trading-mode {spot,margin,futures}
+  --trading-mode {spot,margin,futures}, --tradingmode {spot,margin,futures}
                         Select Trading mode
   --show-timerange      Show timerange available for available data. (May take
                         a while to calculate).
@@ -402,7 +444,7 @@ Common arguments:
                         `userdir/config.json` or `config.json` whichever
                         exists). Multiple --config options may be used. Can be
                         set to `-` to read config from stdin.
-  -d PATH, --datadir PATH
+  -d PATH, --datadir PATH, --data-dir PATH
                         Path to directory with historical backtesting data.
   --userdir PATH, --user-data-dir PATH
                         Path to userdata directory.

docs/developer.md

@@ -409,8 +409,9 @@ Determine if crucial bugfixes have been made between this commit and the current
 
 * Merge the release branch (stable) into this branch.
 * Edit `freqtrade/__init__.py` and add the version matching the current date (for example `2019.7` for July 2019). Minor versions can be `2019.7.1` should we need to do a second release that month. Version numbers must follow allowed versions from PEP0440 to avoid failures pushing to pypi.
-* Commit this part
-* push that branch to the remote and create a PR against the stable branch
+* Commit this part.
+* push that branch to the remote and create a PR against the stable branch.
+* Update develop version to next version following the pattern `2019.8-dev`.
 
 ### Create changelog from git commits
 

docs/exchanges.md

@@ -57,12 +57,20 @@ This configuration enables kraken, as well as rate-limiting to avoid bans from t
 Binance supports [time_in_force](configuration.md#understand-order_time_in_force).
 
 !!! Tip "Stoploss on Exchange"
-    Binance supports `stoploss_on_exchange` and uses `stop-loss-limit` orders. It provides great advantages, so we recommend to benefit from it by enabling stoploss on exchange..
+    Binance supports `stoploss_on_exchange` and uses `stop-loss-limit` orders. It provides great advantages, so we recommend to benefit from it by enabling stoploss on exchange.
+    On futures, Binance supports both `stop-limit` as well as `stop-market` orders. You can use either `"limit"` or `"market"` in the `order_types.stoploss` configuration setting to decide which type to use.
 
-### Binance Blacklist
+### Binance Blacklist recommendation
 
-For Binance, please add `"BNB/<STAKE>"` to your blacklist to avoid issues.
-Accounts having BNB accounts use this to pay for fees - if your first trade happens to be on `BNB`, further trades will consume this position and make the initial BNB trade unsellable as the expected amount is not there anymore.
+For Binance, it is suggested to add `"BNB/<STAKE>"` to your blacklist to avoid issues, unless you are willing to maintain enough extra `BNB` on the account or unless you're willing to disable using `BNB` for fees.
+Binance accounts may use `BNB` for fees, and if a trade happens to be on `BNB`, further trades may consume this position and make the initial BNB trade unsellable as the expected amount is not there anymore.
+
+### Binance sites
+
+Binance has been split into 2, and users must use the correct ccxt exchange ID for their exchange, otherwise API keys are not recognized.
+
+* [binance.com](https://www.binance.com/) - International users. Use exchange id: `binance`.
+* [binance.us](https://www.binance.us/) - US based users. Use exchange id: `binanceus`.
 
 ### Binance Futures
 
@@ -86,12 +94,14 @@ When trading on Binance Futures market, orderbook must be used because there is
   },
 ```
 
-### Binance sites
+#### Binance futures settings
 
-Binance has been split into 2, and users must use the correct ccxt exchange ID for their exchange, otherwise API keys are not recognized.
+Users will also have to have the futures-setting "Position Mode" set to "One-way Mode", and "Asset Mode" set to "Single-Asset Mode".
+These settings will be checked on startup, and freqtrade will show an error if this setting is wrong.
 
-* [binance.com](https://www.binance.com/) - International users. Use exchange id: `binance`.
-* [binance.us](https://www.binance.us/) - US based users. Use exchange id: `binanceus`.
+![Binance futures settings](assets/binance_futures_settings.png)
+
+Freqtrade will not attempt to change these settings.
 
 ## Kraken
 
@@ -205,8 +215,8 @@ Kucoin supports [time_in_force](configuration.md#understand-order_time_in_force)
 
 ### Kucoin Blacklists
 
-For Kucoin, please add `"KCS/<STAKE>"` to your blacklist to avoid issues.
-Accounts having KCS accounts use this to pay for fees - if your first trade happens to be on `KCS`, further trades will consume this position and make the initial KCS trade unsellable as the expected amount is not there anymore.
+For Kucoin, it is suggested to add `"KCS/<STAKE>"` to your blacklist to avoid issues, unless you are willing to maintain enough extra `KCS` on the account or unless you're willing to disable using `KCS` for fees. 
+Kucoin accounts may use `KCS` for fees, and if a trade happens to be on `KCS`, further trades may consume this position and make the initial `KCS` trade unsellable as the expected amount is not there anymore.
 
 ## Huobi
 
@@ -232,7 +242,7 @@ OKX requires a passphrase for each api key, you will therefore need to add this
 
 !!! Warning "Futures"
     OKX Futures has the concept of "position mode" - which can be Net or long/short (hedge mode).
-    Freqtrade supports both modes - but changing the mode mid-trading is not supported and will lead to exceptions and failures to place trades.
+    Freqtrade supports both modes (we recommend to use net mode) - but changing the mode mid-trading is not supported and will lead to exceptions and failures to place trades.
     OKX also only provides MARK candles for the past ~3 months. Backtesting futures prior to that date will therefore lead to slight deviations, as funding-fees cannot be calculated correctly without this data.
 
 ## Gate.io
@@ -278,7 +288,7 @@ For example, to test the order type `FOK` with Kraken, and modify candle limit t
 "exchange": {
     "name": "kraken",
     "_ft_has_params": {
-        "order_time_in_force": ["gtc", "fok"],
+        "order_time_in_force": ["GTC", "FOK"],
         "ohlcv_candle_limit": 200
         }
     //...

docs/faq.md

@@ -4,7 +4,7 @@
 
 Freqtrade supports spot trading only.
 
-### Can I open short positions?
+### Can my bot open short positions?
 
 Freqtrade can open short positions in futures markets.
 This requires the strategy to be made for this - and `"trading_mode": "futures"` in the configuration.
@@ -12,9 +12,9 @@ Please make sure to read the [relevant documentation page](leverage.md) first.
 
 In spot markets, you can in some cases use leveraged spot tokens, which reflect an inverted pair (eg. BTCUP/USD, BTCDOWN/USD, ETHBULL/USD, ETHBEAR/USD,...) which can be traded with Freqtrade.
 
-### Can I trade options or futures?
+### Can my bot trade options or futures?
 
-Futures trading is supported for selected exchanges.
+Futures trading is supported for selected exchanges. Please refer to the [documentation start page](index.md#supported-futures-exchanges-experimental) for an uptodate list of supported exchanges.
 
 ## Beginner Tips & Tricks
 
@@ -22,6 +22,13 @@ Futures trading is supported for selected exchanges.
 
 ## Freqtrade common issues
 
+### Can freqtrade open multiple positions on the same pair in parallel?
+
+No. Freqtrade will only open one position per pair at a time.
+You can however use the [`adjust_trade_position()` callback](strategy-callbacks.md#adjust-trade-position) to adjust an open position.
+
+Backtesting provides an option for this in `--eps` - however this is only there to highlight "hidden" signals, and will not work in live.
+
 ### The bot does not start
 
 Running the bot with `freqtrade trade --config config.json` shows the output `freqtrade: command not found`.
@@ -30,7 +37,7 @@ This could be caused by the following reasons:
 
 * The virtual environment is not active.
   * Run `source .env/bin/activate` to activate the virtual environment.
-* The installation did not work correctly.
+* The installation did not complete successfully.
   * Please check the [Installation documentation](installation.md).
 
 ### I have waited 5 minutes, why hasn't the bot made any trades yet?
@@ -67,7 +74,7 @@ This is not a bot-problem, but will also happen while manual trading.
 While freqtrade can handle this (it'll sell 99 COIN), fees are often below the minimum tradable lot-size (you can only trade full COIN, not 0.9 COIN).
 Leaving the dust (0.9 COIN) on the exchange makes usually sense, as the next time freqtrade buys COIN, it'll eat into the remaining small balance, this time selling everything it bought, and therefore slowly declining the dust balance (although it most likely will never reach exactly 0).
 
-Where possible (e.g. on binance), the use of the exchange's dedicated fee currency will fix this.  
+Where possible (e.g. on binance), the use of the exchange's dedicated fee currency will fix this.
 On binance, it's sufficient to have BNB in your account, and have "Pay fees in BNB" enabled in your profile. Your BNB balance will slowly decline (as it's used to pay fees) - but you'll no longer encounter dust (Freqtrade will include the fees in the profit calculations).
 Other exchanges don't offer such possibilities, where it's simply something you'll have to accept or move to a different exchange.
 
@@ -109,7 +116,7 @@ This warning can point to one of the below problems:
 
 ### I'm getting the "RESTRICTED_MARKET" message in the log
 
-Currently known to happen for US Bittrex users.  
+Currently known to happen for US Bittrex users.
 
 Read [the Bittrex section about restricted markets](exchanges.md#restricted-markets) for more information.
 
@@ -177,8 +184,8 @@ The GPU improvements would only apply to pandas-native calculations - or ones wr
 For hyperopt, freqtrade is using scikit-optimize, which is built on top of scikit-learn.
 Their statement about GPU support is [pretty clear](https://scikit-learn.org/stable/faq.html#will-you-add-gpu-support).
 
-GPU's also are only good at crunching numbers (floating point operations). 
-For hyperopt, we need both number-crunching (find next parameters) and running python code (running backtesting). 
+GPU's also are only good at crunching numbers (floating point operations).
+For hyperopt, we need both number-crunching (find next parameters) and running python code (running backtesting).
 As such, GPU's are not too well suited for most parts of hyperopt.
 
 The benefit of using GPU would therefore be pretty slim - and will not justify the complexity introduced by trying to add GPU support.
@@ -219,9 +226,9 @@ already 8\*10^9\*10 evaluations. A roughly total of 80 billion evaluations.
 Did you run 100 000 evaluations? Congrats, you've done roughly 1 / 100 000 th
 of the search space, assuming that the bot never tests the same parameters more than once.
 
-* The time it takes to run 1000 hyperopt epochs depends on things like: The available cpu, hard-disk, ram, timeframe, timerange, indicator settings, indicator count, amount of coins that hyperopt test strategies on and the resulting trade count - which can be 650 trades in a year or 100000 trades depending if the strategy aims for big profits by trading rarely or for many low profit trades. 
+* The time it takes to run 1000 hyperopt epochs depends on things like: The available cpu, hard-disk, ram, timeframe, timerange, indicator settings, indicator count, amount of coins that hyperopt test strategies on and the resulting trade count - which can be 650 trades in a year or 100000 trades depending if the strategy aims for big profits by trading rarely or for many low profit trades.
 
-Example: 4% profit 650 times vs 0,3% profit a trade 10000 times in a year. If we assume you set the --timerange to 365 days. 
+Example: 4% profit 650 times vs 0,3% profit a trade 10000 times in a year. If we assume you set the --timerange to 365 days.
 
 Example:
 `freqtrade --config config.json --strategy SampleStrategy --hyperopt SampleHyperopt -e 1000 --timerange 20190601-20200601`

docs/freqai-configuration.md

@@ -0,0 +1,217 @@
+# Configuration
+
+FreqAI is configured through the typical [Freqtrade config file](configuration.md) and the standard [Freqtrade strategy](strategy-customization.md). Examples of FreqAI config and strategy files can be found in `config_examples/config_freqai.example.json` and `freqtrade/templates/FreqaiExampleStrategy.py`, respectively.
+
+## Setting up the configuration file
+
+ Although there are plenty of additional parameters to choose from, as highlighted in the [parameter table](freqai-parameter-table.md#parameter-table), a FreqAI config must at minimum include the following parameters (the parameter values are only examples):
+
+```json
+    "freqai": {
+        "enabled": true,
+        "purge_old_models": true,
+        "train_period_days": 30,
+        "backtest_period_days": 7,
+        "identifier" : "unique-id",
+        "feature_parameters" : {
+            "include_timeframes": ["5m","15m","4h"],
+            "include_corr_pairlist": [
+                "ETH/USD",
+                "LINK/USD",
+                "BNB/USD"
+            ],
+            "label_period_candles": 24,
+            "include_shifted_candles": 2,
+            "indicator_periods_candles": [10, 20]
+        },
+        "data_split_parameters" : {
+            "test_size": 0.25
+        },
+        "model_training_parameters" : {
+            "n_estimators": 100
+        },
+    }
+```
+
+A full example config is available in `config_examples/config_freqai.example.json`.
+
+## Building a FreqAI strategy
+
+The FreqAI strategy requires including the following lines of code in the standard [Freqtrade strategy](strategy-customization.md):
+
+```python
+    # user should define the maximum startup candle count (the largest number of candles
+    # passed to any single indicator)
+    startup_candle_count: int = 20
+
+    def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
+
+        # the model will return all labels created by user in `populate_any_indicators`
+        # (& appended targets), an indication of whether or not the prediction should be accepted,
+        # the target mean/std values for each of the labels created by user in
+        # `populate_any_indicators()` for each training period.
+
+        dataframe = self.freqai.start(dataframe, metadata, self)
+
+        return dataframe
+
+    def populate_any_indicators(
+        self, pair, df, tf, informative=None, set_generalized_indicators=False
+    ):
+        """
+        Function designed to automatically generate, name and merge features
+        from user indicated timeframes in the configuration file. User controls the indicators
+        passed to the training/prediction by prepending indicators with `'%-' + coin `
+        (see convention below). I.e. user should not prepend any supporting metrics
+        (e.g. bb_lowerband below) with % unless they explicitly want to pass that metric to the
+        model.
+        :param pair: pair to be used as informative
+        :param df: strategy dataframe which will receive merges from informatives
+        :param tf: timeframe of the dataframe which will modify the feature names
+        :param informative: the dataframe associated with the informative pair
+        :param coin: the name of the coin which will modify the feature names.
+        """
+
+        coin = pair.split('/')[0]
+
+        if informative is None:
+            informative = self.dp.get_pair_dataframe(pair, tf)
+
+        # first loop is automatically duplicating indicators for time periods
+        for t in self.freqai_info["feature_parameters"]["indicator_periods_candles"]:
+            t = int(t)
+            informative[f"%-{coin}rsi-period_{t}"] = ta.RSI(informative, timeperiod=t)
+            informative[f"%-{coin}mfi-period_{t}"] = ta.MFI(informative, timeperiod=t)
+            informative[f"%-{coin}adx-period_{t}"] = ta.ADX(informative, window=t)
+
+        indicators = [col for col in informative if col.startswith("%")]
+        # This loop duplicates and shifts all indicators to add a sense of recency to data
+        for n in range(self.freqai_info["feature_parameters"]["include_shifted_candles"] + 1):
+            if n == 0:
+                continue
+            informative_shift = informative[indicators].shift(n)
+            informative_shift = informative_shift.add_suffix("_shift-" + str(n))
+            informative = pd.concat((informative, informative_shift), axis=1)
+
+        df = merge_informative_pair(df, informative, self.config["timeframe"], tf, ffill=True)
+        skip_columns = [
+            (s + "_" + tf) for s in ["date", "open", "high", "low", "close", "volume"]
+        ]
+        df = df.drop(columns=skip_columns)
+
+        # Add generalized indicators here (because in live, it will call this
+        # function to populate indicators during training). Notice how we ensure not to
+        # add them multiple times
+        if set_generalized_indicators:
+
+            # user adds targets here by prepending them with &- (see convention below)
+            # If user wishes to use multiple targets, a multioutput prediction model
+            # needs to be used such as templates/CatboostPredictionMultiModel.py
+            df["&-s_close"] = (
+                df["close"]
+                .shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
+                .rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
+                .mean()
+                / df["close"]
+                - 1
+            )
+
+        return df
+
+
+```
+
+Notice how the `populate_any_indicators()` is where [features](freqai-feature-engineering.md#feature-engineering) and labels/targets are added. A full example strategy is available in `templates/FreqaiExampleStrategy.py`. 
+
+Notice also the location of the labels under `if set_generalized_indicators:` at the bottom of the example. This is where single features and labels/targets should be added to the feature set to avoid duplication of them from various configuration parameters that multiply the feature set, such as `include_timeframes`.
+
+!!! Note
+    The `self.freqai.start()` function cannot be called outside the `populate_indicators()`.
+
+!!! Note
+    Features **must** be defined in `populate_any_indicators()`. Defining FreqAI features in `populate_indicators()`
+    will cause the algorithm to fail in live/dry mode. In order to add generalized features that are not associated with a specific pair or timeframe, the following structure inside `populate_any_indicators()` should be used
+    (as exemplified in `freqtrade/templates/FreqaiExampleStrategy.py`):
+
+    ```python
+        def populate_any_indicators(self, metadata, pair, df, tf, informative=None, coin="", set_generalized_indicators=False):
+
+            ...
+
+            # Add generalized indicators here (because in live, it will call only this function to populate
+            # indicators for retraining). Notice how we ensure not to add them multiple times by associating
+            # these generalized indicators to the basepair/timeframe
+            if set_generalized_indicators:
+                df['%-day_of_week'] = (df["date"].dt.dayofweek + 1) / 7
+                df['%-hour_of_day'] = (df['date'].dt.hour + 1) / 25
+
+                # user adds targets here by prepending them with &- (see convention below)
+                # If user wishes to use multiple targets, a multioutput prediction model
+                # needs to be used such as templates/CatboostPredictionMultiModel.py
+                df["&-s_close"] = (
+                    df["close"]
+                    .shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
+                    .rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
+                    .mean()
+                    / df["close"]
+                    - 1
+                    )
+    ```
+
+    Please see the example script located in `freqtrade/templates/FreqaiExampleStrategy.py` for a full example of `populate_any_indicators()`.
+
+## Important dataframe key patterns
+
+Below are the values you can expect to include/use inside a typical strategy dataframe (`df[]`):
+
+|  DataFrame Key | Description |
+|------------|-------------|
+| `df['&*']` | Any dataframe column prepended with `&` in `populate_any_indicators()` is treated as a training target (label) inside FreqAI (typically following the naming convention `&-s*`). For example, to predict the close price 40 candles into the future, you would set `df['&-s_close'] = df['close'].shift(-self.freqai_info["feature_parameters"]["label_period_candles"])` with `"label_period_candles": 40` in the config. FreqAI makes the predictions and gives them back under the same key (`df['&-s_close']`) to be used in `populate_entry/exit_trend()`. <br> **Datatype:** Depends on the output of the model.
+| `df['&*_std/mean']` | Standard deviation and mean values of the defined labels during training (or live tracking with `fit_live_predictions_candles`). Commonly used to understand the rarity of a prediction (use the z-score as shown in `templates/FreqaiExampleStrategy.py` and explained [here](#creating-a-dynamic-target-threshold) to evaluate how often a particular prediction was observed during training or historically with `fit_live_predictions_candles`). <br> **Datatype:** Float.
+| `df['do_predict']` | Indication of an outlier data point. The return value is integer between -2 and 2, which lets you know if the prediction is trustworthy or not. `do_predict==1` means that the prediction is trustworthy. If the Dissimilarity Index (DI, see details [here](freqai-feature-engineering.md#identifying-outliers-with-the-dissimilarity-index-di)) of the input data point is above the threshold defined in the config, FreqAI will subtract 1 from `do_predict`, resulting in `do_predict==0`. If `use_SVM_to_remove_outliers()` is active, the Support Vector Machine (SVM, see details [here](freqai-feature-engineering.md#identifying-outliers-using-a-support-vector-machine-svm)) may also detect outliers in training and prediction data. In this case, the SVM will also subtract 1 from `do_predict`. If the input data point was considered an outlier by the SVM but not by the DI, or vice versa, the result will be `do_predict==0`. If both the DI and the SVM considers the input data point to be an outlier, the result will be `do_predict==-1`. As with the SVM, if `use_DBSCAN_to_remove_outliers` is active, DBSCAN (see details [here](freqai-feature-engineering.md#identifying-outliers-with-dbscan)) may also detect outliers and subtract 1 from `do_predict`. Hence, if both the SVM and DBSCAN are active and identify a datapoint that was above the DI threshold as an outlier, the result will be `do_predict==-2`. A particular case is when `do_predict == 2`, which means that the model has expired due to exceeding `expired_hours`. <br> **Datatype:** Integer between -2 and 2.
+| `df['DI_values']` | Dissimilarity Index (DI) values are proxies for the level of confidence FreqAI has in the prediction. A lower DI means the prediction is close to the training data, i.e., higher prediction confidence. See details about the DI [here](freqai-feature-engineering.md#identifying-outliers-with-the-dissimilarity-index-di). <br> **Datatype:** Float.
+| `df['%*']` | Any dataframe column prepended with `%` in `populate_any_indicators()` is treated as a training feature. For example, you can include the RSI in the training feature set (similar to in `templates/FreqaiExampleStrategy.py`) by setting `df['%-rsi']`. See more details on how this is done [here](freqai-feature-engineering.md). <br> **Note:** Since the number of features prepended with `%` can multiply very quickly (10s of thousands of features are easily engineered using the multiplictative functionality of, e.g., `include_shifted_candles` and `include_timeframes` as described in the [parameter table](freqai-parameter-table.md)), these features are removed from the dataframe that is returned from FreqAI to the strategy. To keep a particular type of feature for plotting purposes, you would prepend it with `%%`. <br> **Datatype:** Depends on the output of the model.
+
+## Setting the `startup_candle_count`
+
+The `startup_candle_count` in the FreqAI strategy needs to be set up in the same way as in the standard Freqtrade strategy (see details [here](strategy-customization.md#strategy-startup-period)). This value is used by Freqtrade to ensure that a sufficient amount of data is provided when calling the `dataprovider`, to avoid any NaNs at the beginning of the first training. You can easily set this value by identifying the longest period (in candle units) which is passed to the indicator creation functions (e.g., Ta-Lib functions). In the presented example, `startup_candle_count` is 20 since this is the maximum value in `indicators_periods_candles`.
+
+!!! Note
+    There are instances where the Ta-Lib functions actually require more data than just the passed `period` or else the feature dataset gets populated with NaNs. Anecdotally, multiplying the `startup_candle_count` by 2 always leads to a fully NaN free training dataset. Hence, it is typically safest to multiply the expected `startup_candle_count` by 2. Look out for this log message to confirm that the data is clean:
+
+    ```
+    2022-08-31 15:14:04 - freqtrade.freqai.data_kitchen - INFO - dropped 0 training points due to NaNs in populated dataset 4319.
+    ```
+
+## Creating a dynamic target threshold
+
+Deciding when to enter or exit a trade can be done in a dynamic way to reflect current market conditions. FreqAI allows you to return additional information from the training of a model (more info [here](freqai-feature-engineering.md#returning-additional-info-from-training)). For example, the `&*_std/mean` return values describe the statistical distribution of the target/label *during the most recent training*. Comparing a given prediction to these values allows you to know the rarity of the prediction. In `templates/FreqaiExampleStrategy.py`, the `target_roi` and  `sell_roi` are defined to be 1.25 z-scores away from the mean which causes predictions that are closer to the mean to be filtered out. 
+
+```python
+dataframe["target_roi"] = dataframe["&-s_close_mean"] + dataframe["&-s_close_std"] * 1.25
+dataframe["sell_roi"] = dataframe["&-s_close_mean"] - dataframe["&-s_close_std"] * 1.25
+```
+
+To consider the population of *historical predictions* for creating the dynamic target instead of information from the training as discussed above, you would set `fit_live_prediction_candles` in the config to the number of historical prediction candles you wish to use to generate target statistics.
+
+```json
+    "freqai": {
+        "fit_live_prediction_candles": 300,
+    }
+```
+
+If this value is set, FreqAI will initially use the predictions from the training data and subsequently begin introducing real prediction data as it is generated. FreqAI will save this historical data to be reloaded if you stop and restart a model with the same `identifier`.
+
+## Using different prediction models
+
+FreqAI has multiple example prediction model libraries that are ready to be used as is via the flag `--freqaimodel`. These libraries include `Catboost`, `LightGBM`, and `XGBoost` regression, classification, and multi-target models, and can be found in `freqai/prediction_models/`. However, it is possible to customize and create your own prediction models using the `IFreqaiModel` class. You are encouraged to inherit `fit()`, `train()`, and `predict()` to let these customize various aspects of the training procedures.
+
+### Setting classifier targets
+
+FreqAI includes a variety of classifiers, such as the `CatboostClassifier` via the flag `--freqaimodel CatboostClassifier`. If you elects to use a classifier, the classes need to be set using strings. For example:
+
+```python
+df['&s-up_or_down'] = np.where( df["close"].shift(-100) > df["close"], 'up', 'down')
+```
+
+Additionally, the example classifier models do not accommodate multiple labels, but they do allow multi-class classification within a single label column.

docs/freqai-developers.md

@@ -0,0 +1,78 @@
+# Development
+
+## Project architecture
+
+The architecture and functions of FreqAI are generalized to encourages development of unique features, functions, models, etc.
+
+The class structure and a detailed algorithmic overview is depicted in the following diagram:
+
+![image](assets/freqai_algorithm-diagram.jpg)
+
+As shown, there are three distinct objects comprising FreqAI:
+
+* **IFreqaiModel** - A singular persistent object containing all the necessary logic to collect, store, and process data, engineer features, run training, and inference models.
+* **FreqaiDataKitchen** - A non-persistent object which is created uniquely for each unique asset/model. Beyond metadata, it also contains a variety of data processing tools.
+* **FreqaiDataDrawer** - A singular persistent object containing all the historical predictions, models, and save/load methods.
+
+There are a variety of built-in [prediction models](freqai-configuration.md#using-different-prediction-models) which inherit directly from `IFreqaiModel`. Each of these models have full access to all methods in `IFreqaiModel` and can therefore override any of those functions at will. However, advanced users will likely stick to overriding `fit()`, `train()`, `predict()`, and `data_cleaning_train/predict()`.
+
+## Data handling
+
+FreqAI aims to organize model files, prediction data, and meta data in a way that simplifies post-processing and enhances crash resilience by automatic data reloading. The data is saved in a file structure,`user_data_dir/models/`, which contains all the data associated with the trainings and backtests. The `FreqaiDataKitchen()` relies heavily on the file structure for proper training and inferencing and should therefore not be manually modified.
+
+### File structure
+
+The file structure is automatically generated based on the model `identifier` set in the [config](freqai-configuration.md#setting-up-the-configuration-file). The following structure shows where the data is stored for post processing:
+
+| Structure | Description |
+|-----------|-------------|
+| `config_*.json` | A copy of the model specific configuration file. |
+| `historic_predictions.pkl` | A file containing all historic predictions generated during the lifetime of the `identifier` model during live deployment. `historic_predictions.pkl` is used to reload the model after a crash or a config change. A backup file is always held in case of corruption on the main file. FreqAI **automatically** detects corruption and replaces the corrupted file with the backup. |
+| `pair_dictionary.json` | A file containing the training queue as well as the on disk location of the most recently trained model. |
+| `sub-train-*_TIMESTAMP` | A folder containing all the files associated with a single model, such as: <br>
+|| `*_metadata.json` - Metadata for the model, such as normalization max/min, expected training feature list, etc. <br>
+|| `*_model.*` - The model file saved to disk for reloading from a crash. Can be `joblib` (typical boosting libs), `zip` (stable_baselines), `hd5` (keras type), etc. <br>
+|| `*_pca_object.pkl` - The [Principal component analysis (PCA)](freqai-feature-engineering.md#data-dimensionality-reduction-with-principal-component-analysis) transform (if `principal_component_analysis: True` is set in the config) which will be used to transform unseen prediction features. <br>
+|| `*_svm_model.pkl` - The [Support Vector Machine (SVM)](freqai-feature-engineering.md#identifying-outliers-using-a-support-vector-machine-svm) model (if `use_SVM_to_remove_outliers: True` is set in the config) which is used to detect outliers in unseen prediction features. <br>
+|| `*_trained_df.pkl` - The dataframe containing all the training features used to train the `identifier` model. This is used for computing the [Dissimilarity Index (DI)](freqai-feature-engineering.md#identifying-outliers-with-the-dissimilarity-index-di) and can also be used for post-processing. <br>
+|| `*_trained_dates.df.pkl` - The dates associated with the `trained_df.pkl`, which is useful for post-processing. |
+
+The example file structure would look like this:
+
+```
+├── models
+│   └── unique-id
+│       ├── config_freqai.example.json
+│       ├── historic_predictions.backup.pkl
+│       ├── historic_predictions.pkl
+│       ├── pair_dictionary.json
+│       ├── sub-train-1INCH_1662821319
+│       │   ├── cb_1inch_1662821319_metadata.json
+│       │   ├── cb_1inch_1662821319_model.joblib
+│       │   ├── cb_1inch_1662821319_pca_object.pkl
+│       │   ├── cb_1inch_1662821319_svm_model.joblib
+│       │   ├── cb_1inch_1662821319_trained_dates_df.pkl
+│       │   └── cb_1inch_1662821319_trained_df.pkl
+│       ├── sub-train-1INCH_1662821371
+│       │   ├── cb_1inch_1662821371_metadata.json
+│       │   ├── cb_1inch_1662821371_model.joblib
+│       │   ├── cb_1inch_1662821371_pca_object.pkl
+│       │   ├── cb_1inch_1662821371_svm_model.joblib
+│       │   ├── cb_1inch_1662821371_trained_dates_df.pkl
+│       │   └── cb_1inch_1662821371_trained_df.pkl
+│       ├── sub-train-ADA_1662821344
+│       │   ├── cb_ada_1662821344_metadata.json
+│       │   ├── cb_ada_1662821344_model.joblib
+│       │   ├── cb_ada_1662821344_pca_object.pkl
+│       │   ├── cb_ada_1662821344_svm_model.joblib
+│       │   ├── cb_ada_1662821344_trained_dates_df.pkl
+│       │   └── cb_ada_1662821344_trained_df.pkl
+│       └── sub-train-ADA_1662821399
+│           ├── cb_ada_1662821399_metadata.json
+│           ├── cb_ada_1662821399_model.joblib
+│           ├── cb_ada_1662821399_pca_object.pkl
+│           ├── cb_ada_1662821399_svm_model.joblib
+│           ├── cb_ada_1662821399_trained_dates_df.pkl
+│           └── cb_ada_1662821399_trained_df.pkl
+
+```

docs/freqai-feature-engineering.md

@@ -0,0 +1,268 @@
+# Feature engineering
+
+## Defining the features
+
+Low level feature engineering is performed in the user strategy within a function called `populate_any_indicators()`. That function sets the `base features` such as, `RSI`, `MFI`, `EMA`, `SMA`, time of day, volume, etc. The `base features` can be custom indicators or they can be imported from any technical-analysis library that you can find. One important syntax rule is that all `base features` string names are prepended with `%`, while labels/targets are prepended with `&`.
+
+Meanwhile, high level feature engineering is handled within `"feature_parameters":{}` in the FreqAI config. Within this file, it is possible to decide large scale feature expansions on top of the `base_features` such as "including correlated pairs" or "including informative timeframes" or even "including recent candles."
+
+It is advisable to start from the template `populate_any_indicators()` in the source provided example strategy (found in `templates/FreqaiExampleStrategy.py`) to ensure that the feature definitions are following the correct conventions. Here is an example of how to set the indicators and labels in the strategy:
+
+```python
+    def populate_any_indicators(
+        self, pair, df, tf, informative=None, set_generalized_indicators=False
+    ):
+        """
+        Function designed to automatically generate, name, and merge features
+        from user-indicated timeframes in the configuration file. The user controls the indicators
+        passed to the training/prediction by prepending indicators with `'%-' + coin `
+        (see convention below). I.e., the user should not prepend any supporting metrics
+        (e.g., bb_lowerband below) with % unless they explicitly want to pass that metric to the
+        model.
+        :param pair: pair to be used as informative
+        :param df: strategy dataframe which will receive merges from informatives
+        :param tf: timeframe of the dataframe which will modify the feature names
+        :param informative: the dataframe associated with the informative pair
+        :param coin: the name of the coin which will modify the feature names.
+        """
+
+        coin = pair.split('/')[0]
+
+        if informative is None:
+            informative = self.dp.get_pair_dataframe(pair, tf)
+
+        # first loop is automatically duplicating indicators for time periods
+        for t in self.freqai_info["feature_parameters"]["indicator_periods_candles"]:
+            t = int(t)
+            informative[f"%-{coin}rsi-period_{t}"] = ta.RSI(informative, timeperiod=t)
+            informative[f"%-{coin}mfi-period_{t}"] = ta.MFI(informative, timeperiod=t)
+            informative[f"%-{coin}adx-period_{t}"] = ta.ADX(informative, window=t)
+
+            bollinger = qtpylib.bollinger_bands(
+                qtpylib.typical_price(informative), window=t, stds=2.2
+            )
+            informative[f"{coin}bb_lowerband-period_{t}"] = bollinger["lower"]
+            informative[f"{coin}bb_middleband-period_{t}"] = bollinger["mid"]
+            informative[f"{coin}bb_upperband-period_{t}"] = bollinger["upper"]
+
+            informative[f"%-{coin}bb_width-period_{t}"] = (
+                informative[f"{coin}bb_upperband-period_{t}"]
+                - informative[f"{coin}bb_lowerband-period_{t}"]
+            ) / informative[f"{coin}bb_middleband-period_{t}"]
+            informative[f"%-{coin}close-bb_lower-period_{t}"] = (
+                informative["close"] / informative[f"{coin}bb_lowerband-period_{t}"]
+            )
+
+            informative[f"%-{coin}relative_volume-period_{t}"] = (
+                informative["volume"] / informative["volume"].rolling(t).mean()
+            )
+
+        indicators = [col for col in informative if col.startswith("%")]
+        # This loop duplicates and shifts all indicators to add a sense of recency to data
+        for n in range(self.freqai_info["feature_parameters"]["include_shifted_candles"] + 1):
+            if n == 0:
+                continue
+            informative_shift = informative[indicators].shift(n)
+            informative_shift = informative_shift.add_suffix("_shift-" + str(n))
+            informative = pd.concat((informative, informative_shift), axis=1)
+
+        df = merge_informative_pair(df, informative, self.config["timeframe"], tf, ffill=True)
+        skip_columns = [
+            (s + "_" + tf) for s in ["date", "open", "high", "low", "close", "volume"]
+        ]
+        df = df.drop(columns=skip_columns)
+
+        # Add generalized indicators here (because in live, it will call this
+        # function to populate indicators during training). Notice how we ensure not to
+        # add them multiple times
+        if set_generalized_indicators:
+            df["%-day_of_week"] = (df["date"].dt.dayofweek + 1) / 7
+            df["%-hour_of_day"] = (df["date"].dt.hour + 1) / 25
+
+            # user adds targets here by prepending them with &- (see convention below)
+            # If user wishes to use multiple targets, a multioutput prediction model
+            # needs to be used such as templates/CatboostPredictionMultiModel.py
+            df["&-s_close"] = (
+                df["close"]
+                .shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
+                .rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
+                .mean()
+                / df["close"]
+                - 1
+            )
+
+        return df
+```
+
+In the presented example, the user does not wish to pass the `bb_lowerband` as a feature to the model,
+and has therefore not prepended it with `%`. The user does, however, wish to pass `bb_width` to the
+model for training/prediction and has therefore prepended it with `%`.
+
+After having defined the `base features`, the next step is to expand upon them using the powerful `feature_parameters` in the configuration file:
+
+```json
+    "freqai": {
+        //...
+        "feature_parameters" : {
+            "include_timeframes": ["5m","15m","4h"],
+            "include_corr_pairlist": [
+                "ETH/USD",
+                "LINK/USD",
+                "BNB/USD"
+            ],
+            "label_period_candles": 24,
+            "include_shifted_candles": 2,
+            "indicator_periods_candles": [10, 20]
+        },
+        //...
+    }
+```
+
+The `include_timeframes` in the config above are the timeframes (`tf`) of each call to `populate_any_indicators()` in the strategy. In the presented case, the user is asking for the `5m`, `15m`, and `4h` timeframes of the `rsi`, `mfi`, `roc`, and `bb_width` to be included in the feature set.
+
+You can ask for each of the defined features to be included also for informative pairs using the `include_corr_pairlist`. This means that the feature set will include all the features from `populate_any_indicators` on all the `include_timeframes` for each of the correlated pairs defined in the config (`ETH/USD`, `LINK/USD`, and `BNB/USD` in the presented example).
+
+`include_shifted_candles` indicates the number of previous candles to include in the feature set. For example, `include_shifted_candles: 2` tells FreqAI to include the past 2 candles for each of the features in the feature set.
+
+In total, the number of features the user of the presented example strat has created is: length of `include_timeframes` * no. features in `populate_any_indicators()` * length of `include_corr_pairlist` * no. `include_shifted_candles` * length of `indicator_periods_candles`
+ $= 3 * 3 * 3 * 2 * 2 = 108$.
+
+### Returning additional info from training
+
+Important metrics can be returned to the strategy at the end of each model training by assigning them to `dk.data['extra_returns_per_train']['my_new_value'] = XYZ` inside the custom prediction model class. 
+
+FreqAI takes the `my_new_value` assigned in this dictionary and expands it to fit the dataframe that is returned to the strategy. You can then use the returned metrics in your strategy through `dataframe['my_new_value']`. An example of how return values can be used in FreqAI are the `&*_mean` and `&*_std` values that are used to [created a dynamic target threshold](freqai-configuration.md#creating-a-dynamic-target-threshold).
+
+Another example, where the user wants to use live metrics from the trade database, is shown below:
+
+```json
+    "freqai": {
+        "extra_returns_per_train": {"total_profit": 4}
+    }
+```
+
+You need to set the standard dictionary in the config so that FreqAI can return proper dataframe shapes. These values will likely be overridden by the prediction model, but in the case where the model has yet to set them, or needs a default initial value, the pre-set values are what will be returned.
+
+## Feature normalization
+
+FreqAI is strict when it comes to data normalization. The train features, $X^{train}$, are always normalized to [-1, 1] using a shifted min-max normalization:
+
+$$X^{train}_{norm} = 2 * \frac{X^{train} - X^{train}.min()}{X^{train}.max() - X^{train}.min()} - 1$$
+
+All other data (test data and unseen prediction data in dry/live/backtest) is always automatically normalized to the training feature space according to industry standards. FreqAI stores all the metadata required to ensure that test and prediction features will be properly normalized and that predictions are properly denormalized. For this reason, it is not recommended to eschew industry standards and modify FreqAI internals - however - advanced users can do so by inheriting `train()` in their custom `IFreqaiModel` and using their own normalization functions.
+
+## Data dimensionality reduction with Principal Component Analysis
+
+You can reduce the dimensionality of your features by activating the `principal_component_analysis` in the config:
+
+```json
+    "freqai": {
+        "feature_parameters" : {
+            "principal_component_analysis": true
+        }
+    }
+```
+
+This will perform PCA on the features and reduce their dimensionality so that the explained variance of the data set is >= 0.999. Reducing data dimensionality makes training the model faster and hence allows for more up-to-date models. 
+
+## Inlier metric
+
+The `inlier_metric` is a metric aimed at quantifying how similar a the features of a data point are to the most recent historic data points. 
+
+You define the lookback window by setting `inlier_metric_window` and FreqAI computes the distance between the present time point and each of the previous `inlier_metric_window` lookback points. A Weibull function is fit to each of the lookback distributions and its cumulative distribution function (CDF) is used to produce a quantile for each lookback point. The `inlier_metric` is then computed for each time point as the average of the corresponding lookback quantiles. The figure below explains the concept for an `inlier_metric_window` of 5.
+
+![inlier-metric](assets/freqai_inlier-metric.jpg)
+
+FreqAI adds the `inlier_metric` to the training features and hence gives the model access to a novel type of temporal information. 
+
+This function does **not** remove outliers from the data set.
+
+## Weighting features for temporal importance
+
+FreqAI allows you to set a `weight_factor` to weight recent data more strongly than past data via an exponential function:
+
+$$ W_i = \exp(\frac{-i}{\alpha*n}) $$
+
+where $W_i$ is the weight of data point $i$ in a total set of $n$ data points. Below is a figure showing the effect of different weight factors on the data points in a feature set.
+
+![weight-factor](assets/freqai_weight-factor.jpg)
+
+## Outlier detection
+
+Equity and crypto markets suffer from a high level of non-patterned noise in the form of outlier data points. FreqAI implements a variety of methods to identify such outliers and hence mitigate risk.
+
+### Identifying outliers with the Dissimilarity Index (DI)
+
+ The Dissimilarity Index (DI) aims to quantify the uncertainty associated with each prediction made by the model. 
+
+You can tell FreqAI to remove outlier data points from the training/test data sets using the DI by including the following statement in the config:
+
+```json
+    "freqai": {
+        "feature_parameters" : {
+            "DI_threshold": 1
+        }
+    }
+```
+
+ The DI allows predictions which are outliers (not existent in the model feature space) to be thrown out due to low levels of certainty. To do so, FreqAI measures the distance between each training data point (feature vector), $X_{a}$, and all other training data points:
+
+$$ d_{ab} = \sqrt{\sum_{j=1}^p(X_{a,j}-X_{b,j})^2} $$
+
+where $d_{ab}$ is the distance between the normalized points $a$ and $b$, and $p$ is the number of features, i.e., the length of the vector $X$. The characteristic distance, $\overline{d}$, for a set of training data points is simply the mean of the average distances:
+
+$$ \overline{d} = \sum_{a=1}^n(\sum_{b=1}^n(d_{ab}/n)/n) $$
+
+$\overline{d}$ quantifies the spread of the training data, which is compared to the distance between a new prediction feature vectors, $X_k$ and all the training data:
+
+$$ d_k = \arg \min d_{k,i} $$
+
+This enables the estimation of the Dissimilarity Index as:
+
+$$ DI_k = d_k/\overline{d} $$
+
+You can tweak the DI through the `DI_threshold` to increase or decrease the extrapolation of the trained model. A higher `DI_threshold` means that the DI is more lenient and allows predictions further away from the training data to be used whilst a lower `DI_threshold` has the opposite effect and hence discards more predictions.
+
+Below is a figure that describes the DI for a 3D data set.
+
+![DI](assets/freqai_DI.jpg)
+
+### Identifying outliers using a Support Vector Machine (SVM)
+
+You can tell FreqAI to remove outlier data points from the training/test data sets using a Support Vector Machine (SVM) by including the following statement in the config:
+
+```json
+    "freqai": {
+        "feature_parameters" : {
+            "use_SVM_to_remove_outliers": true
+        }
+    }
+```
+
+The SVM will be trained on the training data and any data point that the SVM deems to be beyond the feature space will be removed.
+
+FreqAI uses `sklearn.linear_model.SGDOneClassSVM` (details are available on scikit-learn's webpage [here](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.SGDOneClassSVM.html) (external website)) and you can elect to provide additional parameters for the SVM, such as `shuffle`, and `nu`.
+
+The parameter `shuffle` is by default set to `False` to ensure consistent results. If it is set to `True`, running the SVM multiple times on the same data set might result in different outcomes due to `max_iter` being to low for the algorithm to reach the demanded `tol`. Increasing `max_iter` solves this issue but causes the procedure to take longer time.
+
+The parameter `nu`, *very* broadly, is the amount of data points that should be considered outliers and should be between 0 and 1.
+
+### Identifying outliers with DBSCAN
+
+You can configure FreqAI to use DBSCAN to cluster and remove outliers from the training/test data set or incoming outliers from predictions, by activating `use_DBSCAN_to_remove_outliers` in the config:
+
+```json
+    "freqai": {
+        "feature_parameters" : {
+            "use_DBSCAN_to_remove_outliers": true
+        }
+    }
+```
+
+DBSCAN is an unsupervised machine learning algorithm that clusters data without needing to know how many clusters there should be.
+
+Given a number of data points $N$, and a distance $\varepsilon$, DBSCAN clusters the data set by setting all data points that have $N-1$ other data points within a distance of $\varepsilon$ as *core points*. A data point that is within a distance of $\varepsilon$ from a *core point* but that does not have $N-1$ other data points within a distance of $\varepsilon$ from itself is considered an *edge point*. A cluster is then the collection of *core points* and *edge points*. Data points that have no other data points at a distance $<\varepsilon$ are considered outliers. The figure below shows a cluster with $N = 3$.
+
+![dbscan](assets/freqai_dbscan.jpg)
+
+FreqAI uses `sklearn.cluster.DBSCAN` (details are available on scikit-learn's webpage [here](https://scikit-learn.org/stable/modules/generated/sklearn.cluster.DBSCAN.html) (external website)) with `min_samples` ($N$) taken as 1/4 of the no. of time points (candles) in the feature set. `eps` ($\varepsilon$) is computed automatically as the elbow point in the *k-distance graph* computed from the nearest neighbors in the pairwise distances of all data points in the feature set.

docs/freqai-parameter-table.md

@@ -0,0 +1,51 @@
+# Parameter table
+
+The table below will list all configuration parameters available for FreqAI. Some of the parameters are exemplified in `config_examples/config_freqai.example.json`.
+
+Mandatory parameters are marked as **Required** and have to be set in one of the suggested ways.
+
+|  Parameter | Description |
+|------------|-------------|
+|  |  **General configuration parameters**
+| `freqai` | **Required.** <br> The parent dictionary containing all the parameters for controlling FreqAI. <br> **Datatype:** Dictionary.
+| `train_period_days` | **Required.** <br> Number of days to use for the training data (width of the sliding window). <br> **Datatype:** Positive integer.
+| `backtest_period_days` | **Required.** <br> Number of days to inference from the trained model before sliding the `train_period_days` window defined above, and retraining the model during backtesting (more info [here](freqai-running.md#backtesting)). This can be fractional days, but beware that the provided `timerange` will be divided by this number to yield the number of trainings necessary to complete the backtest. <br> **Datatype:** Float.
+| `identifier` | **Required.** <br> A unique ID for the current model. If models are saved to disk, the `identifier` allows for reloading specific pre-trained models/data. <br> **Datatype:** String.
+| `live_retrain_hours` | Frequency of retraining during dry/live runs. <br> **Datatype:** Float > 0. <br> Default: `0` (models retrain as often as possible).
+| `expiration_hours` | Avoid making predictions if a model is more than `expiration_hours` old. <br> **Datatype:** Positive integer. <br> Default: `0` (models never expire).
+| `purge_old_models` | Delete obsolete models. <br> **Datatype:** Boolean. <br> Default: `False` (all historic models remain on disk).
+| `save_backtest_models` | Save models to disk when running backtesting. Backtesting operates most efficiently by saving the prediction data and reusing them directly for subsequent runs (when you wish to tune entry/exit parameters). Saving backtesting models to disk also allows to use the same model files for starting a dry/live instance with the same model `identifier`. <br> **Datatype:** Boolean. <br> Default: `False` (no models are saved).
+| `fit_live_predictions_candles` | Number of historical candles to use for computing target (label) statistics from prediction data, instead of from the training dataset (more information can be found [here](freqai-configuration.md#creating-a-dynamic-target-threshold)). <br> **Datatype:** Positive integer.
+| `follow_mode` | Use a `follower` that will look for models associated with a specific `identifier` and load those for inferencing. A `follower` will **not** train new models. <br> **Datatype:** Boolean. <br> Default: `False`.
+| `continual_learning` | Use the final state of the most recently trained model as starting point for the new model, allowing for incremental learning (more information can be found [here](freqai-running.md#continual-learning)). <br> **Datatype:** Boolean. <br> Default: `False`.
+|  |  **Feature parameters**
+| `feature_parameters` | A dictionary containing the parameters used to engineer the feature set. Details and examples are shown [here](freqai-feature-engineering.md). <br> **Datatype:** Dictionary.
+| `include_timeframes` | A list of timeframes that all indicators in `populate_any_indicators` will be created for. The list is added as features to the base indicators dataset. <br> **Datatype:** List of timeframes (strings).
+| `include_corr_pairlist` | A list of correlated coins that FreqAI will add as additional features to all `pair_whitelist` coins. All indicators set in `populate_any_indicators` during feature engineering (see details [here](freqai-feature-engineering.md)) will be created for each correlated coin. The correlated coins features are added to the base indicators dataset. <br> **Datatype:** List of assets (strings).
+| `label_period_candles` | Number of candles into the future that the labels are created for. This is used in `populate_any_indicators` (see `templates/FreqaiExampleStrategy.py` for detailed usage). You can create custom labels and choose whether to make use of this parameter or not. <br> **Datatype:** Positive integer.
+| `include_shifted_candles` | Add features from previous candles to subsequent candles with the intent of adding historical information. If used, FreqAI will duplicate and shift all features from the `include_shifted_candles` previous candles so that the information is available for the subsequent candle. <br> **Datatype:** Positive integer.
+| `weight_factor` | Weight training data points according to their recency (see details [here](freqai-feature-engineering.md#weighting-features-for-temporal-importance)). <br> **Datatype:** Positive float (typically < 1).
+| `indicator_max_period_candles` | **No longer used (#7325)**. Replaced by `startup_candle_count` which is set in the [strategy](freqai-configuration.md#building-a-freqai-strategy). `startup_candle_count` is timeframe independent and defines the maximum *period* used in `populate_any_indicators()` for indicator creation. FreqAI uses this parameter together with the maximum timeframe in `include_time_frames` to calculate how many data points to download such that the first data point does not include a NaN. <br> **Datatype:** Positive integer.
+| `indicator_periods_candles` | Time periods to calculate indicators for. The indicators are added to the base indicator dataset. <br> **Datatype:** List of positive integers.
+| `principal_component_analysis` | Automatically reduce the dimensionality of the data set using Principal Component Analysis. See details about how it works [here](#reducing-data-dimensionality-with-principal-component-analysis) <br> **Datatype:** Boolean. <br> Default: `False`.
+| `plot_feature_importances` | Create a feature importance plot for each model for the top/bottom `plot_feature_importances` number of features. <br> **Datatype:** Integer. <br> Default: `0`.
+| `DI_threshold` | Activates the use of the Dissimilarity Index for outlier detection when set to > 0. See details about how it works [here](freqai-feature-engineering.md#identifying-outliers-with-the-dissimilarity-index-di). <br> **Datatype:** Positive float (typically < 1).
+| `use_SVM_to_remove_outliers` | Train a support vector machine to detect and remove outliers from the training dataset, as well as from incoming data points. See details about how it works [here](freqai-feature-engineering.md#identifying-outliers-using-a-support-vector-machine-svm). <br> **Datatype:** Boolean.
+| `svm_params` | All parameters available in Sklearn's `SGDOneClassSVM()`. See details about some select parameters [here](freqai-feature-engineering.md#identifying-outliers-using-a-support-vector-machine-svm). <br> **Datatype:** Dictionary.
+| `use_DBSCAN_to_remove_outliers` | Cluster data using the DBSCAN algorithm to identify and remove outliers from training and prediction data. See details about how it works [here](freqai-feature-engineering.md#identifying-outliers-with-dbscan). <br> **Datatype:** Boolean. 
+| `inlier_metric_window` | If set, FreqAI adds an `inlier_metric` to the training feature set and set the lookback to be the `inlier_metric_window`, i.e., the number of previous time points to compare the current candle to. Details of how the `inlier_metric` is computed can be found [here](freqai-feature-engineering.md#inlier-metric). <br> **Datatype:** Integer. <br> Default: `0`.
+| `noise_standard_deviation` | If set, FreqAI adds noise to the training features with the aim of preventing overfitting. FreqAI generates random deviates from a gaussian distribution with a standard deviation of `noise_standard_deviation` and adds them to all data points. `noise_standard_deviation` should be kept relative to the normalized space, i.e., between -1 and 1. In other words, since data in FreqAI is always normalized to be between -1 and 1, `noise_standard_deviation: 0.05` would result in 32% of the data being randomly increased/decreased by more than 2.5% (i.e., the percent of data falling within the first standard deviation). <br> **Datatype:** Integer. <br> Default: `0`.
+| `outlier_protection_percentage` | Enable to prevent outlier detection methods from discarding too much data. If more than `outlier_protection_percentage` % of points are detected as outliers by the SVM or DBSCAN, FreqAI will log a warning message and ignore outlier detection, i.e., the original dataset will be kept intact. If the outlier protection is triggered, no predictions will be made based on the training dataset. <br> **Datatype:** Float. <br> Default: `30`.
+| `reverse_train_test_order` | Split the feature dataset (see below) and use the latest data split for training and test on historical split of the data. This allows the model to be trained up to the most recent data point, while avoiding overfitting. However, you should be careful to understand the unorthodox nature of this parameter before employing it. <br> **Datatype:** Boolean. <br> Default: `False` (no reversal).
+|  |  **Data split parameters**
+| `data_split_parameters` | Include any additional parameters available from Scikit-learn `test_train_split()`, which are shown [here](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html) (external website). <br> **Datatype:** Dictionary.
+| `test_size` | The fraction of data that should be used for testing instead of training. <br> **Datatype:** Positive float < 1.
+| `shuffle` | Shuffle the training data points during training. Typically, to not remove the chronological order of data in time-series forecasting, this is set to `False`. <br> **Datatype:** Boolean. <br> Defaut: `False`.
+|  |  **Model training parameters**
+| `model_training_parameters` | A flexible dictionary that includes all parameters available by the selected model library. For example, if you use `LightGBMRegressor`, this dictionary can contain any parameter available by the `LightGBMRegressor` [here](https://lightgbm.readthedocs.io/en/latest/pythonapi/lightgbm.LGBMRegressor.html) (external website). If you select a different model, this dictionary can contain any parameter from that model.  <br> **Datatype:** Dictionary.
+| `n_estimators` | The number of boosted trees to fit in the training of the model. <br> **Datatype:** Integer.
+| `learning_rate` | Boosting learning rate during training of the model. <br> **Datatype:** Float.
+| `n_jobs`, `thread_count`, `task_type` | Set the number of threads for parallel processing and the `task_type` (`gpu` or `cpu`). Different model libraries use different parameter names. <br> **Datatype:** Float.
+|  |  **Extraneous parameters**
+| `keras` | If the selected model makes use of Keras (typical for Tensorflow-based prediction models), this flag needs to be activated so that the model save/loading follows Keras standards. <br> **Datatype:** Boolean. <br> Default: `False`.
+| `conv_width` | The width of a convolutional neural network input tensor. This replaces the need for shifting candles (`include_shifted_candles`) by feeding in historical data points as the second dimension of the tensor. Technically, this parameter can also be used for regressors, but it only adds computational overhead and does not change the model training/prediction. <br> **Datatype:** Integer. <br> Default: `2`.

docs/freqai-running.md

@@ -0,0 +1,156 @@
+# Running FreqAI
+
+There are two ways to train and deploy an adaptive machine learning model - live deployment and historical backtesting. In both cases, FreqAI runs/simulates periodic retraining of models as shown in the following figure:
+
+![freqai-window](assets/freqai_moving-window.jpg)
+
+## Live deployments
+
+FreqAI can be run dry/live using the following command:
+
+```bash
+freqtrade trade --strategy FreqaiExampleStrategy --config config_freqai.example.json --freqaimodel LightGBMRegressor
+```
+
+When launched, FreqAI will start training a new model, with a new `identifier`, based on the config settings. Following training, the model will be used to make predictions on incoming candles until a new model is available. New models are typically generated as often as possible, with FreqAI managing an internal queue of the coin pairs to try to keep all models equally up to date. FreqAI will always use the most recently trained model to make predictions on incoming live data. If you do not want FreqAI to retrain new models as often as possible, you can set `live_retrain_hours` to tell FreqAI to wait at least that number of hours before training a new model. Additionally, you can set `expired_hours` to tell FreqAI to avoid making predictions on models that are older than that number of hours.
+
+Trained models are by default saved to disk to allow for reuse during backtesting or after a crash. You can opt to [purge old models](#purging-old-model-data) to save disk space by setting `"purge_old_models": true` in the config.
+
+To start a dry/live run from a saved backtest model (or from a previously crashed dry/live session), you only need to specify the `identifier` of the specific model:
+
+```json
+    "freqai": {
+        "identifier": "example",
+        "live_retrain_hours": 0.5
+    }
+```
+
+In this case, although FreqAI will initiate with a pre-trained model, it will still check to see how much time has elapsed since the model was trained. If a full `live_retrain_hours` has elapsed since the end of the loaded model, FreqAI will start training a new model.
+
+### Automatic data download
+
+FreqAI automatically downloads the proper amount of data needed to ensure training of a model through the defined `train_period_days` and `startup_candle_count` (see the [parameter table](freqai-parameter-table.md) for detailed descriptions of these parameters). 
+
+### Saving prediction data
+
+All predictions made during the lifetime of a specific `identifier` model are stored in `historic_predictions.pkl` to allow for reloading after a crash or changes made to the config.
+
+### Purging old model data
+
+FreqAI stores new model files after each successful training. These files become obsolete as new models are generated to adapt to new market conditions. If you are planning to leave FreqAI running for extended periods of time with high frequency retraining, you should enable `purge_old_models` in the config:
+
+```json
+    "freqai": {
+        "purge_old_models": true,
+    }
+```
+
+This will automatically purge all models older than the two most recently trained ones to save disk space.
+
+## Backtesting
+
+The FreqAI backtesting module can be executed with the following command:
+
+```bash
+freqtrade backtesting --strategy FreqaiExampleStrategy --strategy-path freqtrade/templates --config config_examples/config_freqai.example.json --freqaimodel LightGBMRegressor --timerange 20210501-20210701
+```
+
+If this command has never been executed with the existing config file, FreqAI will train a new model
+for each pair, for each backtesting window within the expanded `--timerange`.
+
+Backtesting mode requires [downloading the necessary data](#downloading-data-to-cover-the-full-backtest-period) before deployment (unlike in dry/live mode where FreqAI handles the data downloading automatically). You should be careful to consider that the time range of the downloaded data is more than the backtesting time range. This is because FreqAI needs data prior to the desired backtesting time range in order to train a model to be ready to make predictions on the first candle of the set backtesting time range. More details on how to calculate the data to download can be found [here](#deciding-the-size-of-the-sliding-training-window-and-backtesting-duration).
+
+!!! Note "Model reuse"
+    Once the training is completed, you can execute the backtesting again with the same config file and
+    FreqAI will find the trained models and load them instead of spending time training. This is useful
+    if you want to tweak (or even hyperopt) buy and sell criteria inside the strategy. If you
+    *want* to retrain a new model with the same config file, you should simply change the `identifier`.
+    This way, you can return to using any model you wish by simply specifying the `identifier`.
+
+---
+
+### Saving prediction data
+
+To allow for tweaking your strategy (**not** the features!), FreqAI will automatically save the predictions during backtesting so that they can be reused for future backtests and live runs using the same `identifier` model. This provides a performance enhancement geared towards enabling **high-level hyperopting** of entry/exit criteria.
+
+An additional directory called `predictions`, which contains all the predictions stored in `hdf` format, will be created in the `unique-id` folder.
+
+To change your **features**, you **must** set a new `identifier` in the config to signal to FreqAI to train new models.
+
+To save the models generated during a particular backtest so that you can start a live deployment from one of them instead of training a new model, you must set `save_backtest_models` to `True` in the config.
+
+### Downloading data to cover the full backtest period
+
+For live/dry deployments, FreqAI will download the necessary data automatically. However, to use backtesting functionality, you need to download the necessary data using `download-data` (details [here](data-download.md#data-downloading)). You need to pay careful attention to understanding how much *additional* data needs to be downloaded to ensure that there is a sufficient amount of training data *before* the start of the backtesting time range. The amount of additional data can be roughly estimated by moving the start date of the time range backwards by `train_period_days` and the `startup_candle_count` (see the [parameter table](freqai-parameter-table.md) for detailed descriptions of these parameters) from the beginning of the desired backtesting time range. 
+
+As an example, to backtest the `--timerange 20210501-20210701` using the [example config](freqai-configuration.md#setting-up-the-configuration-file) which sets `train_period_days` to 30, together with `startup_candle_count: 40` on a maximum `include_timeframes` of 1h, the start date for the downloaded data needs to be `20210501` - 30 days - 40 * 1h / 24 hours = 20210330 (31.7 days earlier than the start of the desired training time range).
+
+### Deciding the size of the sliding training window and backtesting duration
+
+The backtesting time range is defined with the typical `--timerange` parameter in the configuration file. The duration of the sliding training window is set by `train_period_days`, whilst `backtest_period_days` is the sliding backtesting window, both in number of days (`backtest_period_days` can be
+a float to indicate sub-daily retraining in live/dry mode). In the presented [example config](freqai-configuration.md#setting-up-the-configuration-file) (found in `config_examples/config_freqai.example.json`), the user is asking FreqAI to use a training period of 30 days and backtest on the subsequent 7 days. After the training of the model, FreqAI will backtest the subsequent 7 days. The "sliding window" then moves one week forward (emulating FreqAI retraining once per week in live mode) and the new model uses the previous 30 days (including the 7 days used for backtesting by the previous model) to train. This is repeated until the end of `--timerange`.  This means that if you set `--timerange 20210501-20210701`, FreqAI will have trained 8 separate models at the end of `--timerange` (because the full range comprises 8 weeks).
+
+!!! Note
+    Although fractional `backtest_period_days` is allowed, you should be aware that the `--timerange` is divided by this value to determine the number of models that FreqAI will need to train in order to backtest the full range. For example, by setting a `--timerange` of 10 days, and a `backtest_period_days` of 0.1, FreqAI will need to train 100 models per pair to complete the full backtest. Because of this, a true backtest of FreqAI adaptive training would take a *very* long time. The best way to fully test a model is to run it dry and let it train constantly. In this case, backtesting would take the exact same amount of time as a dry run.
+
+## Defining model expirations
+
+During dry/live mode, FreqAI trains each coin pair sequentially (on separate threads/GPU from the main Freqtrade bot). This means that there is always an age discrepancy between models. If you are training on 50 pairs, and each pair requires 5 minutes to train, the oldest model will be over 4 hours old. This may be undesirable if the characteristic time scale (the trade duration target) for a strategy is less than 4 hours. You can decide to only make trade entries if the model is less than a certain number of hours old by setting the `expiration_hours` in the config file:
+
+```json
+    "freqai": {
+        "expiration_hours": 0.5,
+    }
+```
+
+In the presented example config, the user will only allow predictions on models that are less than 1/2 hours old.
+
+## Controlling the model learning process
+
+Model training parameters are unique to the selected machine learning library. FreqAI allows you to set any parameter for any library using the `model_training_parameters` dictionary in the config. The example config (found in `config_examples/config_freqai.example.json`) shows some of the example parameters associated with `Catboost` and `LightGBM`, but you can add any parameters available in those libraries or any other machine learning library you choose to implement.
+
+Data split parameters are defined in `data_split_parameters` which can be any parameters associated with Scikit-learn's `train_test_split()` function. `train_test_split()` has a parameters called `shuffle` which allows to shuffle the data or keep it unshuffled. This is particularly useful to avoid biasing training with temporally auto-correlated data. More details about these parameters can be found the [Scikit-learn website](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html) (external website).
+
+The FreqAI specific parameter `label_period_candles` defines the offset (number of candles into the future) used for the `labels`. In the presented [example config](freqai-configuration.md#setting-up-the-configuration-file), the user is asking for `labels` that are 24 candles in the future.
+
+## Continual learning
+
+You can choose to adopt a continual learning scheme by setting `"continual_learning": true` in the config. By enabling `continual_learning`, after training an initial model from scratch, subsequent trainings will start from the final model state of the preceding training. This gives the new model a "memory" of the previous state. By default, this is set to `False` which means that all new models are trained from scratch, without input from previous models.
+
+## Hyperopt
+
+You can hyperopt using the same command as for [typical Freqtrade hyperopt](hyperopt.md):
+
+```bash
+freqtrade hyperopt --hyperopt-loss SharpeHyperOptLoss --strategy FreqaiExampleStrategy --freqaimodel LightGBMRegressor --strategy-path freqtrade/templates --config config_examples/config_freqai.example.json --timerange 20220428-20220507
+```
+
+`hyperopt` requires you to have the data pre-downloaded in the same fashion as if you were doing [backtesting](#backtesting). In addition, you must consider some restrictions when trying to hyperopt FreqAI strategies:
+
+- The `--analyze-per-epoch` hyperopt parameter is not compatible with FreqAI.
+- It's not possible to hyperopt indicators in the `populate_any_indicators()` function. This means that you cannot optimize model parameters using hyperopt. Apart from this exception, it is possible to optimize all other [spaces](hyperopt.md#running-hyperopt-with-smaller-search-space).
+- The backtesting instructions also apply to hyperopt.
+
+The best method for combining hyperopt and FreqAI is to focus on hyperopting entry/exit thresholds/criteria. You need to focus on hyperopting parameters that are not used in your features. For example, you should not try to hyperopt rolling window lengths in the feature creation, or any part of the FreqAI config which changes predictions. In order to efficiently hyperopt the FreqAI strategy, FreqAI stores predictions as dataframes and reuses them. Hence the requirement to hyperopt entry/exit thresholds/criteria only.
+
+A good example of a hyperoptable parameter in FreqAI is a threshold for the [Dissimilarity Index (DI)](freqai-feature-engineering.md#identifying-outliers-with-the-dissimilarity-index-di) `DI_values` beyond which we consider data points as outliers:
+
+```python
+di_max = IntParameter(low=1, high=20, default=10, space='buy', optimize=True, load=True)
+dataframe['outlier'] = np.where(dataframe['DI_values'] > self.di_max.value/10, 1, 0)
+```
+
+This specific hyperopt would help you understand the appropriate `DI_values` for your particular parameter space.
+
+## Setting up a follower
+
+You can indicate to the bot that it should not train models, but instead should look for models trained by a leader with a specific `identifier` by defining:
+
+```json
+    "freqai": {
+        "follow_mode": true,
+        "identifier": "example"
+    }
+```
+
+In this example, the user has a leader bot with the `"identifier": "example"`. The leader bot is already running or is launched simultaneously with the follower. The follower will load models created by the leader and inference them to obtain predictions instead of training its own models.

docs/freqai-spice-rack.md

@@ -0,0 +1,71 @@
+# Using the `spice_rack`
+
+!!! Note:
+    `spice_rack` indicators should not be used exclusively for entries and exits, the following example is just a demonstration of syntax. `spice_rack` indicators should **always** be used to support existing strategies.
+
+The `spice_rack` is aimed at users who do not wish to deal with setting up `FreqAI` confgs, but instead prefer to interact with `FreqAI` similar to a `talib` indicator. In this case, the user can instead simply add two keys to their config:
+
+```json
+    "freqai_spice_rack": true, 
+    "freqai_identifier": "spicey-id",
+```
+
+Which tells `FreqAI` to set up a pre-set `FreqAI` instance automatically under the hood with preset parameters. Now the user can access a suite of custom `FreqAI` supercharged indicators inside their strategy by placing the following code into `populate_indicators`:
+
+```python
+        dataframe['dissimilarity_index'] = self.freqai.spice_rack(
+            'DI_values', dataframe, metadata, self)
+        dataframe['extrema'] = self.freqai.spice_rack(
+            '&s-extrema', dataframe, metadata, self)
+        self.freqai.close_spice_rack()  # user must close the spicerack
+```
+
+Users can then use these columns in concert with all their own additional indicators added to `populate_indicators` in their entry/exit criteria and strategy callback methods the same way as any typical indicator. For example:
+
+```python
+    def populate_entry_trend(self, df: DataFrame, metadata: dict) -> DataFrame:
+
+        df.loc[
+            (
+                (df['dissimilarity_index'] < 1) &
+                (df['extrema'] < -0.1)
+            ),
+            'enter_long'] = 1
+
+        df.loc[
+            (
+                (df['dissimilarity_index'] < 1) &
+                (df['extrema'] > 0.1)
+            ),
+            'enter_short'] = 1
+
+        return df
+
+    def populate_exit_trend(self, df: DataFrame, metadata: dict) -> DataFrame:
+
+        df.loc[
+            (
+                (df['dissimilarity_index'] < 1) &
+                (df['extrema'] > 0.1) 
+            ),
+
+            'exit_long'] = 1
+
+        df.loc[
+            (
+
+                (df['dissimilarity_index'] < 1) &
+                (df['extrema'] < -0.1)
+            ),
+            'exit_short'] = 1
+
+        return df
+```
+
+
+## Available indicators
+
+|  Parameter | Description |
+|------------|-------------|
+| `DI_values` | **Required.** <br> The dissimilarity index of the current candle to the recent candles. More information available [here](freqai-feature-engineering.md#identifying-outliers-with-the-dissimilarity-index-di) <br> **Datatype:** Floats.
+| `extrema` | **Required.** <br> A continuous prediction from FreqAI which aims to help predict if the current candle is a maxima or a minma. FreqAI aims for 1 to be a maxima and -1 to be a minima - but the values should typically hover between -0.2 and 0.2. <br> **Datatype:** Floats.

docs/freqai.md

@@ -2,739 +2,77 @@
 
 # FreqAI
 
-FreqAI is a module designed to automate a variety of tasks associated with training a predictive machine learning model to generate market forecasts given a set of input features.
+## Introduction
+
+FreqAI is a software designed to automate a variety of tasks associated with training a predictive machine learning model to generate market forecasts given a set of input features.
 
 Features include:
 
-* **Self-adaptive retraining**: retrain models during [live deployments](#running-the-model-live) to self-adapt to the market in an unsupervised manner.
-* **Rapid feature engineering**: create large rich [feature sets](#feature-engineering) (10k+ features) based on simple user-created strategies.
-* **High performance**: adaptive retraining occurs on a separate thread (or on GPU if available) from inferencing and bot trade operations. Newest models and data are kept in memory for rapid inferencing.
-* **Realistic backtesting**: emulate self-adaptive retraining with a [backtesting module](#backtesting) that automates past retraining.
-* **Modifiability**: use the generalized and robust architecture for incorporating any [machine learning library/method](#building-a-custom-prediction-model) available in Python. Eight examples are currently available, including classifiers, regressors, and a convolutional neural network.
-* **Smart outlier removal**: remove outliers from training and prediction data sets using a variety of [outlier detection techniques](#outlier-removal).
-* **Crash resilience**: store model to disk to make reloading from a crash fast and easy, and [purge obsolete files](#purging-old-model-data) for sustained dry/live runs.
-* **Automatic data normalization**: [normalize the data](#feature-normalization) in a smart and statistically safe way.
-* **Automatic data download**: compute the data download timerange and update historic data (in live deployments).
-* **Cleaning of incoming data**: handle NaNs safely before training and prediction.
-* **Dimensionality reduction**: reduce the size of the training data via [Principal Component Analysis](#reducing-data-dimensionality-with-principal-component-analysis).
-* **Deploying bot fleets**: set one bot to train models while a fleet of [follower bots](#setting-up-a-follower) inference the models and handle trades.
+* **Self-adaptive retraining** - Retrain models during [live deployments](freqai-running.md#live-deployments) to self-adapt to the market in a supervised manner
+* **Rapid feature engineering** - Create large rich [feature sets](freqai-feature-engineering.md#feature-engineering) (10k+ features) based on simple user-created strategies
+* **High performance** - Threading allows for adaptive model retraining on a separate thread (or on GPU if available) from model inferencing (prediction) and bot trade operations. Newest models and data are kept in RAM for rapid inferencing
+* **Realistic backtesting** - Emulate self-adaptive training on historic data with a [backtesting module](freqai-running.md#backtesting) that automates retraining
+* **Extensibility** - The generalized and robust architecture allows for incorporating any [machine learning library/method](freqai-configuration.md#using-different-prediction-models) available in Python. Eight examples are currently available, including classifiers, regressors, and a convolutional neural network
+* **Smart outlier removal** - Remove outliers from training and prediction data sets using a variety of [outlier detection techniques](freqai-feature-engineering.md#outlier-detection)
+* **Crash resilience** - Store trained models to disk to make reloading from a crash fast and easy, and [purge obsolete files](freqai-running.md#purging-old-model-data) for sustained dry/live runs
+* **Automatic data normalization** - [Normalize the data](freqai-feature-engineering.md#feature-normalization) in a smart and statistically safe way
+* **Automatic data download** - Compute timeranges for data downloads and update historic data (in live deployments)
+* **Cleaning of incoming data** - Handle NaNs safely before training and model inferencing
+* **Dimensionality reduction** - Reduce the size of the training data via [Principal Component Analysis](freqai-feature-engineering.md#data-dimensionality-reduction-with-principal-component-analysis)
+* **Deploying bot fleets** - Set one bot to train models while a fleet of [follower bots](freqai-running.md#setting-up-a-follower) inference the models and handle trades
 
 ## Quick start
 
-The easiest way to quickly test FreqAI is to run it in dry mode with the following command
+The easiest way to quickly test FreqAI is to run it in dry mode with the following command:
 
 ```bash
 freqtrade trade --config config_examples/config_freqai.example.json --strategy FreqaiExampleStrategy --freqaimodel LightGBMRegressor --strategy-path freqtrade/templates
 ```
 
-The user will see the boot-up process of automatic data downloading, followed by simultaneous training and trading.
+You will see the boot-up process of automatic data downloading, followed by simultaneous training and trading.
 
-The example strategy, example prediction model, and example config can be found in
+An example strategy, prediction model, and config to use as a starting points can be found in
 `freqtrade/templates/FreqaiExampleStrategy.py`, `freqtrade/freqai/prediction_models/LightGBMRegressor.py`, and
 `config_examples/config_freqai.example.json`, respectively.
 
 ## General approach
 
-The user provides FreqAI with a set of custom *base* indicators (the same way as in a typical Freqtrade strategy) as well as target values (*labels*).
-FreqAI trains a model to predict the target values based on the input of custom indicators, for each pair in the whitelist. These models are consistently retrained to adapt to market conditions. FreqAI offers the ability to both backtest strategies (emulating reality with periodic retraining) and deploy dry/live runs. In dry/live conditions, FreqAI can be set to constant retraining in a background thread in an effort to keep models as up to date as possible.
+You provide FreqAI with a set of custom *base indicators* (the same way as in a [typical Freqtrade strategy](strategy-customization.md)) as well as target values (*labels*). For each pair in the whitelist, FreqAI trains a model to predict the target values based on the input of custom indicators. The models are then consistently retrained, with a predetermined frequency, to adapt to market conditions. FreqAI offers the ability to both backtest strategies (emulating reality with periodic retraining on historic data) and deploy dry/live runs. In dry/live conditions, FreqAI can be set to constant retraining in a background thread to keep models as up to date as possible.
 
-An overview of the algorithm is shown below, explaining the data processing pipeline and the model usage. 
+An overview of the algorithm, explaining the data processing pipeline and model usage, is shown below.
 
 ![freqai-algo](assets/freqai_algo.jpg)
 
 ### Important machine learning vocabulary
 
-**Features** - the quantities with which a model is trained. All features for a single candle is stored as a vector. In FreqAI, the user
-builds the feature sets from anything they can construct in the strategy. 
+**Features** - the parameters, based on historic data, on which a model is trained. All features for a single candle are stored as a vector. In FreqAI, you build a feature data set from anything you can construct in the strategy.
 
-**Labels** - the target values that a model is trained
-toward. Each set of features is associated with a single label that is
-defined by the user within the strategy. These labels intentionally look into the
-future, and are not available to the model during dry/live/backtesting.
+**Labels** - the target values that the model is trained toward. Each feature vector is associated with a single label that is defined by you within the strategy. These labels intentionally look into the future and are what you are training the model to be able to predict.
 
-**Training** - the process of feeding individual feature sets, composed of historic data, with associated labels into the
-model with the goal of matching input feature sets to associated labels. 
+**Training** - the process of "teaching" the model to match the feature sets to the associated labels. Different types of models "learn" in different ways which means that one might be better than another for a specific application. More information about the different models that are already implemented in FreqAI can be found [here](freqai-configuration.md#using-different-prediction-models).
 
-**Train data** - a subset of the historic data that is fed to the model during
-training. This data directly influences weight connections in the model.
+**Train data** - a subset of the feature data set that is fed to the model during training to "teach" the model how to predict the targets. This data directly influences weight connections in the model.
 
-**Test data** - a subset of the historic data that is used to evaluate the performance of the model after training. This data does not influence nodal weights within the model. 
+**Test data** - a subset of the feature data set that is used to evaluate the performance of the model after training. This data does not influence nodal weights within the model.
+
+**Inferencing** - the process of feeding a trained model new unseen data on which it will make a prediction. 
 
 ## Install prerequisites
 
-The normal Freqtrade install process will ask the user if they wish to install FreqAI dependencies. The user should reply "yes" to this question if they wish to use FreqAI. If the user did not reply yes, they can manually install these dependencies after the install with:
+The normal Freqtrade install process will ask if you wish to install FreqAI dependencies. You should reply "yes" to this question if you wish to use FreqAI. If you did not reply yes, you can manually install these dependencies after the install with:
 
 ``` bash
 pip install -r requirements-freqai.txt
 ```
 
 !!! Note
-    Catboost will not be installed on arm devices (raspberry, Mac M1, ARM based VPS, ...), since Catboost does not provide wheels for this platform.
+    Catboost will not be installed on arm devices (raspberry, Mac M1, ARM based VPS, ...), since it does not provide wheels for this platform.
 
 ### Usage with docker
 
-For docker users, a dedicated tag with freqAI dependencies is available as `:freqai`.
-As such - you can replace the image line in your docker-compose file with `image: freqtradeorg/freqtrade:develop_freqai`.
-This image contains the regular freqAI dependencies. Similar to native installs, Catboost will not be available on ARM based devices.
+If you are using docker, a dedicated tag with FreqAI dependencies is available as `:freqai`. As such - you can replace the image line in your docker-compose file with `image: freqtradeorg/freqtrade:develop_freqai`. This image contains the regular FreqAI dependencies. Similar to native installs, Catboost will not be available on ARM based devices.
 
-## Setting up FreqAI
-
-### Parameter table
-
-The table below will list all configuration parameters available for FreqAI, presented in the same order as `config_examples/config_freqai.example.json`.
-
-Mandatory parameters are marked as **Required**, which means that they are required to be set in one of the possible ways.
-
-|  Parameter | Description |
-|------------|-------------|
-|  |  **General configuration parameters**
-| `freqai` | **Required.** <br> The parent dictionary containing all the parameters for controlling FreqAI. <br> **Datatype:** Dictionary.
-| `startup_candles` | Number of candles needed for *backtesting only* to ensure all indicators are non NaNs at the start of the first train period. <br> **Datatype:** Positive integer.
-| `purge_old_models` | Delete obsolete models (otherwise, all historic models will remain on disk). <br> **Datatype:** Boolean. Default: `False`.
-| `train_period_days` | **Required.** <br> Number of days to use for the training data (width of the sliding window). <br> **Datatype:** Positive integer.
-| `backtest_period_days` | **Required.** <br> Number of days to inference from the trained model before sliding the window defined above, and retraining the model. This can be fractional days, but beware that the user-provided `timerange` will be divided by this number to yield the number of trainings necessary to complete the backtest. <br> **Datatype:** Float.
-| `identifier` | **Required.** <br> A unique name for the current model. This can be reused to reload pre-trained models/data. <br> **Datatype:** String.
-| `live_retrain_hours` | Frequency of retraining during dry/live runs. <br> Default set to 0, which means the model will retrain as often as possible. <br> **Datatype:** Float > 0.
-| `expiration_hours` | Avoid making predictions if a model is more than `expiration_hours` old. <br> Defaults set to 0, which means models never expire. <br> **Datatype:** Positive integer.
-| `fit_live_predictions_candles` | Number of historical candles to use for computing target (label) statistics from prediction data, instead of from the training data set. <br> **Datatype:** Positive integer.
-| `follow_mode` | If true, this instance of FreqAI will look for models associated with `identifier` and load those for inferencing. A `follower` will **not** train new models. <br> **Datatype:** Boolean. Default: `False`.
-|  |  **Feature parameters**
-| `feature_parameters` | A dictionary containing the parameters used to engineer the feature set. Details and examples are shown [here](#feature-engineering). <br> **Datatype:** Dictionary.
-| `include_timeframes` | A list of timeframes that all indicators in `populate_any_indicators` will be created for. The list is added as features to the base asset feature set. <br> **Datatype:** List of timeframes (strings).
-| `include_corr_pairlist` | A list of correlated coins that FreqAI will add as additional features to all `pair_whitelist` coins. All indicators set in `populate_any_indicators` during feature engineering (see details [here](#feature-engineering)) will be created for each coin in this list, and that set of features is added to the base asset feature set. <br> **Datatype:** List of assets (strings).
-| `label_period_candles` | Number of candles into the future that the labels are created for. This is used in `populate_any_indicators` (see `templates/FreqaiExampleStrategy.py` for detailed usage). The user can create custom labels, making use of this parameter or not. <br> **Datatype:** Positive integer.
-| `include_shifted_candles` | Add features from previous candles to subsequent candles to add historical information. FreqAI takes all features from the `include_shifted_candles` previous candles, duplicates and shifts them so that the information is available for the subsequent candle. <br> **Datatype:** Positive integer.
-| `weight_factor` | Used to set weights for training data points according to their recency. See details about how it works [here](#controlling-the-model-learning-process). <br> **Datatype:** Positive float (typically < 1). 
-| `indicator_max_period_candles` | The maximum period used in `populate_any_indicators()` for indicator creation. FreqAI uses this information in combination with the maximum timeframe to calculate how many data points that should be downloaded so that the first data point does not have a NaN. <br> **Datatype:** Positive integer.
-| `indicator_periods_candles` | Calculate indicators for `indicator_periods_candles` time periods and add them to the feature set. <br> **Datatype:** List of positive integers.
-| `stratify_training_data` | This value is used to indicate the grouping of the data. For example, 2 would set every 2nd data point into a separate dataset to be pulled from during training/testing. See details about how it works [here](#stratifying-the-data-for-training-and-testing-the-model) <br> **Datatype:** Positive integer.
-| `principal_component_analysis` | Automatically reduce the dimensionality of the data set using Principal Component Analysis. See details about how it works [here](#reducing-data-dimensionality-with-principal-component-analysis) <br> **Datatype:** Boolean. 
-| `DI_threshold` | Activates the Dissimilarity Index for outlier detection when > 0. See details about how it works [here](#removing-outliers-with-the-dissimilarity-index). <br> **Datatype:** Positive float (typically < 1).
-| `use_SVM_to_remove_outliers` | Train a support vector machine to detect and remove outliers from the training data set, as well as from incoming data points. See details about how it works [here](#removing-outliers-using-a-support-vector-machine-svm). <br> **Datatype:** Boolean.
-| `svm_params` | All parameters available in Sklearn's `SGDOneClassSVM()`. See details about some select parameters [here](#removing-outliers-using-a-support-vector-machine-svm). <br> **Datatype:** Dictionary.
-| `use_DBSCAN_to_remove_outliers` | Cluster data using DBSCAN to identify and remove outliers from training and prediction data. See details about how it works [here](#removing-outliers-with-dbscan). <br> **Datatype:** Boolean. 
-| `outlier_protection_percentage` | If more than `outlier_protection_percentage` fraction of points are removed as outliers, FreqAI will log a warning message and ignore outlier detection while keeping the original dataset intact. <br> **Datatype:** float. Default: `30`
-|  |  **Data split parameters**
-| `data_split_parameters` | Include any additional parameters available from Scikit-learn `test_train_split()`, which are shown [here](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html) (external website). <br> **Datatype:** Dictionary.
-| `test_size` | Fraction of data that should be used for testing instead of training. <br> **Datatype:** Positive float < 1.
-| `shuffle` | Shuffle the training data points during training. Typically, for time-series forecasting, this is set to `False`. <br> 
-|  |  **Model training parameters**
-| `model_training_parameters` | A flexible dictionary that includes all parameters available by the user selected model library. For example, if the user uses `LightGBMRegressor`, this dictionary can contain any parameter available by the `LightGBMRegressor` [here](https://lightgbm.readthedocs.io/en/latest/pythonapi/lightgbm.LGBMRegressor.html) (external website). If the user selects a different model, this dictionary can contain any parameter from that model.  <br> **Datatype:** Dictionary.**Datatype:** Boolean.
-| `n_estimators` | The number of boosted trees to fit in regression. <br> **Datatype:** Integer.
-| `learning_rate` | Boosting learning rate during regression. <br> **Datatype:** Float.
-| `n_jobs`, `thread_count`, `task_type` | Set the number of threads for parallel processing and the `task_type` (`gpu` or `cpu`). Different model libraries use different parameter names. <br> **Datatype:** Float.
-|  |  **Extraneous parameters**
-| `keras` | If your model makes use of Keras (typical for Tensorflow-based prediction models), activate this flag so that the model save/loading follows Keras standards. <br> **Datatype:** Boolean. Default: `False`.
-| `conv_width` | The width of a convolutional neural network input tensor. This replaces the need for shifting candles (`include_shifted_candles`) by feeding in historical data points as the second dimension of the tensor. Technically, this parameter can also be used for regressors, but it only adds computational overhead and does not change the model training/prediction. <br> **Datatype:** Integer. Default: 2.
-
-### Important dataframe key patterns
-
-Below are the values the user can expect to include/use inside a typical strategy dataframe (`df[]`):
-
-|  DataFrame Key | Description |
-|------------|-------------|
-| `df['&*']` | Any dataframe column prepended with `&` in `populate_any_indicators()` is treated as a training target (label) inside FreqAI (typically following the naming convention `&-s*`). The names of these dataframe columns are fed back to the user as the predictions. For example, if the user wishes to predict the price change in the next 40 candles (similar to `templates/FreqaiExampleStrategy.py`), they set `df['&-s_close']`. FreqAI makes the predictions and gives them back under the same key (`df['&-s_close']`) to be used in `populate_entry/exit_trend()`. <br> **Datatype:** Depends on the output of the model.
-| `df['&*_std/mean']` | Standard deviation and mean values of the user-defined labels during training (or live tracking with `fit_live_predictions_candles`). Commonly used to understand the rarity of a prediction (use the z-score as shown in `templates/FreqaiExampleStrategy.py` to evaluate how often a particular prediction was observed during training or historically with `fit_live_predictions_candles`). <br> **Datatype:** Float.
-| `df['do_predict']` | Indication of an outlier data point. The return value is integer between -1 and 2, which lets the user know if the prediction is trustworthy or not. `do_predict==1` means the prediction is trustworthy. If the Dissimilarity Index (DI, see details [here](#removing-outliers-with-the-dissimilarity-index)) of the input data point is above the user-defined threshold, FreqAI will subtract 1 from `do_predict`, resulting in `do_predict==0`. If `use_SVM_to_remove_outliers()` is active, the Support Vector Machine (SVM) may also detect outliers in training and prediction data. In this case, the SVM will also subtract 1 from `do_predict`. If the input data point was considered an outlier by the SVM but not by the DI, the result will be `do_predict==0`. If both the DI and the SVM considers the input data point to be an outlier, the result will be `do_predict==-1`. A particular case is when `do_predict == 2`, which means that the model has expired due to exceeding `expired_hours`. <br> **Datatype:** Integer between -1 and 2.
-| `df['DI_values']` | Dissimilarity Index values are proxies to the level of confidence FreqAI has in the prediction. A lower DI means the prediction is close to the training data, i.e., higher prediction confidence. <br> **Datatype:** Float.
-| `df['%*']` | Any dataframe column prepended with `%` in `populate_any_indicators()` is treated as a training feature. For example, the user can include the RSI in the training feature set (similar to in `templates/FreqaiExampleStrategy.py`) by setting `df['%-rsi']`. See more details on how this is done [here](#feature-engineering). <br> **Note**: Since the number of features prepended with `%` can multiply very quickly (10s of thousands of features is easily engineered using the multiplictative functionality described in the `feature_parameters` table shown above), these features are removed from the dataframe upon return from FreqAI. If the user wishes to keep a particular type of feature for plotting purposes, they can prepend it with `%%`. <br> **Datatype:** Depends on the output of the model.
-
-### File structure
-
-`user_data_dir/models/` contains all the data associated with the trainings and backtests.
-This file structure is heavily controlled and inferenced by the `FreqaiDataKitchen()`
-and should therefore not be modified.
-
-### Example config file
-
-The user interface is isolated to the typical Freqtrade config file. A FreqAI config should include:
-
-```json
-    "freqai": {
-        "enabled": true,
-        "startup_candles": 10000,
-        "purge_old_models": true,
-        "train_period_days": 30,
-        "backtest_period_days": 7,
-        "identifier" : "unique-id",
-        "feature_parameters" : {
-            "include_timeframes": ["5m","15m","4h"],
-            "include_corr_pairlist": [
-                "ETH/USD",
-                "LINK/USD",
-                "BNB/USD"
-            ],
-            "label_period_candles": 24,
-            "include_shifted_candles": 2,
-            "indicator_max_period_candles": 20,
-            "indicator_periods_candles": [10, 20]
-        },
-        "data_split_parameters" : {
-            "test_size": 0.25
-        },
-        "model_training_parameters" : {
-            "n_estimators": 100
-        },
-    }
-```
-
-## Building a FreqAI strategy
-
-The FreqAI strategy requires the user to include the following lines of code in the standard Freqtrade strategy:
-
-```python
-
-    def informative_pairs(self):
-        whitelist_pairs = self.dp.current_whitelist()
-        corr_pairs = self.config["freqai"]["feature_parameters"]["include_corr_pairlist"]
-        informative_pairs = []
-        for tf in self.config["freqai"]["feature_parameters"]["include_timeframes"]:
-            for pair in whitelist_pairs:
-                informative_pairs.append((pair, tf))
-            for pair in corr_pairs:
-                if pair in whitelist_pairs:
-                    continue  # avoid duplication
-                informative_pairs.append((pair, tf))
-        return informative_pairs
-
-    def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
-
-        # the model will return all labels created by user in `populate_any_indicators` 
-        # (& appended targets), an indication of whether or not the prediction should be accepted, 
-        # the target mean/std values for each of the labels created by user in 
-        # `populate_any_indicators()` for each training period.
-
-        dataframe = self.freqai.start(dataframe, metadata, self)
-
-        return dataframe
-
-    def populate_any_indicators(
-        self, pair, df, tf, informative=None, set_generalized_indicators=False
-    ):
-        """
-        Function designed to automatically generate, name and merge features
-        from user indicated timeframes in the configuration file. User controls the indicators
-        passed to the training/prediction by prepending indicators with `'%-' + coin `
-        (see convention below). I.e. user should not prepend any supporting metrics
-        (e.g. bb_lowerband below) with % unless they explicitly want to pass that metric to the
-        model.
-        :param pair: pair to be used as informative
-        :param df: strategy dataframe which will receive merges from informatives
-        :param tf: timeframe of the dataframe which will modify the feature names
-        :param informative: the dataframe associated with the informative pair
-        :param coin: the name of the coin which will modify the feature names.
-        """
-
-        coin = pair.split('/')[0]
-
-        if informative is None:
-            informative = self.dp.get_pair_dataframe(pair, tf)
-
-        # first loop is automatically duplicating indicators for time periods
-        for t in self.freqai_info["feature_parameters"]["indicator_periods_candles"]:
-            t = int(t)
-            informative[f"%-{coin}rsi-period_{t}"] = ta.RSI(informative, timeperiod=t)
-            informative[f"%-{coin}mfi-period_{t}"] = ta.MFI(informative, timeperiod=t)
-            informative[f"%-{coin}adx-period_{t}"] = ta.ADX(informative, window=t)
-
-        indicators = [col for col in informative if col.startswith("%")]
-        # This loop duplicates and shifts all indicators to add a sense of recency to data
-        for n in range(self.freqai_info["feature_parameters"]["include_shifted_candles"] + 1):
-            if n == 0:
-                continue
-            informative_shift = informative[indicators].shift(n)
-            informative_shift = informative_shift.add_suffix("_shift-" + str(n))
-            informative = pd.concat((informative, informative_shift), axis=1)
-
-        df = merge_informative_pair(df, informative, self.config["timeframe"], tf, ffill=True)
-        skip_columns = [
-            (s + "_" + tf) for s in ["date", "open", "high", "low", "close", "volume"]
-        ]
-        df = df.drop(columns=skip_columns)
-
-        # Add generalized indicators here (because in live, it will call this
-        # function to populate indicators during training). Notice how we ensure not to
-        # add them multiple times
-        if set_generalized_indicators:
-
-            # user adds targets here by prepending them with &- (see convention below)
-            # If user wishes to use multiple targets, a multioutput prediction model
-            # needs to be used such as templates/CatboostPredictionMultiModel.py
-            df["&-s_close"] = (
-                df["close"]
-                .shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
-                .rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
-                .mean()
-                / df["close"]
-                - 1
-            )
-
-        return df
-
-
-```
-
-Notice how the `populate_any_indicators()` is where the user adds their own features ([more information](#feature-engineering)) and labels ([more information](#setting-classifier-targets)). See a full example at `templates/FreqaiExampleStrategy.py`.
-
-## Creating a dynamic target
-
-The `&*_std/mean` return values describe the statistical fit of the user defined label *during the most recent training*. This value allows the user to know the rarity of a given prediction. For example, `templates/FreqaiExampleStrategy.py`, creates a `target_roi` which is based on filtering out predictions that are below a given z-score of 1.25.
-
-```python
-dataframe["target_roi"] = dataframe["&-s_close_mean"] + dataframe["&-s_close_std"] * 1.25
-dataframe["sell_roi"] = dataframe["&-s_close_mean"] - dataframe["&-s_close_std"] * 1.25
-```
-
-If the user wishes to consider the population
-of *historical predictions* for creating the dynamic target instead of the trained labels, (as discussed above) the user
-can do so by setting `fit_live_prediction_candles` in the config to the number of historical prediction candles
-the user wishes to use to generate target statistics.
-
-```json
-    "freqai": {
-        "fit_live_prediction_candles": 300,
-    }
-```
-
-If the user sets this value, FreqAI will initially use the predictions from the training data
-and subsequently begin introducing real prediction data as it is generated. FreqAI will save
-this historical data to be reloaded if the user stops and restarts a model with the same `identifier`.
-
-## Building a custom prediction model
-
-FreqAI has multiple example prediction model libraries, such as `Catboost` regression (`freqai/prediction_models/CatboostRegressor.py`) and `LightGBM` regression.
-However, the user can customize and create their own prediction models using the `IFreqaiModel` class.
-The user is encouraged to inherit `train()` and `predict()` to let them customize various aspects of their training procedures.
-
-## Feature engineering
-
-Features are added by the user inside the `populate_any_indicators()` method of the strategy
-by prepending indicators with `%`, and labels with `&`.  
-
-There are some important components/structures that the user *must* include when building their feature set; the use of these is shown below:
-
-```python
-    def populate_any_indicators(
-        self, pair, df, tf, informative=None, set_generalized_indicators=False
-    ):
-        """
-        Function designed to automatically generate, name, and merge features
-        from user-indicated timeframes in the configuration file. The user controls the indicators
-        passed to the training/prediction by prepending indicators with `'%-' + coin `
-        (see convention below). I.e., the user should not prepend any supporting metrics
-        (e.g., bb_lowerband below) with % unless they explicitly want to pass that metric to the
-        model.
-        :param pair: pair to be used as informative
-        :param df: strategy dataframe which will receive merges from informatives
-        :param tf: timeframe of the dataframe which will modify the feature names
-        :param informative: the dataframe associated with the informative pair
-        :param coin: the name of the coin which will modify the feature names.
-        """
-
-        coin = pair.split('/')[0]
-
-        if informative is None:
-            informative = self.dp.get_pair_dataframe(pair, tf)
-
-        # first loop is automatically duplicating indicators for time periods
-        for t in self.freqai_info["feature_parameters"]["indicator_periods_candles"]:
-            t = int(t)
-            informative[f"%-{coin}rsi-period_{t}"] = ta.RSI(informative, timeperiod=t)
-            informative[f"%-{coin}mfi-period_{t}"] = ta.MFI(informative, timeperiod=t)
-            informative[f"%-{coin}adx-period_{t}"] = ta.ADX(informative, window=t)
-
-            bollinger = qtpylib.bollinger_bands(
-                qtpylib.typical_price(informative), window=t, stds=2.2
-            )
-            informative[f"{coin}bb_lowerband-period_{t}"] = bollinger["lower"]
-            informative[f"{coin}bb_middleband-period_{t}"] = bollinger["mid"]
-            informative[f"{coin}bb_upperband-period_{t}"] = bollinger["upper"]
-
-            informative[f"%-{coin}bb_width-period_{t}"] = (
-                informative[f"{coin}bb_upperband-period_{t}"]
-                - informative[f"{coin}bb_lowerband-period_{t}"]
-            ) / informative[f"{coin}bb_middleband-period_{t}"]
-            informative[f"%-{coin}close-bb_lower-period_{t}"] = (
-                informative["close"] / informative[f"{coin}bb_lowerband-period_{t}"]
-            )
-
-            informative[f"%-{coin}relative_volume-period_{t}"] = (
-                informative["volume"] / informative["volume"].rolling(t).mean()
-            )
-
-        indicators = [col for col in informative if col.startswith("%")]
-        # This loop duplicates and shifts all indicators to add a sense of recency to data
-        for n in range(self.freqai_info["feature_parameters"]["include_shifted_candles"] + 1):
-            if n == 0:
-                continue
-            informative_shift = informative[indicators].shift(n)
-            informative_shift = informative_shift.add_suffix("_shift-" + str(n))
-            informative = pd.concat((informative, informative_shift), axis=1)
-
-        df = merge_informative_pair(df, informative, self.config["timeframe"], tf, ffill=True)
-        skip_columns = [
-            (s + "_" + tf) for s in ["date", "open", "high", "low", "close", "volume"]
-        ]
-        df = df.drop(columns=skip_columns)
-
-        # Add generalized indicators here (because in live, it will call this
-        # function to populate indicators during training). Notice how we ensure not to
-        # add them multiple times
-        if set_generalized_indicators:
-            df["%-day_of_week"] = (df["date"].dt.dayofweek + 1) / 7
-            df["%-hour_of_day"] = (df["date"].dt.hour + 1) / 25
-
-            # user adds targets here by prepending them with &- (see convention below)
-            # If user wishes to use multiple targets, a multioutput prediction model
-            # needs to be used such as templates/CatboostPredictionMultiModel.py
-            df["&-s_close"] = (
-                df["close"]
-                .shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
-                .rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
-                .mean()
-                / df["close"]
-                - 1
-            )
-
-        return df
-```
-
-In the presented example strategy, the user does not wish to pass the `bb_lowerband` as a feature to the model,
-and has therefore not prepended it with `%`. The user does, however, wish to pass `bb_width` to the
-model for training/prediction and has therefore prepended it with `%`.
-
-The `include_timeframes` in the example config above are the timeframes (`tf`) of each call to `populate_any_indicators()` in the strategy. In the present case, the user is asking for the
-`5m`, `15m`, and `4h` timeframes of the `rsi`, `mfi`, `roc`, and `bb_width` to be included in the feature set.
-
-The user can ask for each of the defined features to be included also from
-informative pairs using the `include_corr_pairlist`. This means that the feature
-set will include all the features from `populate_any_indicators` on all the `include_timeframes` for each of the correlated pairs defined in the config (`ETH/USD`, `LINK/USD`, and `BNB/USD`).
-
-`include_shifted_candles` indicates the number of previous
-candles to include in the feature set. For example, `include_shifted_candles: 2` tells
-FreqAI to include the past 2 candles for each of the features in the feature set.
-
-In total, the number of features the user of the presented example strat has created is:
-length of `include_timeframes` * no. features in `populate_any_indicators()` * length of `include_corr_pairlist` * no. `include_shifted_candles` * length of `indicator_periods_candles`
- $= 3 * 3 * 3 * 2 * 2 = 108$.
-
-Another structure to consider is the location of the labels at the bottom of the example function (below `if set_generalized_indicators:`). 
-This is where the user will add single features and labels to their feature set to avoid duplication of them from
-various configuration parameters that multiply the feature set, such as `include_timeframes`.
-
-!!! Note
-    Features **must** be defined in `populate_any_indicators()`. Definining FreqAI features in `populate_indicators()`
-    will cause the algorithm to fail in live/dry mode. If the user wishes to add generalized features that are not associated with 
-    a specific pair or timeframe, they should use the following structure inside `populate_any_indicators()`
-    (as exemplified in `freqtrade/templates/FreqaiExampleStrategy.py`):
-
-    ```python
-        def populate_any_indicators(self, metadata, pair, df, tf, informative=None, coin="", set_generalized_indicators=False):
-
-            ...
-
-            # Add generalized indicators here (because in live, it will call only this function to populate 
-            # indicators for retraining). Notice how we ensure not to add them multiple times by associating
-            # these generalized indicators to the basepair/timeframe
-            if set_generalized_indicators:
-                df['%-day_of_week'] = (df["date"].dt.dayofweek + 1) / 7
-                df['%-hour_of_day'] = (df['date'].dt.hour + 1) / 25
-
-                # user adds targets here by prepending them with &- (see convention below)
-                # If user wishes to use multiple targets, a multioutput prediction model
-                # needs to be used such as templates/CatboostPredictionMultiModel.py
-                df["&-s_close"] = (
-                    df["close"]
-                    .shift(-self.freqai_info["feature_parameters"]["label_period_candles"])
-                    .rolling(self.freqai_info["feature_parameters"]["label_period_candles"])
-                    .mean()
-                    / df["close"]
-                    - 1
-                    )
-    ```
-
-    (Please see the example script located in `freqtrade/templates/FreqaiExampleStrategy.py` for a full example of `populate_any_indicators()`.)
-
-## Setting classifier targets
-
-FreqAI includes the `CatboostClassifier` via the flag `--freqaimodel CatboostClassifier`. The user should take care to set the classes using strings:
-
-```python
-df['&s-up_or_down'] = np.where( df["close"].shift(-100) > df["close"], 'up', 'down')
-```
-
-Additionally, the example classifier models do not accommodate multiple labels, but they do allow multi-class classification within a single label column.
-
-## Running FreqAI
-
-There are two ways to train and deploy an adaptive machine learning model. FreqAI enables live deployment as well as backtesting analyses. In both cases, a model is trained periodically, as shown in the following figure.
-
-![freqai-window](assets/freqai_moving-window.jpg)
-
-### Running the model live
-
-FreqAI can be run dry/live using the following command:
-
-```bash
-freqtrade trade --strategy FreqaiExampleStrategy --config config_freqai.example.json --freqaimodel LightGBMRegressor
-```
-
-By default, FreqAI will not find any existing models and will start by training a new one
-based on the user's configuration settings. Following training, the model will be used to make predictions on incoming candles until a new model is available. New models are typically generated as often as possible, with FreqAI managing an internal queue of the coin pairs to try to keep all models equally up to date. FreqAI will always use the most recently trained model to make predictions on incoming live data. If the user does not want FreqAI to retrain new models as often as possible, they can set `live_retrain_hours` to tell FreqAI to wait at least that number of hours before training a new model. Additionally, the user can set `expired_hours` to tell FreqAI to avoid making predictions on models that are older than that number of hours.
-
-If the user wishes to start a dry/live run from a saved backtest model (or from a previously crashed dry/live session), the user only needs to reuse
-the same `identifier` parameter:
-
-```json
-    "freqai": {
-        "identifier": "example",
-        "live_retrain_hours": 0.5
-    }
-```
-
-In this case, although FreqAI will initiate with a
-pre-trained model, it will still check to see how much time has elapsed since the model was trained,
-and if a full `live_retrain_hours` has elapsed since the end of the loaded model, FreqAI will retrain.
-
-### Backtesting
-
-The FreqAI backtesting module can be executed with the following command:
-
-```bash
-freqtrade backtesting --strategy FreqaiExampleStrategy --config config_freqai.example.json --freqaimodel LightGBMRegressor --timerange 20210501-20210701
-```
-
-Backtesting mode requires the user to have the data pre-downloaded (unlike in dry/live mode where FreqAI automatically downloads the necessary data). The user should be careful to consider that the time range of the downloaded data is more than the backtesting time range. This is because FreqAI needs data prior to the desired backtesting time range in order to train a model to be ready to make predictions on the first candle of the user-set backtesting time range. More details on how to calculate the data to download can be found [here](#deciding-the-sliding-training-window-and-backtesting-duration).
-
-If this command has never been executed with the existing config file, it will train a new model
-for each pair, for each backtesting window within the expanded `--timerange`.
-
-!!! Note "Model reuse"
-    Once the training is completed, the user can execute the backtesting again with the same config file and
-    FreqAI will find the trained models and load them instead of spending time training. This is useful
-    if the user wants to tweak (or even hyperopt) buy and sell criteria inside the strategy. If the user
-    *wants* to retrain a new model with the same config file, then they should simply change the `identifier`.
-    This way, the user can return to using any model they wish by simply specifying the `identifier`.
-
----
-
-### Deciding the size of the sliding training window and backtesting duration
-
-The user defines the backtesting timerange with the typical `--timerange` parameter in the
-configuration file. The duration of the sliding training window is set by `train_period_days`, whilst
-`backtest_period_days` is the sliding backtesting window, both in number of days (`backtest_period_days` can be
-a float to indicate sub-daily retraining in live/dry mode). In the presented example config,
-the user is asking FreqAI to use a training period of 30 days and backtest on the subsequent 7 days.
-This means that if the user sets `--timerange 20210501-20210701`,
-FreqAI will train have trained 8 separate models at the end of `--timerange` (because the full range comprises 8 weeks). After the training of the model, FreqAI will backtest the subsequent 7 days. The "sliding window" then moves one week forward (emulating FreqAI retraining once per week in live mode) and the new model uses the previous 30 days (including the 7 days used for backtesting by the previous model) to train. This is repeated until the end of `--timerange`.
-
-In live mode, the required training data is automatically computed and downloaded. However, in backtesting mode,
-the user must manually enter the required number of `startup_candles` in the config. This value
-is used to increase the data to FreqAI, which should be sufficient to enable all indicators
-to be NaN free at the beginning of the first training. This is done by identifying the
-longest timeframe (`4h` in presented example config) and the longest indicator period (`20` days in presented example config)
-and adding this to the `train_period_days`. The units need to be in the base candle time frame:
-`startup_candles` = ( 4 hours * 20 max period * 60 minutes/hour + 30 day train_period_days * 1440 minutes per day ) / 5 min (base time frame) = 9360.
-
-!!! Note
-    In dry/live mode, this is all precomputed and handled automatically. Thus, `startup_candle` has no influence on dry/live mode.
-
-!!! Note
-    Although fractional `backtest_period_days` is allowed, the user should be aware that the `--timerange` is divided by this value to determine the number of models that FreqAI will need to train in order to backtest the full range. For example, if the user wants to set a `--timerange` of 10 days, and asks for a `backtest_period_days` of 0.1, FreqAI will need to train 100 models per pair to complete the full backtest. Because of this, a true backtest of FreqAI adaptive training would take a *very* long time. The best way to fully test a model is to run it dry and let it constantly train. In this case, backtesting would take the exact same amount of time as a dry run.
-
-### Defining model expirations
-
-During dry/live mode, FreqAI trains each coin pair sequentially (on separate threads/GPU from the main Freqtrade bot). This means that there is always an age discrepancy between models. If a user is training on 50 pairs, and each pair requires 5 minutes to train, the oldest model will be over 4 hours old. This may be undesirable if the characteristic time scale (the trade duration target) for a strategy is less than 4 hours. The user can decide to only make trade entries if the model is less than 
-a certain number of hours old by setting the `expiration_hours` in the config file:
-
-```json
-    "freqai": {
-        "expiration_hours": 0.5,
-    }
-```
-
-In the presented example config, the user will only allow predictions on models that are less than 1/2 hours old.
-
-### Purging old model data
-
-FreqAI stores new model files each time it retrains. These files become obsolete as new models are trained and FreqAI adapts to new market conditions. Users planning to leave FreqAI running for extended periods of time with high frequency retraining should enable `purge_old_models` in their config:
-
-```json
-    "freqai": {
-        "purge_old_models": true,
-    }
-```
-
-This will automatically purge all models older than the two most recently trained ones.
-
-### Returning additional info from training
-
-The user may find that there are some important metrics that they'd like to return to the strategy at the end of each model training.
-The user can include these metrics by assigning them to `dk.data['extra_returns_per_train']['my_new_value'] = XYZ` inside their custom prediction model class. FreqAI takes the `my_new_value` assigned in this dictionary and expands it to fit the return dataframe to the strategy.
-The user can then use the value in the strategy with `dataframe['my_new_value']`. An example of how this is already used in FreqAI is
-the `&*_mean` and `&*_std` values, which indicate the mean and standard deviation of the particular target (label) during the most recent training.
-An example, where the user wants to use live metrics from the trade database, is shown below:
-
-```json
-    "freqai": {
-        "extra_returns_per_train": {"total_profit": 4}
-    }
-```
-
-The user needs to set the standard dictionary in the config so that FreqAI can return proper dataframe shapes.  These values will likely be overridden by the prediction model, but in the case where the model has yet to set them, or needs a default initial value, this is the value that will be returned.
-
-### Setting up a follower
-
-The user can define:
-
-```json
-    "freqai": {
-        "follow_mode": true,
-        "identifier": "example"
-    }
-```
-
-to indicate to the bot that it should not train models, but instead should look for models trained by a leader with the same `identifier`. In this example, the user has a leader bot with the `identifier: "example"`. The leader bot is already running or launching simultaneously as the follower.
-The follower will load models created by the leader and inference them to obtain predictions.
-
-## Data manipulation techniques
-
-### Feature normalization
-
-The feature set created by the user is automatically normalized to the training data. This includes all test data and unseen prediction data (dry/live/backtest).
-
-### Reducing data dimensionality with Principal Component Analysis
-
-Users can reduce the dimensionality of their features by activating the `principal_component_analysis` in the config:
-
-```json
-    "freqai": {
-        "feature_parameters" : {
-            "principal_component_analysis": true
-        }
-    }
-```
-
-This will perform PCA on the features and reduce the dimensionality of the data so that the explained variance of the data set is >= 0.999.
-
-### Stratifying the data for training and testing the model
-
-The user can stratify (group) the training/testing data using:
-
-```json
-    "freqai": {
-        "feature_parameters" : {
-            "stratify_training_data": 3
-        }
-    }
-```
-
-This will split the data chronologically so that every Xth data point is used to test the model after training. In the
-example above, the user is asking for every third data point in the dataframe to be used for
-testing; the other points are used for training. 
-
-The test data is used to evaluate the performance of the model after training. If the test score is high, the model is able to capture the behavior of the data well. If the test score is low, either the model either does not capture the complexity of the data, the test data is significantly different from the train data, or a different model should be used. 
-
-### Controlling the model learning process
-
-Model training parameters are unique to the machine learning library selected by the user. FreqAI allows the user to set any parameter for any library using the `model_training_parameters` dictionary in the user configuration file. The example configuration file (found in `config_examples/config_freqai.example.json`) show some of the example parameters associated with `Catboost` and `LightGBM`, but the user can add any parameters available in those libraries.
-
-Data split parameters are defined in `data_split_parameters` which can be any parameters associated with `Sklearn`'s `train_test_split()` function. 
-
-FreqAI includes some additional parameters such as `weight_factor`, which allows the user to weight more recent data more strongly
-than past data via an exponential function:
-
-$$ W_i = \exp(\frac{-i}{\alpha*n}) $$
-
-where $W_i$ is the weight of data point $i$ in a total set of $n$ data points. Below is a figure showing the effect of different weight factors on the data points (candles) in a feature set.
-
-![weight-factor](assets/freqai_weight-factor.jpg)
-
-`train_test_split()` has a parameters called `shuffle` that allows the user to keep the data unshuffled. This is particularly useful to avoid biasing training with temporally auto-correlated data.
-
-Finally, `label_period_candles` defines the offset (number of candles into the future) used for the `labels`. In the presented example config,
-the user is asking for `labels` that are 24 candles in the future.
-
-### Outlier removal
-
-#### Removing outliers with the Dissimilarity Index
-
-The user can tell FreqAI to remove outlier data points from the training/test data sets using a Dissimilarity Index by including the following statement in the config:
-
-```json
-    "freqai": {
-        "feature_parameters" : {
-            "DI_threshold": 1
-        }
-    }
-```
-
-Equity and crypto markets suffer from a high level of non-patterned noise in the form of outlier data points. The Dissimilarity Index (DI) aims to quantify the uncertainty associated with each prediction made by the model. The DI allows predictions which are outliers (not existent in the model feature space) to be thrown out due to low levels of certainty. 
-
-To do so, FreqAI measures the distance between each training data point (feature vector), $X_{a}$, and all other training data points:
-
-$$ d_{ab} = \sqrt{\sum_{j=1}^p(X_{a,j}-X_{b,j})^2} $$
-
-where $d_{ab}$ is the distance between the normalized points $a$ and $b$. $p$ is the number of features, i.e., the length of the vector $X$. The characteristic distance, $\overline{d}$ for a set of training data points is simply the mean of the average distances:
-
-$$ \overline{d} = \sum_{a=1}^n(\sum_{b=1}^n(d_{ab}/n)/n) $$
-
-$\overline{d}$ quantifies the spread of the training data, which is compared to the distance between a new prediction feature vectors, $X_k$ and all the training data:
-
-$$ d_k = \arg \min d_{k,i} $$
-
-which enables the estimation of the Dissimilarity Index as:
-
-$$ DI_k = d_k/\overline{d} $$
-
-The user can tweak the DI through the `DI_threshold` to increase or decrease the extrapolation of the trained model. 
-
-Below is a figure that describes the DI for a 3D data set.
-
-![DI](assets/freqai_DI.jpg)
-
-#### Removing outliers using a Support Vector Machine (SVM)
-
-The user can tell FreqAI to remove outlier data points from the training/test data sets using a SVM by setting:
-
-```json
-    "freqai": {
-        "feature_parameters" : {
-            "use_SVM_to_remove_outliers": true
-        }
-    }
-```
-
-FreqAI will train an SVM on the training data (or components of it if the user activated
-`principal_component_analysis`) and remove any data point that the SVM deems to be beyond the feature space. 
-
-The parameter `shuffle` is by default set to `False` to ensure consistent results. If it is set to `True`, running the SVM multiple times on the same data set might result in different outcomes due to `max_iter` being to low for the algorithm to reach the demanded `tol`. Increasing `max_iter` solves this issue but causes the procedure to take longer time. 
-
-The parameter `nu`, *very* broadly, is the amount of data points that should be considered outliers. 
-
-#### Removing outliers with DBSCAN
-
-The user can configure FreqAI to use DBSCAN to cluster and remove outliers from the training/test data set or incoming outliers from predictions, by activating `use_DBSCAN_to_remove_outliers` in the config:
-
-```json
-    "freqai": {
-        "feature_parameters" : {
-            "use_DBSCAN_to_remove_outliers": true
-        }
-    }
-```
-
-DBSCAN is an unsupervised machine learning algorithm that clusters data without needing to know how many clusters there should be.
-
-Given a number of data points $N$, and a distance $\varepsilon$, DBSCAN clusters the data set by setting all data points that have $N-1$ other data points within a distance of $\varepsilon$ as *core points*. A data point that is within a distance of $\varepsilon$ from a *core point* but that does not have $N-1$ other data points within a distance of $\varepsilon$ from itself is considered an *edge point*. A cluster is then the collection of *core points* and *edge points*. Data points that have no other data points at a distance $<\varepsilon$ are considered outliers. The figure below shows a cluster with $N = 3$.
-
-![dbscan](assets/freqai_dbscan.jpg)
-
-FreqAI uses `sklearn.cluster.DBSCAN` (details are available on scikit-learn's webpage [here](#https://scikit-learn.org/stable/modules/generated/sklearn.cluster.DBSCAN.html)) with `min_samples` ($N$) taken as double the no. of user-defined features, and `eps` ($\varepsilon$) taken as the longest distance in the *k-distance graph* computed from the nearest neighbors in the pairwise distances of all data points in the feature set.
-
-## Additional information
-
-### Common pitfalls
+## Common pitfalls
 
 FreqAI cannot be combined with dynamic `VolumePairlists` (or any pairlist filter that adds and removes pairs dynamically).
 This is for performance reasons - FreqAI relies on making quick predictions/retrains. To do this effectively,
@@ -743,17 +81,19 @@ new candles automatically for future retrains. This means that if new pairs arri
 
 ## Credits
 
-FreqAI was developed by a group of individuals who all contributed specific skillsets to the project.
+FreqAI is developed by a group of individuals who all contribute specific skillsets to the project.
 
 Conception and software development:
 Robert Caulk @robcaulk
 
-Theoretical brainstorming, data analysis:
+Theoretical brainstorming and data analysis:
 Elin Törnquist @th0rntwig
 
-Code review, software architecture brainstorming:
+Code review and software architecture brainstorming:
 @xmatthias
 
+Software development:
+Wagner Costa @wagnercosta
+
 Beta testing and bug reporting:
-@bloodhunter4rc, Salah Lamkadem @ikonx, @ken11o2, @longyu, @paranoidandy, @smidelis, @smarm
-Juha Nykänen @suikula, Wagner Costa @wagnercosta
+Stefan Gehring @bloodhunter4rc, @longyu, Andrew Lawless @paranoidandy, Pascal Schmidt @smidelis, Ryan McMullan @smarmau, Juha Nykänen @suikula, Johan van der Vlugt @jooopiert, Richárd Józsa @richardjosza, Timothy Pogue @wizrds

docs/includes/pairlists.md

@@ -22,6 +22,7 @@ You may also use something like `.*DOWN/BTC` or `.*UP/BTC` to exclude leveraged
 
 * [`StaticPairList`](#static-pair-list) (default, if not configured differently)
 * [`VolumePairList`](#volume-pair-list)
+* [`ProducerPairList`](#producerpairlist)
 * [`AgeFilter`](#agefilter)
 * [`OffsetFilter`](#offsetfilter)
 * [`PerformanceFilter`](#performancefilter)
@@ -84,7 +85,7 @@ Filtering instances (not the first position in the list) will not apply any cach
 
 You can define a minimum volume with `min_value` - which will filter out pairs with a volume lower than the specified value in the specified timerange.
 
-### VolumePairList Advanced mode
+##### VolumePairList Advanced mode
 
 `VolumePairList` can also operate in an advanced mode to build volume over a given timerange of specified candle size. It utilizes exchange historical candle data, builds a typical price (calculated by (open+high+low)/3) and multiplies the typical price with every candle's volume. The sum is the `quoteVolume` over the given range. This allows different scenarios, for a  more smoothened volume, when using longer ranges with larger candle sizes, or the opposite when using a short range with small candles.
 
@@ -146,6 +147,32 @@ More sophisticated approach can be used, by using `lookback_timeframe` for candl
 !!! Note
     `VolumePairList` does not support backtesting mode.
 
+#### ProducerPairList
+
+With `ProducerPairList`, you can reuse the pairlist from a [Producer](producer-consumer.md) without explicitly defining the pairlist on each consumer.
+
+[Consumer mode](producer-consumer.md) is required for this pairlist to work.
+
+The pairlist will perform a check on active pairs against the current exchange configuration to avoid attempting to trade on invalid markets.
+
+You can limit the length of the pairlist with the optional parameter `number_assets`. Using `"number_assets"=0` or omitting this key will result in the reuse of all producer pairs valid for the current setup.
+
+```json
+"pairlists": [
+    {
+        "method": "ProducerPairList",
+        "number_assets": 5,
+        "producer_name": "default",
+    }
+],
+```
+
+
+!!! Tip "Combining pairlists"
+    This pairlist can be combined with all other pairlists and filters for further pairlist reduction, and can also act as an "additional" pairlist, on top of already defined pairs.
+    `ProducerPairList` can also be used multiple times in sequence, combining the pairs from multiple producers.
+    Obviously in complex such configurations, the Producer may not provide data for all pairs, so the strategy must be fit for this.
+
 #### AgeFilter
 
 Removes pairs that have been listed on the exchange for less than `min_days_listed` days (defaults to `10`) or more than `max_days_listed` days (defaults `None` mean infinity).

docs/leverage.md

@@ -13,7 +13,7 @@
     Please only use advanced trading modes when you know how freqtrade (and your strategy) works.
     Also, never risk more than what you can afford to lose.
 
-Please read the [strategy migration guide](strategy_migration.md#strategy-migration-between-v2-and-v3) to migrate your strategy from a freqtrade v2 strategy, to v3 strategy that can short and trade futures.
+If you already have an existing strategy, please read the [strategy migration guide](strategy_migration.md#strategy-migration-between-v2-and-v3) to migrate your strategy from a freqtrade v2 strategy, to strategy of version 3 which can short and trade futures.
 
 ## Shorting
 
@@ -62,6 +62,13 @@ You will also have to pick a "margin mode" (explanation below) - with freqtrade
 "margin_mode": "isolated"
 ```
 
+##### Pair namings
+
+Freqtrade follows the [ccxt naming conventions for futures](https://docs.ccxt.com/en/latest/manual.html?#perpetual-swap-perpetual-future).
+A futures pair will therefore have the naming of `base/quote:settle` (e.g. `ETH/USDT:USDT`).
+
+Binance is currently still an exception to this naming scheme, where pairs are named `ETH/USDT` also for futures markets, but will be aligned as soon as CCXT is ready.
+
 ### Margin mode
 
 On top of `trading_mode` - you will also have to configure your `margin_mode`.

docs/producer-consumer.md

@@ -0,0 +1,163 @@
+# Producer / Consumer mode
+
+freqtrade provides a mechanism whereby an instance (also called `consumer`) may listen to messages from an upstream freqtrade instance (also called `producer`) using the message websocket. Mainly, `analyzed_df` and `whitelist` messages. This allows the reuse of computed indicators (and signals) for pairs in multiple bots without needing to compute them multiple times.
+
+See [Message Websocket](rest-api.md#message-websocket) in the Rest API docs for setting up the `api_server` configuration for your message websocket (this will be your producer).
+
+!!! Note
+    We strongly recommend to set `ws_token` to something random and known only to yourself to avoid unauthorized access to your bot.
+
+## Configuration
+
+Enable subscribing to an instance by adding the `external_message_consumer` section to the consumer's config file.
+
+```json
+{
+    //...
+   "external_message_consumer": {
+        "enabled": true,
+        "producers": [
+            {
+                "name": "default", // This can be any name you'd like, default is "default"
+                "host": "127.0.0.1", // The host from your producer's api_server config
+                "port": 8080, // The port from your producer's api_server config
+                "ws_token": "sercet_Ws_t0ken" // The ws_token from your producer's api_server config
+            }
+        ],
+        // The following configurations are optional, and usually not required
+        // "wait_timeout": 300,
+        // "ping_timeout": 10,
+        // "sleep_time": 10,
+        // "remove_entry_exit_signals": false,
+        // "message_size_limit": 8
+    }
+    //...
+}
+```
+
+|  Parameter | Description |
+|------------|-------------|
+| `enabled` | **Required.** Enable consumer mode. If set to false, all other settings in this section are ignored.<br>*Defaults to `false`.*<br> **Datatype:** boolean .
+| `producers` | **Required.** List of producers <br> **Datatype:** Array.
+| `producers.name` | **Required.** Name of this producer. This name must be used in calls to `get_producer_pairs()` and `get_producer_df()` if more than one producer is used.<br> **Datatype:** string
+| `producers.host` | **Required.** The hostname or IP address from your producer.<br> **Datatype:** string
+| `producers.port` | **Required.** The port matching the above host.<br> **Datatype:** string
+| `producers.ws_token` | **Required.**  `ws_token` as configured on the producer.<br> **Datatype:** string
+| | **Optional settings**
+| `wait_timeout` | Timeout until we ping again if no message is received. <br>*Defaults to `300`.*<br> **Datatype:** Integer - in seconds.
+| `wait_timeout` | Ping timeout <br>*Defaults to `10`.*<br> **Datatype:** Integer - in seconds.
+| `sleep_time` | Sleep time before retrying to connect.<br>*Defaults to `10`.*<br> **Datatype:** Integer - in seconds.
+| `remove_entry_exit_signals` | Remove signal columns from the dataframe (set them to 0) on dataframe receipt.<br>*Defaults to `10`.*<br> **Datatype:** Integer - in seconds.
+| `message_size_limit` | Size limit per message<br>*Defaults to `8`.*<br> **Datatype:** Integer - Megabytes.
+
+Instead of (or as well as) calculating indicators in `populate_indicators()` the follower instance listens on the connection to a producer instance's messages (or multiple producer instances in advanced configurations) and requests the producer's most recently analyzed dataframes for each pair in the active whitelist.
+
+A consumer instance will then have a full copy of the analyzed dataframes without the need to calculate them itself.
+
+## Examples
+
+### Example - Producer Strategy
+
+A simple strategy with multiple indicators. No special considerations are required in the strategy itself.
+
+```py
+class ProducerStrategy(IStrategy):
+    #...
+    def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
+        """
+        Calculate indicators in the standard freqtrade way which can then be broadcast to other instances
+        """
+        dataframe['rsi'] = ta.RSI(dataframe)
+        bollinger = qtpylib.bollinger_bands(qtpylib.typical_price(dataframe), window=20, stds=2)
+        dataframe['bb_lowerband'] = bollinger['lower']
+        dataframe['bb_middleband'] = bollinger['mid']
+        dataframe['bb_upperband'] = bollinger['upper']
+        dataframe['tema'] = ta.TEMA(dataframe, timeperiod=9)
+
+        return dataframe
+
+    def populate_entry_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
+        """
+        Populates the entry signal for the given dataframe
+        """
+        dataframe.loc[
+            (
+                (qtpylib.crossed_above(dataframe['rsi'], self.buy_rsi.value)) &
+                (dataframe['tema'] <= dataframe['bb_middleband']) &
+                (dataframe['tema'] > dataframe['tema'].shift(1)) &
+                (dataframe['volume'] > 0)
+            ),
+            'enter_long'] = 1
+
+        return dataframe
+```
+
+!!! Tip "FreqAI"
+    You can use this to setup [FreqAI](freqai.md) on a powerful machine, while you run consumers on simple machines like raspberries, which can interpret the signals generated from the producer in different ways.
+
+
+### Example - Consumer Strategy
+
+A logically equivalent strategy which calculates no indicators itself, but will have the same analyzed dataframes available to make trading decisions based on the indicators calculated in the producer. In this example the consumer has the same entry criteria, however this is not necessary. The consumer may use different logic to enter/exit trades, and only use the indicators as specified.
+
+```py
+class ConsumerStrategy(IStrategy):
+    #...
+    process_only_new_candles = False # required for consumers
+
+    _columns_to_expect = ['rsi_default', 'tema_default', 'bb_middleband_default']
+
+    def populate_indicators(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
+        """
+        Use the websocket api to get pre-populated indicators from another freqtrade instance.
+        Use `self.dp.get_producer_df(pair)` to get the dataframe
+        """
+        pair = metadata['pair']
+        timeframe = self.timeframe
+
+        producer_pairs = self.dp.get_producer_pairs()
+        # You can specify which producer to get pairs from via:
+        # self.dp.get_producer_pairs("my_other_producer")
+
+        # This func returns the analyzed dataframe, and when it was analyzed
+        producer_dataframe, _ = self.dp.get_producer_df(pair)
+        # You can get other data if the producer makes it available:
+        # self.dp.get_producer_df(
+        #   pair,
+        #   timeframe="1h",
+        #   candle_type=CandleType.SPOT,
+        #   producer_name="my_other_producer"
+        # )
+
+        if not producer_dataframe.empty:
+            # If you plan on passing the producer's entry/exit signal directly,
+            # specify ffill=False or it will have unintended results
+            merged_dataframe = merge_informative_pair(dataframe, producer_dataframe,
+                                                      timeframe, timeframe,
+                                                      append_timeframe=False,
+                                                      suffix="default")
+            return merged_dataframe
+        else:
+            dataframe[self._columns_to_expect] = 0
+
+        return dataframe
+
+    def populate_entry_trend(self, dataframe: DataFrame, metadata: dict) -> DataFrame:
+        """
+        Populates the entry signal for the given dataframe
+        """
+        # Use the dataframe columns as if we calculated them ourselves
+        dataframe.loc[
+            (
+                (qtpylib.crossed_above(dataframe['rsi_default'], self.buy_rsi.value)) &
+                (dataframe['tema_default'] <= dataframe['bb_middleband_default']) &
+                (dataframe['tema_default'] > dataframe['tema_default'].shift(1)) &
+                (dataframe['volume'] > 0)
+            ),
+            'enter_long'] = 1
+
+        return dataframe
+```
+
+!!! Tip "Using upstream signals"
+    By setting `remove_entry_exit_signals=false`, you can also use the producer's signals directly. They should be available as `enter_long_default` (assuming `suffix="default"` was used) - and can be used as either signal directly, or as additional indicator.

docs/requirements-docs.txt

@@ -1,6 +1,6 @@
 markdown==3.3.7
-mkdocs==1.3.1
-mkdocs-material==8.4.1
+mkdocs==1.4.0
+mkdocs-material==8.5.6
 mdx_truly_sane_lists==1.3
-pymdown-extensions==9.5
+pymdown-extensions==9.6
 jinja2==3.1.2

docs/rest-api.md

@@ -31,7 +31,8 @@ Sample configuration:
         "jwt_secret_key": "somethingrandom",
         "CORS_origins": [],
         "username": "Freqtrader",
-        "password": "SuperSecret1!"
+        "password": "SuperSecret1!",
+        "ws_token": "sercet_Ws_t0ken"
     },
 ```
 
@@ -66,7 +67,7 @@ secrets.token_hex()
 
 !!! Danger "Password selection"
     Please make sure to select a very strong, unique password to protect your bot from unauthorized access.
-    Also change `jwt_secret_key` to something random (no need to remember this, but it'll be used to encrypt your session, so it better be something unique!). 
+    Also change `jwt_secret_key` to something random (no need to remember this, but it'll be used to encrypt your session, so it better be something unique!).
 
 ### Configuration with docker
 
@@ -93,7 +94,6 @@ Make sure that the following 2 lines are available in your docker-compose file:
 !!! Danger "Security warning"
     By using `8080:8080` in the docker port mapping, the API will be available to everyone connecting to the server under the correct port, so others may be able to control your bot.
 
-
 ## Rest API
 
 ### Consuming the API
@@ -274,7 +274,7 @@ reload_config
 	Reload configuration.
 
 show_config
-	
+
         Returns part of the configuration, relevant for trading operations.
 
 start
@@ -322,6 +322,73 @@ whitelist
 
 ```
 
+### Message WebSocket
+
+The API Server includes a websocket endpoint for subscribing to RPC messages from the freqtrade Bot.
+This can be used to consume real-time data from your bot, such as entry/exit fill messages, whitelist changes, populated indicators for pairs, and more.
+
+This is also used to setup [Producer/Consumer mode](producer-consumer.md) in Freqtrade.
+
+Assuming your rest API is set to `127.0.0.1` on port `8080`, the endpoint is available at `http://localhost:8080/api/v1/message/ws`.
+
+To access the websocket endpoint, the `ws_token` is required as a query parameter in the endpoint URL.
+
+To generate a safe `ws_token` you can run the following code:
+
+``` python
+>>> import secrets
+>>> secrets.token_urlsafe(25)
+'hZ-y58LXyX_HZ8O1cJzVyN6ePWrLpNQv4Q'
+```
+
+You would then add that token under `ws_token` in your `api_server` config. Like so:
+
+``` json
+"api_server": {
+    "enabled": true,
+    "listen_ip_address": "127.0.0.1",
+    "listen_port": 8080,
+    "verbosity": "error",
+    "enable_openapi": false,
+    "jwt_secret_key": "somethingrandom",
+    "CORS_origins": [],
+    "username": "Freqtrader",
+    "password": "SuperSecret1!",
+    "ws_token": "hZ-y58LXyX_HZ8O1cJzVyN6ePWrLpNQv4Q" // <-----
+},
+```
+
+You can now connect to the endpoint at `http://localhost:8080/api/v1/message/ws?token=hZ-y58LXyX_HZ8O1cJzVyN6ePWrLpNQv4Q`.
+
+!!! Danger "Reuse of example tokens"
+    Please do not use the above example token. To make sure you are secure, generate a completely new token.
+
+#### Using the WebSocket
+
+Once connected to the WebSocket, the bot will broadcast RPC messages to anyone who is subscribed to them. To subscribe to a list of messages, you must send a JSON request through the WebSocket like the one below. The `data` key must be a list of message type strings.
+
+``` json
+{
+  "type": "subscribe",
+  "data": ["whitelist", "analyzed_df"] // A list of string message types
+}
+```
+
+For a list of message types, please refer to the RPCMessageType enum in `freqtrade/enums/rpcmessagetype.py`
+
+Now anytime those types of RPC messages are sent in the bot, you will receive them through the WebSocket as long as the connection is active. They typically take the same form as the request:
+
+``` json
+{
+  "type": "analyzed_df",
+  "data": {
+      "key": ["NEO/BTC", "5m", "spot"],
+      "df": {}, // The dataframe
+      "la": "2022-09-08 22:14:41.457786+00:00"
+  }
+}
+```
+
 ### OpenAPI interface
 
 To enable the builtin openAPI interface (Swagger UI), specify `"enable_openapi": true` in the api_server configuration.

docs/strategy-advanced.md

@@ -106,6 +106,12 @@ def custom_exit(self, pair: str, trade: Trade, current_time: datetime, current_r
 !!! Note
     `enter_tag` is limited to 100 characters, remaining data will be truncated.
 
+!!! Warning
+    There is only one `enter_tag` column, which is used for both long and short trades.
+    As a consequence, this column must be treated as "last write wins" (it's just a dataframe column after all).
+    In fancy situations, where multiple signals collide (or if signals are deactivated again based on different conditions), this can lead to odd results with the wrong tag applied to an entry signal.
+    These results are a consequence of the strategy overwriting prior tags - where the last tag will "stick" and will be the one freqtrade will use.
+
 ## Exit tag
 
 Similar to [Buy Tagging](#buy-tag), you can also specify a sell tag.

docs/strategy-callbacks.md

@@ -643,7 +643,7 @@ This callback is **not** called when there is an open order (either buy or sell)
 
 Additional Buys are ignored once you have reached the maximum amount of extra buys that you have set on `max_entry_position_adjustment`, but the callback is called anyway looking for partial exits.
 
-Position adjustments will always be applied in the direction of the trade, so a positive value will always increase your position (negative values will decrease your position), no matter if it's a long or short trade. Modifications to leverage are not possible.
+Position adjustments will always be applied in the direction of the trade, so a positive value will always increase your position (negative values will decrease your position), no matter if it's a long or short trade. Modifications to leverage are not possible, and the stake-amount is assumed to be before applying leverage.
 
 !!! Note "About stake size"
     Using fixed stake size means it will be the amount used for the first order, just like without position adjustment.

docs/strategy-customization.md

@@ -166,7 +166,7 @@ Additional technical libraries can be installed as necessary, or custom indicato
 
 Most indicators have an instable startup period, in which they are either not available (NaN), or the calculation is incorrect. This can lead to inconsistencies, since Freqtrade does not know how long this instable period should be.
 To account for this, the strategy can be assigned the `startup_candle_count` attribute.
-This should be set to the maximum number of candles that the strategy requires to calculate stable indicators.
+This should be set to the maximum number of candles that the strategy requires to calculate stable indicators. In the case where a user includes higher timeframes with informative pairs, the `startup_candle_count` does not necessarily change. The value is the maximum period (in candles) that any of the informatives timeframes need to compute stable indicators.
 
 In this example strategy, this should be set to 100 (`startup_candle_count = 100`), since the longest needed history is 100 candles.
 
@@ -264,7 +264,8 @@ def populate_entry_trend(self, dataframe: DataFrame, metadata: dict) -> DataFram
 ### Exit signal rules
 
 Edit the method `populate_exit_trend()` into your strategy file to update your exit strategy.
-Please note that the exit-signal is only used if `use_exit_signal` is set to true in the configuration.
+The exit-signal is only used for exits if `use_exit_signal` is set to true in the configuration.
+`use_exit_signal` will not influence [signal collision rules](#colliding-signals) - which will still apply and can prevent entries.
 
 It's important to always return the dataframe without removing/modifying the columns `"open", "high", "low", "close", "volume"`, otherwise these fields would contain something unexpected.
 
@@ -824,6 +825,8 @@ Options:
 - Merge the dataframe without lookahead bias
 - Forward-fill (optional)
 
+For a full sample, please refer to the [complete data provider example](#complete-data-provider-sample) below.
+
 All columns of the informative dataframe will be available on the returning dataframe in a renamed fashion:
 
 !!! Example "Column renaming"

docs/strategy_migration.md

@@ -332,8 +332,8 @@ After:
 
 ``` python hl_lines="2 3"
     order_time_in_force: Dict = {
-        "entry": "gtc",
-        "exit": "gtc",
+        "entry": "GTC",
+        "exit": "GTC",
     }
 ```
 

docs/telegram-usage.md

@@ -82,6 +82,8 @@ Example configuration showing the different settings:
         "warning": "on",
         "startup": "off",
         "entry": "silent",
+        "entry_fill": "on",
+        "entry_cancel": "silent",
         "exit": {
             "roi": "silent",
             "emergency_exit": "on",
@@ -90,11 +92,10 @@ Example configuration showing the different settings:
             "trailing_stop_loss": "on",
             "stop_loss": "on",
             "stoploss_on_exchange": "on",
-            "custom_exit": "silent"
+            "custom_exit": "silent",
+            "partial_exit": "on"
         },
-        "entry_cancel": "silent",
         "exit_cancel": "on",
-        "entry_fill": "off",
         "exit_fill": "off",
         "protection_trigger": "off",
         "protection_trigger_global": "on",
@@ -138,7 +139,7 @@ You can create your own keyboard in `config.json`:
       "enabled": true,
       "token": "your_telegram_token",
       "chat_id": "your_telegram_chat_id",
-      "keyboard": [   
+      "keyboard": [
           ["/daily", "/stats", "/balance", "/profit"],
           ["/status table", "/performance"],
           ["/reload_config", "/count", "/logs"]
@@ -225,16 +226,16 @@ Once all positions are sold, run `/stop` to completely stop the bot.
 For each open trade, the bot will send you the following message.
 Enter Tag is configurable via Strategy.
 
-> **Trade ID:** `123` `(since 1 days ago)`  
-> **Current Pair:** CVC/BTC  
+> **Trade ID:** `123` `(since 1 days ago)`
+> **Current Pair:** CVC/BTC
 > **Direction:** Long
 > **Leverage:** 1.0
-> **Amount:** `26.64180098`  
+> **Amount:** `26.64180098`
 > **Enter Tag:** Awesome Long Signal
-> **Open Rate:** `0.00007489`  
-> **Current Rate:** `0.00007489`  
-> **Current Profit:** `12.95%`  
-> **Stoploss:** `0.00007389 (-0.02%)`  
+> **Open Rate:** `0.00007489`
+> **Current Rate:** `0.00007489`
+> **Current Profit:** `12.95%`
+> **Stoploss:** `0.00007389 (-0.02%)`
 
 ### /status table
 
@@ -261,26 +262,26 @@ current    max
 
 Return a summary of your profit/loss and performance.
 
-> **ROI:** Close trades  
->   ∙ `0.00485701 BTC (2.2%) (15.2 Σ%)`  
->   ∙ `62.968 USD`  
-> **ROI:** All trades  
->   ∙ `0.00255280 BTC (1.5%) (6.43 Σ%)`  
->   ∙ `33.095 EUR`  
->  
-> **Total Trade Count:** `138`  
-> **First Trade opened:** `3 days ago`  
-> **Latest Trade opened:** `2 minutes ago`  
-> **Avg. Duration:** `2:33:45`  
-> **Best Performing:** `PAY/BTC: 50.23%`  
-> **Trading volume:** `0.5 BTC`  
-> **Profit factor:** `1.04`  
-> **Max Drawdown:** `9.23% (0.01255 BTC)`  
+> **ROI:** Close trades
+>   ∙ `0.00485701 BTC (2.2%) (15.2 Σ%)`
+>   ∙ `62.968 USD`
+> **ROI:** All trades
+>   ∙ `0.00255280 BTC (1.5%) (6.43 Σ%)`
+>   ∙ `33.095 EUR`
+>
+> **Total Trade Count:** `138`
+> **First Trade opened:** `3 days ago`
+> **Latest Trade opened:** `2 minutes ago`
+> **Avg. Duration:** `2:33:45`
+> **Best Performing:** `PAY/BTC: 50.23%`
+> **Trading volume:** `0.5 BTC`
+> **Profit factor:** `1.04`
+> **Max Drawdown:** `9.23% (0.01255 BTC)`
 
-The relative profit of `1.2%` is the average profit per trade.  
-The relative profit of `15.2 Σ%` is be based on the starting capital - so in this case, the starting capital was `0.00485701 * 1.152 = 0.00738 BTC`.  
-Starting capital is either taken from the `available_capital` setting, or calculated by using current wallet size - profits.  
-Profit Factor is calculated as gross profits / gross losses - and should serve as an overall metric for the strategy.  
+The relative profit of `1.2%` is the average profit per trade.
+The relative profit of `15.2 Σ%` is be based on the starting capital - so in this case, the starting capital was `0.00485701 * 1.152 = 0.00738 BTC`.
+Starting capital is either taken from the `available_capital` setting, or calculated by using current wallet size - profits.
+Profit Factor is calculated as gross profits / gross losses - and should serve as an overall metric for the strategy.
 Max drawdown corresponds to the backtesting metric `Absolute Drawdown (Account)` - calculated as `(Absolute Drawdown) / (DrawdownHigh + startingBalance)`.
 
 ### /forceexit <trade_id>
@@ -309,27 +310,27 @@ Note that for this to work, `force_entry_enable` needs to be set to true.
 ### /performance
 
 Return the performance of each crypto-currency the bot has sold.
-> Performance:  
-> 1. `RCN/BTC 0.003 BTC (57.77%) (1)`  
-> 2. `PAY/BTC 0.0012 BTC (56.91%) (1)`  
-> 3. `VIB/BTC 0.0011 BTC (47.07%) (1)`  
-> 4. `SALT/BTC 0.0010 BTC (30.24%) (1)`  
-> 5. `STORJ/BTC 0.0009 BTC (27.24%) (1)`  
-> ...  
+> Performance:
+> 1. `RCN/BTC 0.003 BTC (57.77%) (1)`
+> 2. `PAY/BTC 0.0012 BTC (56.91%) (1)`
+> 3. `VIB/BTC 0.0011 BTC (47.07%) (1)`
+> 4. `SALT/BTC 0.0010 BTC (30.24%) (1)`
+> 5. `STORJ/BTC 0.0009 BTC (27.24%) (1)`
+> ...
 
 ### /balance
 
 Return the balance of all crypto-currency your have on the exchange.
 
-> **Currency:** BTC  
-> **Available:** 3.05890234  
-> **Balance:** 3.05890234  
-> **Pending:** 0.0  
+> **Currency:** BTC
+> **Available:** 3.05890234
+> **Balance:** 3.05890234
+> **Pending:** 0.0
 
-> **Currency:** CVC  
-> **Available:** 86.64180098  
-> **Balance:** 86.64180098  
-> **Pending:** 0.0  
+> **Currency:** CVC
+> **Available:** 86.64180098
+> **Balance:** 86.64180098
+> **Pending:** 0.0
 
 ### /daily <n>
 
@@ -376,7 +377,7 @@ Month (count)  Profit BTC      Profit USD    Profit %
 
 Shows the current whitelist
 
-> Using whitelist `StaticPairList` with 22 pairs  
+> Using whitelist `StaticPairList` with 22 pairs
 > `IOTA/BTC, NEO/BTC, TRX/BTC, VET/BTC, ADA/BTC, ETC/BTC, NCASH/BTC, DASH/BTC, XRP/BTC, XVG/BTC, EOS/BTC, LTC/BTC, OMG/BTC, BTG/BTC, LSK/BTC, ZEC/BTC, HOT/BTC, IOTX/BTC, XMR/BTC, AST/BTC, XLM/BTC, NANO/BTC`
 
 ### /blacklist [pair]
@@ -386,7 +387,7 @@ If Pair is set, then this pair will be added to the pairlist.
 Also supports multiple pairs, separated by a space.
 Use `/reload_config` to reset the blacklist.
 
-> Using blacklist `StaticPairList` with 2 pairs  
+> Using blacklist `StaticPairList` with 2 pairs
 >`DODGE/BTC`, `HOT/BTC`.
 
 ### /edge

docs/updating.md

@@ -37,3 +37,12 @@ pip install -e .
 # Ensure freqUI is at the latest version
 freqtrade install-ui 
 ```
+
+### Problems updating
+
+Update-problems usually come missing dependencies (you didn't follow the above instructions) - or from updated dependencies, which fail to install (for example TA-lib).
+Please refer to the corresponding installation sections (common problems linked below)
+
+Common problems and their solutions:
+
+* [ta-lib update on windows](windows_installation.md#2-install-ta-lib)

docs/utils.md

@@ -525,12 +525,14 @@ Requires a configuration with specified `pairlists` attribute.
 Can be used to generate static pairlists to be used during backtesting / hyperopt.
 
 ```
-usage: freqtrade test-pairlist [-h] [-v] [-c PATH]
+usage: freqtrade test-pairlist [-h] [--userdir PATH] [-v] [-c PATH]
                                [--quote QUOTE_CURRENCY [QUOTE_CURRENCY ...]]
                                [-1] [--print-json] [--exchange EXCHANGE]
 
 optional arguments:
   -h, --help            show this help message and exit
+  --userdir PATH, --user-data-dir PATH
+                        Path to userdata directory.
   -v, --verbose         Verbose mode (-vv for more, -vvv to get all messages).
   -c PATH, --config PATH
                         Specify configuration file (default:

docs/windows_installation.md

@@ -23,7 +23,7 @@ git clone https://github.com/freqtrade/freqtrade.git
 
 Install ta-lib according to the [ta-lib documentation](https://github.com/mrjbq7/ta-lib#windows).
 
-As compiling from source on windows has heavy dependencies (requires a partial visual studio installation), there is also a repository of unofficial pre-compiled windows Wheels [here](https://www.lfd.uci.edu/~gohlke/pythonlibs/#ta-lib), which need to be downloaded and installed using `pip install TA_Lib-0.4.24-cp38-cp38-win_amd64.whl` (make sure to use the version matching your python version).
+As compiling from source on windows has heavy dependencies (requires a partial visual studio installation), there is also a repository of unofficial pre-compiled windows Wheels [here](https://www.lfd.uci.edu/~gohlke/pythonlibs/#ta-lib), which need to be downloaded and installed using `pip install TA_Lib-0.4.25-cp38-cp38-win_amd64.whl` (make sure to use the version matching your python version).
 
 Freqtrade provides these dependencies for the latest 3 Python versions (3.8, 3.9 and 3.10) and for 64bit Windows.
 Other versions must be downloaded from the above link.
@@ -34,7 +34,7 @@ python -m venv .env
 .env\Scripts\activate.ps1
 # optionally install ta-lib from wheel
 # Eventually adjust the below filename to match the downloaded wheel
-pip install build_helpers/TA_Lib-0.4.19-cp38-cp38-win_amd64.whl
+pip install --find-links build_helpers\ TA-Lib -U
 pip install -r requirements.txt
 pip install -e .
 freqtrade

environment.yml

@@ -34,6 +34,7 @@ dependencies:
     - schedule
     - python-dateutil
     - joblib
+    - pyarrow
 
 
     # ============================

freqtrade/__init__.py

@@ -1,5 +1,5 @@
 """ Freqtrade bot """
-__version__ = '2022.8.dev'
+__version__ = '2022.10.dev'
 
 if 'dev' in __version__:
     try:

freqtrade/commands/arguments.py

@@ -53,8 +53,8 @@ ARGS_LIST_PAIRS = ["exchange", "print_list", "list_pairs_print_json", "print_one
                    "print_csv", "base_currencies", "quote_currencies", "list_pairs_all",
                    "trading_mode"]
 
-ARGS_TEST_PAIRLIST = ["verbosity", "config", "quote_currencies", "print_one_column",
-                      "list_pairs_print_json", "exchange"]
+ARGS_TEST_PAIRLIST = ["user_data_dir", "verbosity", "config", "quote_currencies",
+                      "print_one_column", "list_pairs_print_json", "exchange"]
 
 ARGS_CREATE_USERDIR = ["user_data_dir", "reset"]
 
@@ -62,9 +62,9 @@ ARGS_BUILD_CONFIG = ["config"]
 
 ARGS_BUILD_STRATEGY = ["user_data_dir", "strategy", "template"]
 
-ARGS_CONVERT_DATA = ["pairs", "format_from", "format_to", "erase"]
+ARGS_CONVERT_DATA = ["pairs", "format_from", "format_to", "erase", "exchange"]
 
-ARGS_CONVERT_DATA_OHLCV = ARGS_CONVERT_DATA + ["timeframes", "exchange", "trading_mode",
+ARGS_CONVERT_DATA_OHLCV = ARGS_CONVERT_DATA + ["timeframes", "trading_mode",
                                                "candle_types"]
 
 ARGS_CONVERT_TRADES = ["pairs", "timeframes", "exchange", "dataformat_ohlcv", "dataformat_trades"]

freqtrade/commands/build_config_commands.py

@@ -211,6 +211,7 @@ def ask_user_config() -> Dict[str, Any]:
     )
     # Force JWT token to be a random string
     answers['api_server_jwt_key'] = secrets.token_hex()
+    answers['api_server_ws_token'] = secrets.token_urlsafe(25)
 
     return answers
 

freqtrade/commands/cli_options.py

@@ -69,7 +69,7 @@ AVAILABLE_CLI_OPTIONS = {
         metavar='PATH',
     ),
     "datadir": Arg(
-        '-d', '--datadir',
+        '-d', '--datadir', '--data-dir',
         help='Path to directory with historical backtesting data.',
         metavar='PATH',
     ),
@@ -393,7 +393,8 @@ AVAILABLE_CLI_OPTIONS = {
     # Download data
     "pairs_file": Arg(
         '--pairs-file',
-        help='File containing a list of pairs to download.',
+        help='File containing a list of pairs. '
+             'Takes precedence over --pairs or pairs configured in the configuration.',
         metavar='FILE',
     ),
     "days": Arg(
@@ -439,7 +440,7 @@ AVAILABLE_CLI_OPTIONS = {
     "dataformat_trades": Arg(
         '--data-format-trades',
         help='Storage format for downloaded trades data. (default: `jsongz`).',
-        choices=constants.AVAILABLE_DATAHANDLERS,
+        choices=constants.AVAILABLE_DATAHANDLERS_TRADES,
     ),
     "show_timerange": Arg(
         '--show-timerange',
@@ -455,8 +456,6 @@ AVAILABLE_CLI_OPTIONS = {
         '-t', '--timeframes',
         help='Specify which tickers to download. Space-separated list. '
         'Default: `1m 5m`.',
-        choices=['1m', '3m', '5m', '15m', '30m', '1h', '2h', '4h',
-                 '6h', '8h', '12h', '1d', '3d', '1w', '2w', '1M', '1y'],
         default=['1m', '5m'],
         nargs='+',
     ),

freqtrade/commands/data_commands.py

@@ -11,7 +11,8 @@ from freqtrade.data.history import (convert_trades_to_ohlcv, refresh_backtest_oh
                                     refresh_backtest_trades_data)
 from freqtrade.enums import CandleType, RunMode, TradingMode
 from freqtrade.exceptions import OperationalException
-from freqtrade.exchange import market_is_active, timeframe_to_minutes
+from freqtrade.exchange import Exchange, market_is_active, timeframe_to_minutes
+from freqtrade.freqai.utils import setup_freqai_spice_rack
 from freqtrade.plugins.pairlist.pairlist_helpers import dynamic_expand_pairlist, expand_pairlist
 from freqtrade.resolvers import ExchangeResolver
 
@@ -48,6 +49,10 @@ def start_download_data(args: Dict[str, Any]) -> None:
 
     # Init exchange
     exchange = ExchangeResolver.load_exchange(config['exchange']['name'], config, validate=False)
+
+    if config.get('freqai_spice_rack', False):
+        config = setup_freqai_spice_rack(config, exchange)
+
     markets = [p for p, m in exchange.markets.items() if market_is_active(m)
                or config.get('include_inactive')]
 
@@ -63,37 +68,7 @@ def start_download_data(args: Dict[str, Any]) -> None:
         exchange.validate_timeframes(timeframe)
 
     try:
-
-        if config.get('download_trades'):
-            if config.get('trading_mode') == 'futures':
-                raise OperationalException("Trade download not supported for futures.")
-            pairs_not_available = refresh_backtest_trades_data(
-                exchange, pairs=expanded_pairs, datadir=config['datadir'],
-                timerange=timerange, new_pairs_days=config['new_pairs_days'],
-                erase=bool(config.get('erase')), data_format=config['dataformat_trades'])
-
-            # Convert downloaded trade data to different timeframes
-            convert_trades_to_ohlcv(
-                pairs=expanded_pairs, timeframes=config['timeframes'],
-                datadir=config['datadir'], timerange=timerange, erase=bool(config.get('erase')),
-                data_format_ohlcv=config['dataformat_ohlcv'],
-                data_format_trades=config['dataformat_trades'],
-            )
-        else:
-            if not exchange.get_option('ohlcv_has_history', True):
-                raise OperationalException(
-                    f"Historic klines not available for {exchange.name}. "
-                    "Please use `--dl-trades` instead for this exchange "
-                    "(will unfortunately take a long time)."
-                    )
-            pairs_not_available = refresh_backtest_ohlcv_data(
-                exchange, pairs=expanded_pairs, timeframes=config['timeframes'],
-                datadir=config['datadir'], timerange=timerange,
-                new_pairs_days=config['new_pairs_days'],
-                erase=bool(config.get('erase')), data_format=config['dataformat_ohlcv'],
-                trading_mode=config.get('trading_mode', 'spot'),
-                prepend=config.get('prepend_data', False)
-            )
+        pairs_not_available = download_trades(exchange, expanded_pairs, config, timerange)
 
     except KeyboardInterrupt:
         sys.exit("SIGINT received, aborting ...")
@@ -104,6 +79,42 @@ def start_download_data(args: Dict[str, Any]) -> None:
                         f"on exchange {exchange.name}.")
 
 
+def download_trades(exchange: Exchange, expanded_pairs: list,
+                    config: Dict[str, Any], timerange: TimeRange) -> list:
+    if config.get('download_trades'):
+        if config.get('trading_mode') == 'futures':
+            raise OperationalException("Trade download not supported for futures.")
+        pairs_not_available = refresh_backtest_trades_data(
+            exchange, pairs=expanded_pairs, datadir=config['datadir'],
+            timerange=timerange, new_pairs_days=config['new_pairs_days'],
+            erase=bool(config.get('erase')), data_format=config['dataformat_trades'])
+
+        # Convert downloaded trade data to different timeframes
+        convert_trades_to_ohlcv(
+            pairs=expanded_pairs, timeframes=config['timeframes'],
+            datadir=config['datadir'], timerange=timerange, erase=bool(config.get('erase')),
+            data_format_ohlcv=config['dataformat_ohlcv'],
+            data_format_trades=config['dataformat_trades'],
+        )
+    else:
+        if not exchange.get_option('ohlcv_has_history', True):
+            raise OperationalException(
+                f"Historic klines not available for {exchange.name}. "
+                "Please use `--dl-trades` instead for this exchange "
+                "(will unfortunately take a long time)."
+                )
+        pairs_not_available = refresh_backtest_ohlcv_data(
+            exchange, pairs=expanded_pairs, timeframes=config['timeframes'],
+            datadir=config['datadir'], timerange=timerange,
+            new_pairs_days=config['new_pairs_days'],
+            erase=bool(config.get('erase')), data_format=config['dataformat_ohlcv'],
+            trading_mode=config.get('trading_mode', 'spot'),
+            prepend=config.get('prepend_data', False)
+        )
+
+    return pairs_not_available
+
+
 def start_convert_trades(args: Dict[str, Any]) -> None:
 
     config = setup_utils_configuration(args, RunMode.UTIL_EXCHANGE)

freqtrade/commands/db_commands.py

@@ -4,7 +4,7 @@ from typing import Any, Dict
 from sqlalchemy import func
 
 from freqtrade.configuration.config_setup import setup_utils_configuration
-from freqtrade.enums.runmode import RunMode
+from freqtrade.enums import RunMode
 
 
 logger = logging.getLogger(__name__)

freqtrade/commands/deploy_commands.py

@@ -36,24 +36,24 @@ def deploy_new_strategy(strategy_name: str, strategy_path: Path, subtemplate: st
     """
     fallback = 'full'
     indicators = render_template_with_fallback(
-        templatefile=f"subtemplates/indicators_{subtemplate}.j2",
-        templatefallbackfile=f"subtemplates/indicators_{fallback}.j2",
+        templatefile=f"strategy_subtemplates/indicators_{subtemplate}.j2",
+        templatefallbackfile=f"strategy_subtemplates/indicators_{fallback}.j2",
     )
     buy_trend = render_template_with_fallback(
-        templatefile=f"subtemplates/buy_trend_{subtemplate}.j2",
-        templatefallbackfile=f"subtemplates/buy_trend_{fallback}.j2",
+        templatefile=f"strategy_subtemplates/buy_trend_{subtemplate}.j2",
+        templatefallbackfile=f"strategy_subtemplates/buy_trend_{fallback}.j2",
     )
     sell_trend = render_template_with_fallback(
-        templatefile=f"subtemplates/sell_trend_{subtemplate}.j2",
-        templatefallbackfile=f"subtemplates/sell_trend_{fallback}.j2",
+        templatefile=f"strategy_subtemplates/sell_trend_{subtemplate}.j2",
+        templatefallbackfile=f"strategy_subtemplates/sell_trend_{fallback}.j2",
     )
     plot_config = render_template_with_fallback(
-        templatefile=f"subtemplates/plot_config_{subtemplate}.j2",
-        templatefallbackfile=f"subtemplates/plot_config_{fallback}.j2",
+        templatefile=f"strategy_subtemplates/plot_config_{subtemplate}.j2",
+        templatefallbackfile=f"strategy_subtemplates/plot_config_{fallback}.j2",
     )
     additional_methods = render_template_with_fallback(
-        templatefile=f"subtemplates/strategy_methods_{subtemplate}.j2",
-        templatefallbackfile="subtemplates/strategy_methods_empty.j2",
+        templatefile=f"strategy_subtemplates/strategy_methods_{subtemplate}.j2",
+        templatefallbackfile="strategy_subtemplates/strategy_methods_empty.j2",
     )
 
     strategy_text = render_template(templatefile='base_strategy.py.j2',

freqtrade/configuration/__init__.py

@@ -1,6 +1,5 @@
 # flake8: noqa: F401
 
-from freqtrade.configuration.check_exchange import check_exchange
 from freqtrade.configuration.config_setup import setup_utils_configuration
 from freqtrade.configuration.config_validation import validate_config_consistency
 from freqtrade.configuration.configuration import Configuration

freqtrade/configuration/config_validation.py

@@ -1,4 +1,5 @@
 import logging
+from collections import Counter
 from copy import deepcopy
 from typing import Any, Dict
 
@@ -84,6 +85,8 @@ def validate_config_consistency(conf: Dict[str, Any], preliminary: bool = False)
     _validate_protections(conf)
     _validate_unlimited_amount(conf)
     _validate_ask_orderbook(conf)
+    _validate_freqai_hyperopt(conf)
+    _validate_consumers(conf)
     validate_migrated_strategy_settings(conf)
 
     # validate configuration before returning
@@ -323,6 +326,31 @@ def _validate_pricing_rules(conf: Dict[str, Any]) -> None:
             del conf['ask_strategy']
 
 
+def _validate_freqai_hyperopt(conf: Dict[str, Any]) -> None:
+    freqai_enabled = conf.get('freqai', {}).get('enabled', False)
+    analyze_per_epoch = conf.get('analyze_per_epoch', False)
+    if analyze_per_epoch and freqai_enabled:
+        raise OperationalException(
+            'Using analyze-per-epoch parameter is not supported with a FreqAI strategy.')
+
+
+def _validate_consumers(conf: Dict[str, Any]) -> None:
+    emc_conf = conf.get('external_message_consumer', {})
+    if emc_conf.get('enabled', False):
+        if len(emc_conf.get('producers', [])) < 1:
+            raise OperationalException("You must specify at least 1 Producer to connect to.")
+
+        producer_names = [p['name'] for p in emc_conf.get('producers', [])]
+        duplicates = [item for item, count in Counter(producer_names).items() if count > 1]
+        if duplicates:
+            raise OperationalException(
+                f"Producer names must be unique. Duplicate: {', '.join(duplicates)}")
+        if conf.get('process_only_new_candles', True):
+            # Warning here or require it?
+            logger.warning("To receive best performance with external data, "
+                           "please set `process_only_new_candles` to False")
+
+
 def _strategy_settings(conf: Dict[str, Any]) -> None:
 
     process_deprecated_setting(conf, None, 'use_sell_signal', None, 'use_exit_signal')

freqtrade/configuration/configuration.py

@@ -8,11 +8,11 @@ from pathlib import Path
 from typing import Any, Callable, Dict, List, Optional
 
 from freqtrade import constants
-from freqtrade.configuration.check_exchange import check_exchange
 from freqtrade.configuration.deprecated_settings import process_temporary_deprecated_settings
 from freqtrade.configuration.directory_operations import create_datadir, create_userdata_dir
 from freqtrade.configuration.environment_vars import enironment_vars_to_dict
 from freqtrade.configuration.load_config import load_file, load_from_files
+from freqtrade.constants import Config
 from freqtrade.enums import NON_UTIL_MODES, TRADING_MODES, CandleType, RunMode, TradingMode
 from freqtrade.exceptions import OperationalException
 from freqtrade.loggers import setup_logging
@@ -30,10 +30,10 @@ class Configuration:
 
     def __init__(self, args: Dict[str, Any], runmode: RunMode = None) -> None:
         self.args = args
-        self.config: Optional[Dict[str, Any]] = None
+        self.config: Optional[Config] = None
         self.runmode = runmode
 
-    def get_config(self) -> Dict[str, Any]:
+    def get_config(self) -> Config:
         """
         Return the config. Use this method to get the bot config
         :return: Dict: Bot config
@@ -65,7 +65,7 @@ class Configuration:
         :return: Configuration dictionary
         """
         # Load all configs
-        config: Dict[str, Any] = load_from_files(self.args.get("config", []))
+        config: Config = load_from_files(self.args.get("config", []))
 
         # Load environment variables
         env_data = enironment_vars_to_dict()
@@ -99,6 +99,9 @@ class Configuration:
 
         self._process_freqai_options(config)
 
+        # Import check_exchange here to avoid import cycle problems
+        from freqtrade.exchange.check_exchange import check_exchange
+
         # Check if the exchange set by the user is supported
         check_exchange(config, config.get('experimental', {}).get('block_bad_exchanges', True))
 
@@ -108,7 +111,7 @@ class Configuration:
 
         return config
 
-    def _process_logging_options(self, config: Dict[str, Any]) -> None:
+    def _process_logging_options(self, config: Config) -> None:
         """
         Extract information for sys.argv and load logging configuration:
         the -v/--verbose, --logfile options
@@ -121,7 +124,7 @@ class Configuration:
 
         setup_logging(config)
 
-    def _process_trading_options(self, config: Dict[str, Any]) -> None:
+    def _process_trading_options(self, config: Config) -> None:
         if config['runmode'] not in TRADING_MODES:
             return
 
@@ -137,7 +140,7 @@ class Configuration:
 
         logger.info(f'Using DB: "{parse_db_uri_for_logging(config["db_url"])}"')
 
-    def _process_common_options(self, config: Dict[str, Any]) -> None:
+    def _process_common_options(self, config: Config) -> None:
 
         # Set strategy if not specified in config and or if it's non default
         if self.args.get('strategy') or not config.get('strategy'):
@@ -161,7 +164,7 @@ class Configuration:
         if 'sd_notify' in self.args and self.args['sd_notify']:
             config['internals'].update({'sd_notify': True})
 
-    def _process_datadir_options(self, config: Dict[str, Any]) -> None:
+    def _process_datadir_options(self, config: Config) -> None:
         """
         Extract information for sys.argv and load directory configurations
         --user-data, --datadir
@@ -195,7 +198,7 @@ class Configuration:
             config['exportfilename'] = (config['user_data_dir']
                                         / 'backtest_results')
 
-    def _process_optimize_options(self, config: Dict[str, Any]) -> None:
+    def _process_optimize_options(self, config: Config) -> None:
 
         # This will override the strategy configuration
         self._args_to_config(config, argname='timeframe',
@@ -380,7 +383,7 @@ class Configuration:
         self._args_to_config(config, argname="hyperopt_ignore_missing_space",
                              logstring="Paramter --ignore-missing-space detected: {}")
 
-    def _process_plot_options(self, config: Dict[str, Any]) -> None:
+    def _process_plot_options(self, config: Config) -> None:
 
         self._args_to_config(config, argname='pairs',
                              logstring='Using pairs {}')
@@ -432,7 +435,7 @@ class Configuration:
         self._args_to_config(config, argname='show_timerange',
                              logstring='Detected --show-timerange')
 
-    def _process_data_options(self, config: Dict[str, Any]) -> None:
+    def _process_data_options(self, config: Config) -> None:
         self._args_to_config(config, argname='new_pairs_days',
                              logstring='Detected --new-pairs-days: {}')
         self._args_to_config(config, argname='trading_mode',
@@ -443,7 +446,7 @@ class Configuration:
         self._args_to_config(config, argname='candle_types',
                              logstring='Detected --candle-types: {}')
 
-    def _process_analyze_options(self, config: Dict[str, Any]) -> None:
+    def _process_analyze_options(self, config: Config) -> None:
         self._args_to_config(config, argname='analysis_groups',
                              logstring='Analysis reason groups: {}')
 
@@ -456,7 +459,7 @@ class Configuration:
         self._args_to_config(config, argname='indicator_list',
                              logstring='Analysis indicator list: {}')
 
-    def _process_runmode(self, config: Dict[str, Any]) -> None:
+    def _process_runmode(self, config: Config) -> None:
 
         self._args_to_config(config, argname='dry_run',
                              logstring='Parameter --dry-run detected, '
@@ -469,7 +472,7 @@ class Configuration:
 
         config.update({'runmode': self.runmode})
 
-    def _process_freqai_options(self, config: Dict[str, Any]) -> None:
+    def _process_freqai_options(self, config: Config) -> None:
 
         self._args_to_config(config, argname='freqaimodel',
                              logstring='Using freqaimodel class name: {}')
@@ -479,7 +482,7 @@ class Configuration:
 
         return
 
-    def _args_to_config(self, config: Dict[str, Any], argname: str,
+    def _args_to_config(self, config: Config, argname: str,
                         logstring: str, logfun: Optional[Callable] = None,
                         deprecated_msg: Optional[str] = None) -> None:
         """
@@ -502,7 +505,7 @@ class Configuration:
             if deprecated_msg:
                 warnings.warn(f"DEPRECATED: {deprecated_msg}", DeprecationWarning)
 
-    def _resolve_pairs_list(self, config: Dict[str, Any]) -> None:
+    def _resolve_pairs_list(self, config: Config) -> None:
         """
         Helper for download script.
         Takes first found:

freqtrade/configuration/deprecated_settings.py

@@ -3,15 +3,16 @@ Functions to handle deprecated settings
 """
 
 import logging
-from typing import Any, Dict, Optional
+from typing import Optional
 
+from freqtrade.constants import Config
 from freqtrade.exceptions import OperationalException
 
 
 logger = logging.getLogger(__name__)
 
 
-def check_conflicting_settings(config: Dict[str, Any],
+def check_conflicting_settings(config: Config,
                                section_old: Optional[str], name_old: str,
                                section_new: Optional[str], name_new: str) -> None:
     section_new_config = config.get(section_new, {}) if section_new else config
@@ -28,7 +29,7 @@ def check_conflicting_settings(config: Dict[str, Any],
         )
 
 
-def process_removed_setting(config: Dict[str, Any],
+def process_removed_setting(config: Config,
                             section1: str, name1: str,
                             section2: Optional[str], name2: str) -> None:
     """
@@ -47,7 +48,7 @@ def process_removed_setting(config: Dict[str, Any],
         )
 
 
-def process_deprecated_setting(config: Dict[str, Any],
+def process_deprecated_setting(config: Config,
                                section_old: Optional[str], name_old: str,
                                section_new: Optional[str], name_new: str
                                ) -> None:
@@ -69,7 +70,7 @@ def process_deprecated_setting(config: Dict[str, Any],
         del section_old_config[name_old]
 
 
-def process_temporary_deprecated_settings(config: Dict[str, Any]) -> None:
+def process_temporary_deprecated_settings(config: Config) -> None:
 
     # Kept for future deprecated / moved settings
     # check_conflicting_settings(config, 'ask_strategy', 'use_sell_signal',

freqtrade/configuration/directory_operations.py

@@ -1,16 +1,16 @@
 import logging
 import shutil
 from pathlib import Path
-from typing import Any, Dict, Optional
+from typing import Optional
 
-from freqtrade.constants import USER_DATA_FILES
+from freqtrade.constants import USER_DATA_FILES, Config
 from freqtrade.exceptions import OperationalException
 
 
 logger = logging.getLogger(__name__)
 
 
-def create_datadir(config: Dict[str, Any], datadir: Optional[str] = None) -> Path:
+def create_datadir(config: Config, datadir: Optional[str] = None) -> Path:
 
     folder = Path(datadir) if datadir else Path(f"{config['user_data_dir']}/data")
     if not datadir:

freqtrade/configuration/load_config.py

@@ -10,7 +10,7 @@ from typing import Any, Dict, List
 
 import rapidjson
 
-from freqtrade.constants import MINIMAL_CONFIG
+from freqtrade.constants import MINIMAL_CONFIG, Config
 from freqtrade.exceptions import OperationalException
 from freqtrade.misc import deep_merge_dicts
 
@@ -80,7 +80,7 @@ def load_from_files(files: List[str], base_path: Path = None, level: int = 0) ->
     Recursively load configuration files if specified.
     Sub-files are assumed to be relative to the initial config.
     """
-    config: Dict[str, Any] = {}
+    config: Config = {}
     if level > 5:
         raise OperationalException("Config loop detected.")
 

freqtrade/constants.py

@@ -3,7 +3,7 @@
 """
 bot constants
 """
-from typing import List, Literal, Tuple
+from typing import Any, Dict, List, Literal, Tuple
 
 from freqtrade.enums import CandleType
 
@@ -23,19 +23,21 @@ REQUIRED_ORDERTIF = ['entry', 'exit']
 REQUIRED_ORDERTYPES = ['entry', 'exit', 'stoploss', 'stoploss_on_exchange']
 PRICING_SIDES = ['ask', 'bid', 'same', 'other']
 ORDERTYPE_POSSIBILITIES = ['limit', 'market']
-ORDERTIF_POSSIBILITIES = ['gtc', 'fok', 'ioc']
+_ORDERTIF_POSSIBILITIES = ['GTC', 'FOK', 'IOC', 'PO']
+ORDERTIF_POSSIBILITIES = _ORDERTIF_POSSIBILITIES + [t.lower() for t in _ORDERTIF_POSSIBILITIES]
 HYPEROPT_LOSS_BUILTIN = ['ShortTradeDurHyperOptLoss', 'OnlyProfitHyperOptLoss',
                          'SharpeHyperOptLoss', 'SharpeHyperOptLossDaily',
                          'SortinoHyperOptLoss', 'SortinoHyperOptLossDaily',
                          'CalmarHyperOptLoss',
                          'MaxDrawDownHyperOptLoss', 'MaxDrawDownRelativeHyperOptLoss',
                          'ProfitDrawDownHyperOptLoss']
-AVAILABLE_PAIRLISTS = ['StaticPairList', 'VolumePairList',
+AVAILABLE_PAIRLISTS = ['StaticPairList', 'VolumePairList', 'ProducerPairList',
                        'AgeFilter', 'OffsetFilter', 'PerformanceFilter',
                        'PrecisionFilter', 'PriceFilter', 'RangeStabilityFilter',
                        'ShuffleFilter', 'SpreadFilter', 'VolatilityFilter']
 AVAILABLE_PROTECTIONS = ['CooldownPeriod', 'LowProfitPairs', 'MaxDrawdown', 'StoplossGuard']
-AVAILABLE_DATAHANDLERS = ['json', 'jsongz', 'hdf5']
+AVAILABLE_DATAHANDLERS_TRADES = ['json', 'jsongz', 'hdf5']
+AVAILABLE_DATAHANDLERS = AVAILABLE_DATAHANDLERS_TRADES + ['feather', 'parquet']
 BACKTEST_BREAKDOWNS = ['day', 'week', 'month']
 BACKTEST_CACHE_AGE = ['none', 'day', 'week', 'month']
 BACKTEST_CACHE_DEFAULT = 'day'
@@ -242,6 +244,7 @@ CONF_SCHEMA = {
         'exchange': {'$ref': '#/definitions/exchange'},
         'edge': {'$ref': '#/definitions/edge'},
         'freqai': {'$ref': '#/definitions/freqai'},
+        'external_message_consumer': {'$ref': '#/definitions/external_message_consumer'},
         'experimental': {
             'type': 'object',
             'properties': {
@@ -288,11 +291,12 @@ CONF_SCHEMA = {
                         'warning': {'type': 'string', 'enum': TELEGRAM_SETTING_OPTIONS},
                         'startup': {'type': 'string', 'enum': TELEGRAM_SETTING_OPTIONS},
                         'entry': {'type': 'string', 'enum': TELEGRAM_SETTING_OPTIONS},
-                        'entry_cancel': {'type': 'string', 'enum': TELEGRAM_SETTING_OPTIONS},
-                        'entry_fill': {'type': 'string',
-                                       'enum': TELEGRAM_SETTING_OPTIONS,
-                                       'default': 'off'
-                                       },
+                        'entry_fill': {
+                            'type': 'string',
+                            'enum': TELEGRAM_SETTING_OPTIONS,
+                            'default': 'off'
+                        },
+                        'entry_cancel': {'type': 'string', 'enum': TELEGRAM_SETTING_OPTIONS, },
                         'exit': {
                             'type': ['string', 'object'],
                             'additionalProperties': {
@@ -300,12 +304,12 @@ CONF_SCHEMA = {
                                 'enum': TELEGRAM_SETTING_OPTIONS
                             }
                         },
-                        'exit_cancel': {'type': 'string', 'enum': TELEGRAM_SETTING_OPTIONS},
                         'exit_fill': {
                             'type': 'string',
                             'enum': TELEGRAM_SETTING_OPTIONS,
                             'default': 'on'
                         },
+                        'exit_cancel': {'type': 'string', 'enum': TELEGRAM_SETTING_OPTIONS},
                         'protection_trigger': {
                             'type': 'string',
                             'enum': TELEGRAM_SETTING_OPTIONS,
@@ -314,14 +318,17 @@ CONF_SCHEMA = {
                         'protection_trigger_global': {
                             'type': 'string',
                             'enum': TELEGRAM_SETTING_OPTIONS,
+                            'default': 'on'
                         },
                         'show_candle': {
                             'type': 'string',
                             'enum': ['off', 'ohlc'],
+                            'default': 'off'
                         },
                         'strategy_msg': {
                             'type': 'string',
                             'enum': TELEGRAM_SETTING_OPTIONS,
+                            'default': 'on'
                         },
                     }
                 },
@@ -399,6 +406,7 @@ CONF_SCHEMA = {
                 },
                 'username': {'type': 'string'},
                 'password': {'type': 'string'},
+                'ws_token': {'type': ['string', 'array'], 'items': {'type': 'string'}},
                 'jwt_secret_key': {'type': 'string'},
                 'CORS_origins': {'type': 'array', 'items': {'type': 'string'}},
                 'verbosity': {'type': 'string', 'enum': ['error', 'info']},
@@ -427,7 +435,7 @@ CONF_SCHEMA = {
         },
         'dataformat_trades': {
             'type': 'string',
-            'enum': AVAILABLE_DATAHANDLERS,
+            'enum': AVAILABLE_DATAHANDLERS_TRADES,
             'default': 'jsongz'
         },
         'position_adjustment_enable': {'type': 'boolean'},
@@ -483,6 +491,47 @@ CONF_SCHEMA = {
             },
             'required': ['process_throttle_secs', 'allowed_risk']
         },
+        'external_message_consumer': {
+            'type': 'object',
+            'properties': {
+                'enabled': {'type': 'boolean', 'default': False},
+                'producers': {
+                    'type': 'array',
+                    'items': {
+                        'type': 'object',
+                        'properties': {
+                            'name': {'type': 'string'},
+                            'host': {'type': 'string'},
+                            'port': {
+                                'type': 'integer',
+                                'default': 8080,
+                                'minimum': 0,
+                                'maximum': 65535
+                            },
+                            'ws_token': {'type': 'string'},
+                        },
+                        'required': ['name', 'host', 'ws_token']
+                    }
+                },
+                'wait_timeout': {'type': 'integer', 'minimum': 0},
+                'sleep_time': {'type': 'integer', 'minimum': 0},
+                'ping_timeout': {'type': 'integer', 'minimum': 0},
+                'remove_entry_exit_signals': {'type': 'boolean', 'default': False},
+                'initial_candle_limit': {
+                    'type': 'integer',
+                    'minimum': 0,
+                    'maximum': 1500,
+                    'default': 1500
+                },
+                'message_size_limit': {  # In megabytes
+                    'type': 'integer',
+                    'minimum': 1,
+                    'maxmium': 20,
+                    'default': 8,
+                }
+            },
+            'required': ['producers']
+        },
         "freqai": {
             "type": "object",
             "properties": {
@@ -503,6 +552,7 @@ CONF_SCHEMA = {
                         "weight_factor": {"type": "number", "default": 0},
                         "principal_component_analysis": {"type": "boolean", "default": False},
                         "use_SVM_to_remove_outliers": {"type": "boolean", "default": False},
+                        "plot_feature_importances": {"type": "integer", "default": 0},
                         "svm_params": {"type": "object",
                                        "properties": {
                                            "shuffle": {"type": "boolean", "default": False},
@@ -517,6 +567,7 @@ CONF_SCHEMA = {
                     "properties": {
                         "test_size": {"type": "number"},
                         "random_state": {"type": "integer"},
+                        "shuffle": {"type": "boolean", "default": False}
                     },
                 },
                 "model_training_parameters": {
@@ -602,3 +653,5 @@ LongShort = Literal['long', 'short']
 EntryExit = Literal['entry', 'exit']
 BuySell = Literal['buy', 'sell']
 MakerTaker = Literal['maker', 'taker']
+
+Config = Dict[str, Any]

freqtrade/data/btanalysis.py

@@ -284,7 +284,7 @@ def load_backtest_data(filename: Union[Path, str], strategy: Optional[str] = Non
                 df['enter_tag'] = df['buy_tag']
                 df = df.drop(['buy_tag'], axis=1)
             if 'orders' not in df.columns:
-                df.loc[:, 'orders'] = None
+                df['orders'] = None
 
     else:
         # old format - only with lists.
@@ -341,9 +341,9 @@ def trade_list_to_dataframe(trades: List[LocalTrade]) -> pd.DataFrame:
     """
     df = pd.DataFrame.from_records([t.to_json(True) for t in trades], columns=BT_DATA_COLUMNS)
     if len(df) > 0:
-        df.loc[:, 'close_date'] = pd.to_datetime(df['close_date'], utc=True)
-        df.loc[:, 'open_date'] = pd.to_datetime(df['open_date'], utc=True)
-        df.loc[:, 'close_rate'] = df['close_rate'].astype('float64')
+        df['close_date'] = pd.to_datetime(df['close_date'], utc=True)
+        df['open_date'] = pd.to_datetime(df['open_date'], utc=True)
+        df['close_rate'] = df['close_rate'].astype('float64')
     return df
 
 

freqtrade/data/converter.py

@@ -5,12 +5,12 @@ import itertools
 import logging
 from datetime import datetime, timezone
 from operator import itemgetter
-from typing import Any, Dict, List
+from typing import Dict, List
 
 import pandas as pd
 from pandas import DataFrame, to_datetime
 
-from freqtrade.constants import DEFAULT_DATAFRAME_COLUMNS, DEFAULT_TRADES_COLUMNS, TradeList
+from freqtrade.constants import DEFAULT_DATAFRAME_COLUMNS, DEFAULT_TRADES_COLUMNS, Config, TradeList
 from freqtrade.enums import CandleType
 
 
@@ -47,8 +47,7 @@ def ohlcv_to_dataframe(ohlcv: list, timeframe: str, pair: str, *,
 
 
 def clean_ohlcv_dataframe(data: DataFrame, timeframe: str, pair: str, *,
-                          fill_missing: bool = True,
-                          drop_incomplete: bool = True) -> DataFrame:
+                          fill_missing: bool, drop_incomplete: bool) -> DataFrame:
     """
     Cleanse a OHLCV dataframe by
       * Grouping it by date (removes duplicate tics)
@@ -237,7 +236,7 @@ def trades_to_ohlcv(trades: TradeList, timeframe: str) -> DataFrame:
     return df_new.loc[:, DEFAULT_DATAFRAME_COLUMNS]
 
 
-def convert_trades_format(config: Dict[str, Any], convert_from: str, convert_to: str, erase: bool):
+def convert_trades_format(config: Config, convert_from: str, convert_to: str, erase: bool):
     """
     Convert trades from one format to another format.
     :param config: Config dictionary
@@ -263,7 +262,7 @@ def convert_trades_format(config: Dict[str, Any], convert_from: str, convert_to:
 
 
 def convert_ohlcv_format(
-    config: Dict[str, Any],
+    config: Config,
     convert_from: str,
     convert_to: str,
     erase: bool,
@@ -292,6 +291,7 @@ def convert_ohlcv_format(
                 timeframe,
                 candle_type=candle_type
             ))
+        config['pairs'] = sorted(set(config['pairs']))
     logger.info(f"Converting candle (OHLCV) data for {config['pairs']}")
 
     for timeframe in timeframes:
@@ -302,7 +302,7 @@ def convert_ohlcv_format(
                                   drop_incomplete=False,
                                   startup_candles=0,
                                   candle_type=candle_type)
-            logger.info(f"Converting {len(data)} {candle_type} candles for {pair}")
+            logger.info(f"Converting {len(data)} {timeframe} {candle_type} candles for {pair}")
             if len(data) > 0:
                 trg.ohlcv_store(
                     pair=pair,

freqtrade/data/dataprovider.py

@@ -12,11 +12,12 @@ from typing import Any, Dict, List, Optional, Tuple
 from pandas import DataFrame
 
 from freqtrade.configuration import TimeRange
-from freqtrade.constants import ListPairsWithTimeframes, PairWithTimeframe
+from freqtrade.constants import Config, ListPairsWithTimeframes, PairWithTimeframe
 from freqtrade.data.history import load_pair_history
-from freqtrade.enums import CandleType, RunMode
+from freqtrade.enums import CandleType, RPCMessageType, RunMode
 from freqtrade.exceptions import ExchangeError, OperationalException
 from freqtrade.exchange import Exchange, timeframe_to_seconds
+from freqtrade.rpc import RPCManager
 from freqtrade.util import PeriodicCache
 
 
@@ -28,17 +29,33 @@ MAX_DATAFRAME_CANDLES = 1000
 
 class DataProvider:
 
-    def __init__(self, config: dict, exchange: Optional[Exchange], pairlists=None) -> None:
+    def __init__(
+        self,
+        config: Config,
+        exchange: Optional[Exchange],
+        pairlists=None,
+        rpc: Optional[RPCManager] = None
+    ) -> None:
         self._config = config
         self._exchange = exchange
         self._pairlists = pairlists
+        self.__rpc = rpc
         self.__cached_pairs: Dict[PairWithTimeframe, Tuple[DataFrame, datetime]] = {}
         self.__slice_index: Optional[int] = None
         self.__cached_pairs_backtesting: Dict[PairWithTimeframe, DataFrame] = {}
+        self.__producer_pairs_df: Dict[str,
+                                       Dict[PairWithTimeframe, Tuple[DataFrame, datetime]]] = {}
+        self.__producer_pairs: Dict[str, List[str]] = {}
         self._msg_queue: deque = deque()
 
+        self._default_candle_type = self._config.get('candle_type_def', CandleType.SPOT)
+        self._default_timeframe = self._config.get('timeframe', '1h')
+
         self.__msg_cache = PeriodicCache(
-            maxsize=1000, ttl=timeframe_to_seconds(self._config.get('timeframe', '1h')))
+            maxsize=1000, ttl=timeframe_to_seconds(self._default_timeframe))
+
+        self.producers = self._config.get('external_message_consumer', {}).get('producers', [])
+        self.external_data_enabled = len(self.producers) > 0
 
     def _set_dataframe_max_index(self, limit_index: int):
         """
@@ -63,9 +80,110 @@ class DataProvider:
         :param dataframe: analyzed dataframe
         :param candle_type: Any of the enum CandleType (must match trading mode!)
         """
-        self.__cached_pairs[(pair, timeframe, candle_type)] = (
+        pair_key = (pair, timeframe, candle_type)
+        self.__cached_pairs[pair_key] = (
             dataframe, datetime.now(timezone.utc))
 
+    # For multiple producers we will want to merge the pairlists instead of overwriting
+    def _set_producer_pairs(self, pairlist: List[str], producer_name: str = "default"):
+        """
+        Set the pairs received to later be used.
+
+        :param pairlist: List of pairs
+        """
+        self.__producer_pairs[producer_name] = pairlist
+
+    def get_producer_pairs(self, producer_name: str = "default") -> List[str]:
+        """
+        Get the pairs cached from the producer
+
+        :returns: List of pairs
+        """
+        return self.__producer_pairs.get(producer_name, []).copy()
+
+    def _emit_df(
+        self,
+        pair_key: PairWithTimeframe,
+        dataframe: DataFrame
+    ) -> None:
+        """
+        Send this dataframe as an ANALYZED_DF message to RPC
+
+        :param pair_key: PairWithTimeframe tuple
+        :param data: Tuple containing the DataFrame and the datetime it was cached
+        """
+        if self.__rpc:
+            self.__rpc.send_msg(
+                {
+                    'type': RPCMessageType.ANALYZED_DF,
+                    'data': {
+                        'key': pair_key,
+                        'df': dataframe,
+                        'la': datetime.now(timezone.utc)
+                    }
+                }
+            )
+
+    def _add_external_df(
+        self,
+        pair: str,
+        dataframe: DataFrame,
+        last_analyzed: datetime,
+        timeframe: str,
+        candle_type: CandleType,
+        producer_name: str = "default"
+    ) -> None:
+        """
+        Add the pair data to this class from an external source.
+
+        :param pair: pair to get the data for
+        :param timeframe: Timeframe to get data for
+        :param candle_type: Any of the enum CandleType (must match trading mode!)
+        """
+        pair_key = (pair, timeframe, candle_type)
+
+        if producer_name not in self.__producer_pairs_df:
+            self.__producer_pairs_df[producer_name] = {}
+
+        _last_analyzed = datetime.now(timezone.utc) if not last_analyzed else last_analyzed
+
+        self.__producer_pairs_df[producer_name][pair_key] = (dataframe, _last_analyzed)
+        logger.debug(f"External DataFrame for {pair_key} from {producer_name} added.")
+
+    def get_producer_df(
+        self,
+        pair: str,
+        timeframe: Optional[str] = None,
+        candle_type: Optional[CandleType] = None,
+        producer_name: str = "default"
+    ) -> Tuple[DataFrame, datetime]:
+        """
+        Get the pair data from producers.
+
+        :param pair: pair to get the data for
+        :param timeframe: Timeframe to get data for
+        :param candle_type: Any of the enum CandleType (must match trading mode!)
+        :returns: Tuple of the DataFrame and last analyzed timestamp
+        """
+        _timeframe = self._default_timeframe if not timeframe else timeframe
+        _candle_type = self._default_candle_type if not candle_type else candle_type
+
+        pair_key = (pair, _timeframe, _candle_type)
+
+        # If we have no data from this Producer yet
+        if producer_name not in self.__producer_pairs_df:
+            # We don't have this data yet, return empty DataFrame and datetime (01-01-1970)
+            return (DataFrame(), datetime.fromtimestamp(0, tz=timezone.utc))
+
+        # If we do have data from that Producer, but no data on this pair_key
+        if pair_key not in self.__producer_pairs_df[producer_name]:
+            # We don't have this data yet, return empty DataFrame and datetime (01-01-1970)
+            return (DataFrame(), datetime.fromtimestamp(0, tz=timezone.utc))
+
+        # We have it, return this data
+        df, la = self.__producer_pairs_df[producer_name][pair_key]
+        return (df.copy(), la)
+
     def add_pairlisthandler(self, pairlists) -> None:
         """
         Allow adding pairlisthandler after initialization
@@ -86,14 +204,16 @@ class DataProvider:
         """
         _candle_type = CandleType.from_string(
             candle_type) if candle_type != '' else self._config['candle_type_def']
-        saved_pair = (pair, str(timeframe), _candle_type)
+        saved_pair: PairWithTimeframe = (pair, str(timeframe), _candle_type)
         if saved_pair not in self.__cached_pairs_backtesting:
             timerange = TimeRange.parse_timerange(None if self._config.get(
                 'timerange') is None else str(self._config.get('timerange')))
-            # Move informative start time respecting startup_candle_count
-            timerange.subtract_start(
-                timeframe_to_seconds(str(timeframe)) * self._config.get('startup_candle_count', 0)
-            )
+
+            # It is not necessary to add the training candles, as they
+            # were already added at the beginning of the backtest.
+            startup_candles = self.get_required_startup(str(timeframe), False)
+            tf_seconds = timeframe_to_seconds(str(timeframe))
+            timerange.subtract_start(tf_seconds * startup_candles)
             self.__cached_pairs_backtesting[saved_pair] = load_pair_history(
                 pair=pair,
                 timeframe=timeframe or self._config['timeframe'],
@@ -105,6 +225,23 @@ class DataProvider:
             )
         return self.__cached_pairs_backtesting[saved_pair].copy()
 
+    def get_required_startup(self, timeframe: str, add_train_candles: bool = True) -> int:
+        freqai_config = self._config.get('freqai', {})
+        if not freqai_config.get('enabled', False):
+            return self._config.get('startup_candle_count', 0)
+        else:
+            startup_candles = self._config.get('startup_candle_count', 0)
+            indicator_periods = freqai_config['feature_parameters']['indicator_periods_candles']
+            # make sure the startupcandles is at least the set maximum indicator periods
+            self._config['startup_candle_count'] = max(startup_candles, max(indicator_periods))
+            tf_seconds = timeframe_to_seconds(timeframe)
+            train_candles = 0
+            if add_train_candles:
+                train_candles = freqai_config['train_period_days'] * 86400 / tf_seconds
+            total_candles = int(self._config['startup_candle_count'] + train_candles)
+            logger.info(f'Increasing startup_candle_count for freqai to {total_candles}')
+            return total_candles
+
     def get_pair_dataframe(
         self,
         pair: str,
@@ -181,7 +318,9 @@ class DataProvider:
         Clear pair dataframe cache.
         """
         self.__cached_pairs = {}
-        self.__cached_pairs_backtesting = {}
+        # Don't reset backtesting pairs -
+        # otherwise they're reloaded each time during hyperopt due to with analyze_per_epoch
+        # self.__cached_pairs_backtesting = {}
         self.__slice_index = 0
 
     # Exchange functions

freqtrade/data/history/featherdatahandler.py

@@ -0,0 +1,130 @@
+import logging
+from typing import Optional
+
+from pandas import DataFrame, read_feather, to_datetime
+
+from freqtrade.configuration import TimeRange
+from freqtrade.constants import DEFAULT_DATAFRAME_COLUMNS, TradeList
+from freqtrade.enums import CandleType
+
+from .idatahandler import IDataHandler
+
+
+logger = logging.getLogger(__name__)
+
+
+class FeatherDataHandler(IDataHandler):
+
+    _columns = DEFAULT_DATAFRAME_COLUMNS
+
+    def ohlcv_store(
+            self, pair: str, timeframe: str, data: DataFrame, candle_type: CandleType) -> None:
+        """
+        Store data in json format "values".
+            format looks as follows:
+            [[<date>,<open>,<high>,<low>,<close>]]
+        :param pair: Pair - used to generate filename
+        :param timeframe: Timeframe - used to generate filename
+        :param data: Dataframe containing OHLCV data
+        :param candle_type: Any of the enum CandleType (must match trading mode!)
+        :return: None
+        """
+        filename = self._pair_data_filename(self._datadir, pair, timeframe, candle_type)
+        self.create_dir_if_needed(filename)
+
+        data.reset_index(drop=True).loc[:, self._columns].to_feather(
+            filename, compression_level=9, compression='lz4')
+
+    def _ohlcv_load(self, pair: str, timeframe: str,
+                    timerange: Optional[TimeRange], candle_type: CandleType
+                    ) -> DataFrame:
+        """
+        Internal method used to load data for one pair from disk.
+        Implements the loading and conversion to a Pandas dataframe.
+        Timerange trimming and dataframe validation happens outside of this method.
+        :param pair: Pair to load data
+        :param timeframe: Timeframe (e.g. "5m")
+        :param timerange: Limit data to be loaded to this timerange.
+                        Optionally implemented by subclasses to avoid loading
+                        all data where possible.
+        :param candle_type: Any of the enum CandleType (must match trading mode!)
+        :return: DataFrame with ohlcv data, or empty DataFrame
+        """
+        filename = self._pair_data_filename(
+            self._datadir, pair, timeframe, candle_type=candle_type)
+        if not filename.exists():
+            # Fallback mode for 1M files
+            filename = self._pair_data_filename(
+                self._datadir, pair, timeframe, candle_type=candle_type, no_timeframe_modify=True)
+            if not filename.exists():
+                return DataFrame(columns=self._columns)
+
+        pairdata = read_feather(filename)
+        pairdata.columns = self._columns
+        pairdata = pairdata.astype(dtype={'open': 'float', 'high': 'float',
+                                          'low': 'float', 'close': 'float', 'volume': 'float'})
+        pairdata['date'] = to_datetime(pairdata['date'],
+                                       unit='ms',
+                                       utc=True,
+                                       infer_datetime_format=True)
+        return pairdata
+
+    def ohlcv_append(
+        self,
+        pair: str,
+        timeframe: str,
+        data: DataFrame,
+        candle_type: CandleType
+    ) -> None:
+        """
+        Append data to existing data structures
+        :param pair: Pair
+        :param timeframe: Timeframe this ohlcv data is for
+        :param data: Data to append.
+        :param candle_type: Any of the enum CandleType (must match trading mode!)
+        """
+        raise NotImplementedError()
+
+    def trades_store(self, pair: str, data: TradeList) -> None:
+        """
+        Store trades data (list of Dicts) to file
+        :param pair: Pair - used for filename
+        :param data: List of Lists containing trade data,
+                     column sequence as in DEFAULT_TRADES_COLUMNS
+        """
+        # filename = self._pair_trades_filename(self._datadir, pair)
+
+        raise NotImplementedError()
+        # array = pa.array(data)
+        # array
+        # feather.write_feather(data, filename)
+
+    def trades_append(self, pair: str, data: TradeList):
+        """
+        Append data to existing files
+        :param pair: Pair - used for filename
+        :param data: List of Lists containing trade data,
+                     column sequence as in DEFAULT_TRADES_COLUMNS
+        """
+        raise NotImplementedError()
+
+    def _trades_load(self, pair: str, timerange: Optional[TimeRange] = None) -> TradeList:
+        """
+        Load a pair from file, either .json.gz or .json
+        # TODO: respect timerange ...
+        :param pair: Load trades for this pair
+        :param timerange: Timerange to load trades for - currently not implemented
+        :return: List of trades
+        """
+        raise NotImplementedError()
+        # filename = self._pair_trades_filename(self._datadir, pair)
+        # tradesdata = misc.file_load_json(filename)
+
+        # if not tradesdata:
+        #     return []
+
+        # return tradesdata
+
+    @classmethod
+    def _get_file_extension(cls):
+        return "feather"

freqtrade/data/history/hdf5datahandler.py

@@ -1,7 +1,5 @@
 import logging
-import re
-from pathlib import Path
-from typing import List, Optional
+from typing import Optional
 
 import numpy as np
 import pandas as pd
@@ -20,26 +18,6 @@ class HDF5DataHandler(IDataHandler):
 
     _columns = DEFAULT_DATAFRAME_COLUMNS
 
-    @classmethod
-    def ohlcv_get_pairs(cls, datadir: Path, timeframe: str, candle_type: CandleType) -> List[str]:
-        """
-        Returns a list of all pairs with ohlcv data available in this datadir
-        for the specified timeframe
-        :param datadir: Directory to search for ohlcv files
-        :param timeframe: Timeframe to search pairs for
-        :param candle_type: Any of the enum CandleType (must match trading mode!)
-        :return: List of Pairs
-        """
-        candle = ""
-        if candle_type != CandleType.SPOT:
-            datadir = datadir.joinpath('futures')
-            candle = f"-{candle_type}"
-
-        _tmp = [re.search(r'^(\S+)(?=\-' + timeframe + candle + '.h5)', p.name)
-                for p in datadir.glob(f"*{timeframe}{candle}.h5")]
-        # Check if regex found something and only return these results
-        return [cls.rebuild_pair_from_filename(match[0]) for match in _tmp if match]
-
     def ohlcv_store(
             self, pair: str, timeframe: str, data: pd.DataFrame, candle_type: CandleType) -> None:
         """
@@ -103,6 +81,7 @@ class HDF5DataHandler(IDataHandler):
             raise ValueError("Wrong dataframe format")
         pairdata = pairdata.astype(dtype={'open': 'float', 'high': 'float',
                                           'low': 'float', 'close': 'float', 'volume': 'float'})
+        pairdata = pairdata.reset_index(drop=True)
         return pairdata
 
     def ohlcv_append(
@@ -121,18 +100,6 @@ class HDF5DataHandler(IDataHandler):
         """
         raise NotImplementedError()
 
-    @classmethod
-    def trades_get_pairs(cls, datadir: Path) -> List[str]:
-        """
-        Returns a list of all pairs for which trade data is available in this
-        :param datadir: Directory to search for ohlcv files
-        :return: List of Pairs
-        """
-        _tmp = [re.search(r'^(\S+)(?=\-trades.h5)', p.name)
-                for p in datadir.glob("*trades.h5")]
-        # Check if regex found something and only return these results to avoid exceptions.
-        return [cls.rebuild_pair_from_filename(match[0]) for match in _tmp if match]
-
     def trades_store(self, pair: str, data: TradeList) -> None:
         """
         Store trades data (list of Dicts) to file

freqtrade/data/history/history_utils.py

@@ -26,7 +26,7 @@ def load_pair_history(pair: str,
                       datadir: Path, *,
                       timerange: Optional[TimeRange] = None,
                       fill_up_missing: bool = True,
-                      drop_incomplete: bool = True,
+                      drop_incomplete: bool = False,
                       startup_candles: int = 0,
                       data_format: str = None,
                       data_handler: IDataHandler = None,
@@ -228,9 +228,9 @@ def _download_pair_history(pair: str, *,
                     )
 
         logger.debug("Current Start: %s",
-                     f"{data.iloc[0]['date']:%Y-%m-%d %H:%M:%S}" if not data.empty else 'None')
+                     f"{data.iloc[0]['date']:DATETIME_PRINT_FORMAT}" if not data.empty else 'None')
         logger.debug("Current End: %s",
-                     f"{data.iloc[-1]['date']:%Y-%m-%d %H:%M:%S}" if not data.empty else 'None')
+                     f"{data.iloc[-1]['date']:DATETIME_PRINT_FORMAT}" if not data.empty else 'None')
 
         # Default since_ms to 30 days if nothing is given
         new_data = exchange.get_historic_ohlcv(pair=pair,
@@ -254,9 +254,9 @@ def _download_pair_history(pair: str, *,
                                          fill_missing=False, drop_incomplete=False)
 
         logger.debug("New  Start: %s",
-                     f"{data.iloc[0]['date']:%Y-%m-%d %H:%M:%S}" if not data.empty else 'None')
+                     f"{data.iloc[0]['date']:DATETIME_PRINT_FORMAT}" if not data.empty else 'None')
         logger.debug("New End: %s",
-                     f"{data.iloc[-1]['date']:%Y-%m-%d %H:%M:%S}" if not data.empty else 'None')
+                     f"{data.iloc[-1]['date']:DATETIME_PRINT_FORMAT}" if not data.empty else 'None')
 
         data_handler.ohlcv_store(pair, timeframe, data=data, candle_type=candle_type)
         return True

freqtrade/data/history/idatahandler.py

@@ -26,7 +26,7 @@ logger = logging.getLogger(__name__)
 
 class IDataHandler(ABC):
 
-    _OHLCV_REGEX = r'^([a-zA-Z_-]+)\-(\d+[a-zA-Z]{1,2})\-?([a-zA-Z_]*)?(?=\.)'
+    _OHLCV_REGEX = r'^([a-zA-Z_\d-]+)\-(\d+[a-zA-Z]{1,2})\-?([a-zA-Z_]*)?(?=\.)'
 
     def __init__(self, datadir: Path) -> None:
         self._datadir = datadir
@@ -61,7 +61,6 @@ class IDataHandler(ABC):
             ) for match in _tmp if match and len(match.groups()) > 1]
 
     @classmethod
-    @abstractmethod
     def ohlcv_get_pairs(cls, datadir: Path, timeframe: str, candle_type: CandleType) -> List[str]:
         """
         Returns a list of all pairs with ohlcv data available in this datadir
@@ -71,6 +70,15 @@ class IDataHandler(ABC):
         :param candle_type: Any of the enum CandleType (must match trading mode!)
         :return: List of Pairs
         """
+        candle = ""
+        if candle_type != CandleType.SPOT:
+            datadir = datadir.joinpath('futures')
+            candle = f"-{candle_type}"
+        ext = cls._get_file_extension()
+        _tmp = [re.search(r'^(\S+)(?=\-' + timeframe + candle + f'.{ext})', p.name)
+                for p in datadir.glob(f"*{timeframe}{candle}.{ext}")]
+        # Check if regex found something and only return these results
+        return [cls.rebuild_pair_from_filename(match[0]) for match in _tmp if match]
 
     @abstractmethod
     def ohlcv_store(
@@ -144,13 +152,17 @@ class IDataHandler(ABC):
         """
 
     @classmethod
-    @abstractmethod
     def trades_get_pairs(cls, datadir: Path) -> List[str]:
         """
         Returns a list of all pairs for which trade data is available in this
         :param datadir: Directory to search for ohlcv files
         :return: List of Pairs
         """
+        _ext = cls._get_file_extension()
+        _tmp = [re.search(r'^(\S+)(?=\-trades.' + _ext + ')', p.name)
+                for p in datadir.glob(f"*trades.{_ext}")]
+        # Check if regex found something and only return these results to avoid exceptions.
+        return [cls.rebuild_pair_from_filename(match[0]) for match in _tmp if match]
 
     @abstractmethod
     def trades_store(self, pair: str, data: TradeList) -> None:
@@ -255,15 +267,15 @@ class IDataHandler(ABC):
         Rebuild pair name from filename
         Assumes a asset name of max. 7 length to also support BTC-PERP and BTC-PERP:USD names.
         """
-        res = re.sub(r'^(([A-Za-z]{1,10})|^([A-Za-z\-]{1,6}))(_)', r'\g<1>/', pair, 1)
+        res = re.sub(r'^(([A-Za-z\d]{1,10})|^([A-Za-z\-]{1,6}))(_)', r'\g<1>/', pair, 1)
         res = re.sub('_', ':', res, 1)
         return res
 
     def ohlcv_load(self, pair, timeframe: str,
-                   candle_type: CandleType,
+                   candle_type: CandleType, *,
                    timerange: Optional[TimeRange] = None,
                    fill_missing: bool = True,
-                   drop_incomplete: bool = True,
+                   drop_incomplete: bool = False,
                    startup_candles: int = 0,
                    warn_no_data: bool = True,
                    ) -> DataFrame:
@@ -363,6 +375,12 @@ def get_datahandlerclass(datatype: str) -> Type[IDataHandler]:
     elif datatype == 'hdf5':
         from .hdf5datahandler import HDF5DataHandler
         return HDF5DataHandler
+    elif datatype == 'feather':
+        from .featherdatahandler import FeatherDataHandler
+        return FeatherDataHandler
+    elif datatype == 'parquet':
+        from .parquetdatahandler import ParquetDataHandler
+        return ParquetDataHandler
     else:
         raise ValueError(f"No datahandler for datatype {datatype} available.")
 

freqtrade/data/history/jsondatahandler.py

@@ -1,7 +1,5 @@
 import logging
-import re
-from pathlib import Path
-from typing import List, Optional
+from typing import Optional
 
 import numpy as np
 from pandas import DataFrame, read_json, to_datetime
@@ -23,26 +21,6 @@ class JsonDataHandler(IDataHandler):
     _use_zip = False
     _columns = DEFAULT_DATAFRAME_COLUMNS
 
-    @classmethod
-    def ohlcv_get_pairs(cls, datadir: Path, timeframe: str, candle_type: CandleType) -> List[str]:
-        """
-        Returns a list of all pairs with ohlcv data available in this datadir
-        for the specified timeframe
-        :param datadir: Directory to search for ohlcv files
-        :param timeframe: Timeframe to search pairs for
-        :param candle_type: Any of the enum CandleType (must match trading mode!)
-        :return: List of Pairs
-        """
-        candle = ""
-        if candle_type != CandleType.SPOT:
-            datadir = datadir.joinpath('futures')
-            candle = f"-{candle_type}"
-
-        _tmp = [re.search(r'^(\S+)(?=\-' + timeframe + candle + '.json)', p.name)
-                for p in datadir.glob(f"*{timeframe}{candle}.{cls._get_file_extension()}")]
-        # Check if regex found something and only return these results
-        return [cls.rebuild_pair_from_filename(match[0]) for match in _tmp if match]
-
     def ohlcv_store(
             self, pair: str, timeframe: str, data: DataFrame, candle_type: CandleType) -> None:
         """
@@ -119,18 +97,6 @@ class JsonDataHandler(IDataHandler):
         """
         raise NotImplementedError()
 
-    @classmethod
-    def trades_get_pairs(cls, datadir: Path) -> List[str]:
-        """
-        Returns a list of all pairs for which trade data is available in this
-        :param datadir: Directory to search for ohlcv files
-        :return: List of Pairs
-        """
-        _tmp = [re.search(r'^(\S+)(?=\-trades.json)', p.name)
-                for p in datadir.glob(f"*trades.{cls._get_file_extension()}")]
-        # Check if regex found something and only return these results to avoid exceptions.
-        return [cls.rebuild_pair_from_filename(match[0]) for match in _tmp if match]
-
     def trades_store(self, pair: str, data: TradeList) -> None:
         """
         Store trades data (list of Dicts) to file

freqtrade/data/history/parquetdatahandler.py

@@ -0,0 +1,129 @@
+import logging
+from typing import Optional
+
+from pandas import DataFrame, read_parquet, to_datetime
+
+from freqtrade.configuration import TimeRange
+from freqtrade.constants import DEFAULT_DATAFRAME_COLUMNS, TradeList
+from freqtrade.enums import CandleType
+
+from .idatahandler import IDataHandler
+
+
+logger = logging.getLogger(__name__)
+
+
+class ParquetDataHandler(IDataHandler):
+
+    _columns = DEFAULT_DATAFRAME_COLUMNS
+
+    def ohlcv_store(
+            self, pair: str, timeframe: str, data: DataFrame, candle_type: CandleType) -> None:
+        """
+        Store data in json format "values".
+            format looks as follows:
+            [[<date>,<open>,<high>,<low>,<close>]]
+        :param pair: Pair - used to generate filename
+        :param timeframe: Timeframe - used to generate filename
+        :param data: Dataframe containing OHLCV data
+        :param candle_type: Any of the enum CandleType (must match trading mode!)
+        :return: None
+        """
+        filename = self._pair_data_filename(self._datadir, pair, timeframe, candle_type)
+        self.create_dir_if_needed(filename)
+
+        data.reset_index(drop=True).loc[:, self._columns].to_parquet(filename)
+
+    def _ohlcv_load(self, pair: str, timeframe: str,
+                    timerange: Optional[TimeRange], candle_type: CandleType
+                    ) -> DataFrame:
+        """
+        Internal method used to load data for one pair from disk.
+        Implements the loading and conversion to a Pandas dataframe.
+        Timerange trimming and dataframe validation happens outside of this method.
+        :param pair: Pair to load data
+        :param timeframe: Timeframe (e.g. "5m")
+        :param timerange: Limit data to be loaded to this timerange.
+                        Optionally implemented by subclasses to avoid loading
+                        all data where possible.
+        :param candle_type: Any of the enum CandleType (must match trading mode!)
+        :return: DataFrame with ohlcv data, or empty DataFrame
+        """
+        filename = self._pair_data_filename(
+            self._datadir, pair, timeframe, candle_type=candle_type)
+        if not filename.exists():
+            # Fallback mode for 1M files
+            filename = self._pair_data_filename(
+                self._datadir, pair, timeframe, candle_type=candle_type, no_timeframe_modify=True)
+            if not filename.exists():
+                return DataFrame(columns=self._columns)
+
+        pairdata = read_parquet(filename)
+        pairdata.columns = self._columns
+        pairdata = pairdata.astype(dtype={'open': 'float', 'high': 'float',
+                                          'low': 'float', 'close': 'float', 'volume': 'float'})
+        pairdata['date'] = to_datetime(pairdata['date'],
+                                       unit='ms',
+                                       utc=True,
+                                       infer_datetime_format=True)
+        return pairdata
+
+    def ohlcv_append(
+        self,
+        pair: str,
+        timeframe: str,
+        data: DataFrame,
+        candle_type: CandleType
+    ) -> None:
+        """
+        Append data to existing data structures
+        :param pair: Pair
+        :param timeframe: Timeframe this ohlcv data is for
+        :param data: Data to append.
+        :param candle_type: Any of the enum CandleType (must match trading mode!)
+        """
+        raise NotImplementedError()
+
+    def trades_store(self, pair: str, data: TradeList) -> None:
+        """
+        Store trades data (list of Dicts) to file
+        :param pair: Pair - used for filename
+        :param data: List of Lists containing trade data,
+                     column sequence as in DEFAULT_TRADES_COLUMNS
+        """
+        # filename = self._pair_trades_filename(self._datadir, pair)
+
+        raise NotImplementedError()
+        # array = pa.array(data)
+        # array
+        # feather.write_feather(data, filename)
+
+    def trades_append(self, pair: str, data: TradeList):
+        """
+        Append data to existing files
+        :param pair: Pair - used for filename
+        :param data: List of Lists containing trade data,
+                     column sequence as in DEFAULT_TRADES_COLUMNS
+        """
+        raise NotImplementedError()
+
+    def _trades_load(self, pair: str, timerange: Optional[TimeRange] = None) -> TradeList:
+        """
+        Load a pair from file, either .json.gz or .json
+        # TODO: respect timerange ...
+        :param pair: Load trades for this pair
+        :param timerange: Timerange to load trades for - currently not implemented
+        :return: List of trades
+        """
+        raise NotImplementedError()
+        # filename = self._pair_trades_filename(self._datadir, pair)
+        # tradesdata = misc.file_load_json(filename)
+
+        # if not tradesdata:
+        #     return []
+
+        # return tradesdata
+
+    @classmethod
+    def _get_file_extension(cls):
+        return "parquet"

freqtrade/edge/edge_positioning.py

@@ -11,7 +11,7 @@ import utils_find_1st as utf1st
 from pandas import DataFrame
 
 from freqtrade.configuration import TimeRange
-from freqtrade.constants import DATETIME_PRINT_FORMAT, UNLIMITED_STAKE_AMOUNT
+from freqtrade.constants import DATETIME_PRINT_FORMAT, UNLIMITED_STAKE_AMOUNT, Config
 from freqtrade.data.history import get_timerange, load_data, refresh_data
 from freqtrade.enums import CandleType, ExitType, RunMode
 from freqtrade.exceptions import OperationalException
@@ -42,10 +42,9 @@ class Edge:
     Author: https://github.com/mishaker
     """
 
-    config: Dict = {}
     _cached_pairs: Dict[str, Any] = {}  # Keeps a list of pairs
 
-    def __init__(self, config: Dict[str, Any], exchange, strategy) -> None:
+    def __init__(self, config: Config, exchange, strategy) -> None:
 
         self.config = config
         self.exchange = exchange

freqtrade/enums/__init__.py

@@ -6,7 +6,7 @@ from freqtrade.enums.exittype import ExitType
 from freqtrade.enums.hyperoptstate import HyperoptState
 from freqtrade.enums.marginmode import MarginMode
 from freqtrade.enums.ordertypevalue import OrderTypeValues
-from freqtrade.enums.rpcmessagetype import RPCMessageType
+from freqtrade.enums.rpcmessagetype import RPCMessageType, RPCRequestType
 from freqtrade.enums.runmode import NON_UTIL_MODES, OPTIMIZE_MODES, TRADING_MODES, RunMode
 from freqtrade.enums.signaltype import SignalDirection, SignalTagType, SignalType
 from freqtrade.enums.state import State

freqtrade/enums/rpcmessagetype.py

@@ -1,7 +1,7 @@
 from enum import Enum
 
 
-class RPCMessageType(Enum):
+class RPCMessageType(str, Enum):
     STATUS = 'status'
     WARNING = 'warning'
     STARTUP = 'startup'
@@ -19,8 +19,19 @@ class RPCMessageType(Enum):
 
     STRATEGY_MSG = 'strategy_msg'
 
+    WHITELIST = 'whitelist'
+    ANALYZED_DF = 'analyzed_df'
+
     def __repr__(self):
         return self.value
 
     def __str__(self):
         return self.value
+
+
+# Enum for parsing requests from ws consumers
+class RPCRequestType(str, Enum):
+    SUBSCRIBE = 'subscribe'
+
+    WHITELIST = 'whitelist'
+    ANALYZED_DF = 'analyzed_df'

freqtrade/exchange/__init__.py

@@ -12,8 +12,8 @@ from freqtrade.exchange.coinbasepro import Coinbasepro
 from freqtrade.exchange.exchange import (amount_to_contract_precision, amount_to_contracts,
                                          amount_to_precision, available_exchanges, ccxt_exchanges,
                                          contracts_to_amount, date_minus_candles,
-                                         is_exchange_known_ccxt, is_exchange_officially_supported,
-                                         market_is_active, price_to_precision, timeframe_to_minutes,
+                                         is_exchange_known_ccxt, market_is_active,
+                                         price_to_precision, timeframe_to_minutes,
                                          timeframe_to_msecs, timeframe_to_next_date,
                                          timeframe_to_prev_date, timeframe_to_seconds,
                                          validate_exchange, validate_exchanges)

freqtrade/exchange/binance.py

@@ -1,5 +1,4 @@
 """ Binance exchange subclass """
-import json
 import logging
 from datetime import datetime
 from pathlib import Path
@@ -12,7 +11,7 @@ from freqtrade.enums import CandleType, MarginMode, TradingMode
 from freqtrade.exceptions import DDosProtection, OperationalException, TemporaryError
 from freqtrade.exchange import Exchange
 from freqtrade.exchange.common import retrier
-from freqtrade.misc import deep_merge_dicts
+from freqtrade.misc import deep_merge_dicts, json_load
 
 
 logger = logging.getLogger(__name__)
@@ -23,8 +22,7 @@ class Binance(Exchange):
     _ft_has: Dict = {
         "stoploss_on_exchange": True,
         "stoploss_order_types": {"limit": "stop_loss_limit"},
-        "order_time_in_force": ['gtc', 'fok', 'ioc'],
-        "time_in_force_parameter": "timeInForce",
+        "order_time_in_force": ['GTC', 'FOK', 'IOC'],
         "ohlcv_candle_limit": 1000,
         "trades_pagination": "id",
         "trades_pagination_arg": "fromId",
@@ -32,7 +30,7 @@ class Binance(Exchange):
         "ccxt_futures_name": "future"
     }
     _ft_has_futures: Dict = {
-        "stoploss_order_types": {"limit": "stop"},
+        "stoploss_order_types": {"limit": "limit", "market": "market"},
         "tickers_have_price": False,
     }
 
@@ -49,13 +47,12 @@ class Binance(Exchange):
         Returns True if adjustment is necessary.
         :param side: "buy" or "sell"
         """
-
-        ordertype = 'stop' if self.trading_mode == TradingMode.FUTURES else 'stop_loss_limit'
+        order_types = ('stop_loss_limit', 'stop', 'stop_market')
 
         return (
             order.get('stopPrice', None) is None
             or (
-                order['type'] == ordertype
+                order['type'] in order_types
                 and (
                     (side == "sell" and stop_loss > float(order['stopPrice'])) or
                     (side == "buy" and stop_loss < float(order['stopPrice']))
@@ -71,6 +68,37 @@ class Binance(Exchange):
             tickers = deep_merge_dicts(bidsasks, tickers, allow_null_overrides=False)
         return tickers
 
+    @retrier
+    def additional_exchange_init(self) -> None:
+        """
+        Additional exchange initialization logic.
+        .api will be available at this point.
+        Must be overridden in child methods if required.
+        """
+        try:
+            if self.trading_mode == TradingMode.FUTURES and not self._config['dry_run']:
+                position_side = self._api.fapiPrivateGetPositionsideDual()
+                self._log_exchange_response('position_side_setting', position_side)
+                assets_margin = self._api.fapiPrivateGetMultiAssetsMargin()
+                self._log_exchange_response('multi_asset_margin', assets_margin)
+                msg = ""
+                if position_side.get('dualSidePosition') is True:
+                    msg += (
+                        "\nHedge Mode is not supported by freqtrade. "
+                        "Please change 'Position Mode' on your binance futures account.")
+                if assets_margin.get('multiAssetsMargin') is True:
+                    msg += ("\nMulti-Asset Mode is not supported by freqtrade. "
+                            "Please change 'Asset Mode' on your binance futures account.")
+                if msg:
+                    raise OperationalException(msg)
+        except ccxt.DDoSProtection as e:
+            raise DDosProtection(e) from e
+        except (ccxt.NetworkError, ccxt.ExchangeError) as e:
+            raise TemporaryError(
+                f'Could not set leverage due to {e.__class__.__name__}. Message: {e}') from e
+        except ccxt.BaseError as e:
+            raise OperationalException(e) from e
+
     @retrier
     def _set_leverage(
         self,
@@ -202,7 +230,7 @@ class Binance(Exchange):
                     Path(__file__).parent / 'binance_leverage_tiers.json'
                 )
                 with open(leverage_tiers_path) as json_file:
-                    return json.load(json_file)
+                    return json_load(json_file)
             else:
                 try:
                     return self._api.fetch_leverage_tiers()

freqtrade/exchange/check_exchange.py

@@ -1,16 +1,16 @@
 import logging
-from typing import Any, Dict
 
+from freqtrade.constants import Config
 from freqtrade.enums import RunMode
 from freqtrade.exceptions import OperationalException
-from freqtrade.exchange import (available_exchanges, is_exchange_known_ccxt,
-                                is_exchange_officially_supported, validate_exchange)
+from freqtrade.exchange import available_exchanges, is_exchange_known_ccxt, validate_exchange
+from freqtrade.exchange.common import MAP_EXCHANGE_CHILDCLASS, SUPPORTED_EXCHANGES
 
 
 logger = logging.getLogger(__name__)
 
 
-def check_exchange(config: Dict[str, Any], check_for_bad: bool = True) -> bool:
+def check_exchange(config: Config, check_for_bad: bool = True) -> bool:
     """
     Check if the exchange name in the config file is supported by Freqtrade
     :param check_for_bad: if True, check the exchange against the list of known 'bad'
@@ -52,7 +52,7 @@ def check_exchange(config: Dict[str, Any], check_for_bad: bool = True) -> bool:
         else:
             logger.warning(f'Exchange "{exchange}"  will not work with Freqtrade. Reason: {reason}')
 
-    if is_exchange_officially_supported(exchange):
+    if MAP_EXCHANGE_CHILDCLASS.get(exchange, exchange) in SUPPORTED_EXCHANGES:
         logger.info(f'Exchange "{exchange}" is officially supported '
                     f'by the Freqtrade development team.')
     else:

freqtrade/exchange/exchange.py

@@ -18,19 +18,19 @@ import ccxt.async_support as ccxt_async
 from cachetools import TTLCache
 from ccxt import ROUND_DOWN, ROUND_UP, TICK_SIZE, TRUNCATE, decimal_to_precision
 from dateutil import parser
-from pandas import DataFrame
+from pandas import DataFrame, concat
 
 from freqtrade.constants import (DEFAULT_AMOUNT_RESERVE_PERCENT, NON_OPEN_EXCHANGE_STATES, BuySell,
-                                 EntryExit, ListPairsWithTimeframes, MakerTaker, PairWithTimeframe)
-from freqtrade.data.converter import ohlcv_to_dataframe, trades_dict_to_list
+                                 Config, EntryExit, ListPairsWithTimeframes, MakerTaker,
+                                 PairWithTimeframe)
+from freqtrade.data.converter import clean_ohlcv_dataframe, ohlcv_to_dataframe, trades_dict_to_list
 from freqtrade.enums import OPTIMIZE_MODES, CandleType, MarginMode, TradingMode
 from freqtrade.exceptions import (DDosProtection, ExchangeError, InsufficientFundsError,
                                   InvalidOrderException, OperationalException, PricingError,
                                   RetryableOrderError, TemporaryError)
 from freqtrade.exchange.common import (API_FETCH_ORDER_RETRY_COUNT, BAD_EXCHANGES,
                                        EXCHANGE_HAS_OPTIONAL, EXCHANGE_HAS_REQUIRED,
-                                       SUPPORTED_EXCHANGES, remove_credentials, retrier,
-                                       retrier_async)
+                                       remove_credentials, retrier, retrier_async)
 from freqtrade.misc import (chunks, deep_merge_dicts, file_dump_json, file_load_json,
                             safe_value_fallback2)
 from freqtrade.plugins.pairlist.pairlist_helpers import expand_pairlist
@@ -62,7 +62,7 @@ class Exchange:
     # or by specifying them in the configuration.
     _ft_has_default: Dict = {
         "stoploss_on_exchange": False,
-        "order_time_in_force": ["gtc"],
+        "order_time_in_force": ["GTC"],
         "time_in_force_parameter": "timeInForce",
         "ohlcv_params": {},
         "ohlcv_candle_limit": 500,
@@ -91,7 +91,7 @@ class Exchange:
         # TradingMode.SPOT always supported and not required in this list
     ]
 
-    def __init__(self, config: Dict[str, Any], validate: bool = True,
+    def __init__(self, config: Config, validate: bool = True,
                  load_leverage_tiers: bool = False) -> None:
         """
         Initializes this module with the given config,
@@ -108,7 +108,7 @@ class Exchange:
         self._loop_lock = Lock()
         self.loop = asyncio.new_event_loop()
         asyncio.set_event_loop(self.loop)
-        self._config: Dict = {}
+        self._config: Config = {}
 
         self._config.update(config)
 
@@ -184,8 +184,9 @@ class Exchange:
             # Initial markets load
             self._load_markets()
             self.validate_config(config)
+            self._startup_candle_count: int = config.get('startup_candle_count', 0)
             self.required_candle_call_count = self.validate_required_startup_candles(
-                config.get('startup_candle_count', 0), config.get('timeframe', ''))
+                self._startup_candle_count, config.get('timeframe', ''))
 
         # Converts the interval provided in minutes in config to seconds
         self.markets_refresh_interval: int = exchange_config.get(
@@ -205,7 +206,7 @@ class Exchange:
         logger.debug("Exchange object destroyed, closing async loop")
         if (self._api_async and inspect.iscoroutinefunction(self._api_async.close)
                 and self._api_async.session):
-            logger.info("Closing async ccxt session.")
+            logger.debug("Closing async ccxt session.")
             self.loop.run_until_complete(self._api_async.close())
 
     def validate_config(self, config):
@@ -446,6 +447,15 @@ class Exchange:
         contract_size = self.get_contract_size(pair)
         return contracts_to_amount(num_contracts, contract_size)
 
+    def amount_to_contract_precision(self, pair: str, amount: float) -> float:
+        """
+        Helper wrapper around amount_to_contract_precision
+        """
+        contract_size = self.get_contract_size(pair)
+
+        return amount_to_contract_precision(amount, self.get_precision_amount(pair),
+                                            self.precisionMode, contract_size)
+
     def set_sandbox(self, api: ccxt.Exchange, exchange_config: dict, name: str) -> None:
         if exchange_config.get('sandbox'):
             if api.urls.get('test'):
@@ -611,7 +621,7 @@ class Exchange:
         """
         Checks if order time in force configured in strategy/config are supported
         """
-        if any(v not in self._ft_has["order_time_in_force"]
+        if any(v.upper() not in self._ft_has["order_time_in_force"]
                for k, v in order_time_in_force.items()):
             raise OperationalException(
                 f'Time in force policies are not supported for {self.name} yet.')
@@ -989,12 +999,12 @@ class Exchange:
         ordertype: str,
         leverage: float,
         reduceOnly: bool,
-        time_in_force: str = 'gtc',
+        time_in_force: str = 'GTC',
     ) -> Dict:
         params = self._params.copy()
-        if time_in_force != 'gtc' and ordertype != 'market':
+        if time_in_force != 'GTC' and ordertype != 'market':
             param = self._ft_has.get('time_in_force_parameter', '')
-            params.update({param: time_in_force})
+            params.update({param: time_in_force.upper()})
         if reduceOnly:
             params.update({'reduceOnly': True})
         return params
@@ -1009,7 +1019,7 @@ class Exchange:
         rate: float,
         leverage: float,
         reduceOnly: bool = False,
-        time_in_force: str = 'gtc',
+        time_in_force: str = 'GTC',
     ) -> Dict:
         if self._config['dry_run']:
             dry_order = self.create_dry_run_order(
@@ -1282,7 +1292,14 @@ class Exchange:
             order = self.fetch_order(order_id, pair)
         except InvalidOrderException:
             logger.warning(f"Could not fetch cancelled order {order_id}.")
-            order = {'fee': {}, 'status': 'canceled', 'amount': amount, 'info': {}}
+            order = {
+                'id': order_id,
+                'status': 'canceled',
+                'amount': amount,
+                'filled': 0.0,
+                'fee': {},
+                'info': {}
+            }
 
         return order
 
@@ -1834,10 +1851,22 @@ class Exchange:
         return pair, timeframe, candle_type, data
 
     def _build_coroutine(self, pair: str, timeframe: str, candle_type: CandleType,
-                         since_ms: Optional[int]) -> Coroutine:
+                         since_ms: Optional[int], cache: bool) -> Coroutine:
+        not_all_data = self.required_candle_call_count > 1
+        if cache and (pair, timeframe, candle_type) in self._klines:
+            candle_limit = self.ohlcv_candle_limit(timeframe, candle_type)
+            min_date = date_minus_candles(timeframe, candle_limit - 5).timestamp()
+            # Check if 1 call can get us updated candles without hole in the data.
+            if min_date < self._pairs_last_refresh_time.get((pair, timeframe, candle_type), 0):
+                # Cache can be used - do one-off call.
+                not_all_data = False
+            else:
+                # Time jump detected, evict cache
+                logger.info(
+                    f"Time jump detected. Evicting cache for {pair}, {timeframe}, {candle_type}")
+                del self._klines[(pair, timeframe, candle_type)]
 
-        if (not since_ms
-                and (self._ft_has["ohlcv_require_since"] or self.required_candle_call_count > 1)):
+        if (not since_ms and (self._ft_has["ohlcv_require_since"] or not_all_data)):
             # Multiple calls for one pair - to get more history
             one_call = timeframe_to_msecs(timeframe) * self.ohlcv_candle_limit(
                 timeframe, candle_type, since_ms)
@@ -1853,6 +1882,59 @@ class Exchange:
             return self._async_get_candle_history(
                 pair, timeframe, since_ms=since_ms, candle_type=candle_type)
 
+    def _build_ohlcv_dl_jobs(
+            self, pair_list: ListPairsWithTimeframes, since_ms: Optional[int],
+            cache: bool) -> Tuple[List[Coroutine], List[Tuple[str, str, CandleType]]]:
+        """
+        Build Coroutines to execute as part of refresh_latest_ohlcv
+        """
+        input_coroutines = []
+        cached_pairs = []
+        for pair, timeframe, candle_type in set(pair_list):
+            if (timeframe not in self.timeframes
+                    and candle_type in (CandleType.SPOT, CandleType.FUTURES)):
+                logger.warning(
+                    f"Cannot download ({pair}, {timeframe}) combination as this timeframe is "
+                    f"not available on {self.name}. Available timeframes are "
+                    f"{', '.join(self.timeframes)}.")
+                continue
+
+            if ((pair, timeframe, candle_type) not in self._klines or not cache
+                    or self._now_is_time_to_refresh(pair, timeframe, candle_type)):
+
+                input_coroutines.append(
+                    self._build_coroutine(pair, timeframe, candle_type, since_ms, cache))
+
+            else:
+                logger.debug(
+                    f"Using cached candle (OHLCV) data for {pair}, {timeframe}, {candle_type} ..."
+                )
+                cached_pairs.append((pair, timeframe, candle_type))
+
+        return input_coroutines, cached_pairs
+
+    def _process_ohlcv_df(self, pair: str, timeframe: str, c_type: CandleType, ticks: List[List],
+                          cache: bool, drop_incomplete: bool) -> DataFrame:
+        # keeping last candle time as last refreshed time of the pair
+        if ticks and cache:
+            self._pairs_last_refresh_time[(pair, timeframe, c_type)] = ticks[-1][0] // 1000
+        # keeping parsed dataframe in cache
+        ohlcv_df = ohlcv_to_dataframe(ticks, timeframe, pair=pair, fill_missing=True,
+                                      drop_incomplete=drop_incomplete)
+        if cache:
+            if (pair, timeframe, c_type) in self._klines:
+                old = self._klines[(pair, timeframe, c_type)]
+                # Reassign so we return the updated, combined df
+                ohlcv_df = clean_ohlcv_dataframe(concat([old, ohlcv_df], axis=0), timeframe, pair,
+                                                 fill_missing=True, drop_incomplete=False)
+                candle_limit = self.ohlcv_candle_limit(timeframe, self._config['candle_type_def'])
+                # Age out old candles
+                ohlcv_df = ohlcv_df.tail(candle_limit + self._startup_candle_count)
+                self._klines[(pair, timeframe, c_type)] = ohlcv_df
+            else:
+                self._klines[(pair, timeframe, c_type)] = ohlcv_df
+        return ohlcv_df
+
     def refresh_latest_ohlcv(self, pair_list: ListPairsWithTimeframes, *,
                              since_ms: Optional[int] = None, cache: bool = True,
                              drop_incomplete: Optional[bool] = None
@@ -1870,27 +1952,9 @@ class Exchange:
         """
         logger.debug("Refreshing candle (OHLCV) data for %d pairs", len(pair_list))
         drop_incomplete = self._ohlcv_partial_candle if drop_incomplete is None else drop_incomplete
-        input_coroutines = []
-        cached_pairs = []
-        # Gather coroutines to run
-        for pair, timeframe, candle_type in set(pair_list):
-            if (timeframe not in self.timeframes
-                    and candle_type in (CandleType.SPOT, CandleType.FUTURES)):
-                logger.warning(
-                    f"Cannot download ({pair}, {timeframe}) combination as this timeframe is "
-                    f"not available on {self.name}. Available timeframes are "
-                    f"{', '.join(self.timeframes)}.")
-                continue
-            if ((pair, timeframe, candle_type) not in self._klines or not cache
-                    or self._now_is_time_to_refresh(pair, timeframe, candle_type)):
-                input_coroutines.append(self._build_coroutine(
-                    pair, timeframe, candle_type=candle_type, since_ms=since_ms))
 
-            else:
-                logger.debug(
-                    f"Using cached candle (OHLCV) data for {pair}, {timeframe}, {candle_type} ..."
-                )
-                cached_pairs.append((pair, timeframe, candle_type))
+        # Gather coroutines to run
+        input_coroutines, cached_pairs = self._build_ohlcv_dl_jobs(pair_list, since_ms, cache)
 
         results_df = {}
         # Chunk requests into batches of 100 to avoid overwelming ccxt Throttling
@@ -1907,16 +1971,11 @@ class Exchange:
                     continue
                 # Deconstruct tuple (has 4 elements)
                 pair, timeframe, c_type, ticks = res
-                # keeping last candle time as last refreshed time of the pair
-                if ticks:
-                    self._pairs_last_refresh_time[(pair, timeframe, c_type)] = ticks[-1][0] // 1000
-                # keeping parsed dataframe in cache
-                ohlcv_df = ohlcv_to_dataframe(
-                    ticks, timeframe, pair=pair, fill_missing=True,
-                    drop_incomplete=drop_incomplete)
+                ohlcv_df = self._process_ohlcv_df(
+                    pair, timeframe, c_type, ticks, cache, drop_incomplete)
+
                 results_df[(pair, timeframe, c_type)] = ohlcv_df
-                if cache:
-                    self._klines[(pair, timeframe, c_type)] = ohlcv_df
+
         # Return cached klines
         for pair, timeframe, c_type in cached_pairs:
             results_df[(pair, timeframe, c_type)] = self.klines(
@@ -1931,10 +1990,8 @@ class Exchange:
         interval_in_sec = timeframe_to_seconds(timeframe)
 
         return not (
-            (self._pairs_last_refresh_time.get(
-                (pair, timeframe, candle_type),
-                0
-            ) + interval_in_sec) >= arrow.utcnow().int_timestamp
+            (self._pairs_last_refresh_time.get((pair, timeframe, candle_type), 0)
+             + interval_in_sec) >= arrow.utcnow().int_timestamp
         )
 
     @retrier_async
@@ -2295,7 +2352,7 @@ class Exchange:
             updated = tiers.get('updated')
             if updated:
                 updated_dt = parser.parse(updated)
-                if updated_dt < datetime.now(timezone.utc) - timedelta(days=1):
+                if updated_dt < datetime.now(timezone.utc) - timedelta(weeks=4):
                     logger.info("Cached leverage tiers are outdated. Will update.")
                     return None
             return tiers['data']
@@ -2432,36 +2489,6 @@ class Exchange:
         """
         return 0.0
 
-    def get_liquidation_price(
-            self,
-            pair: str,
-            open_rate: float,
-            amount: float,  # quote currency, includes leverage
-            stake_amount: float,
-            leverage: float,
-            is_short: bool
-    ) -> Optional[float]:
-
-        if self.trading_mode in TradingMode.SPOT:
-            return None
-        elif (
-            self.trading_mode == TradingMode.FUTURES
-        ):
-            isolated_liq = self.get_or_calculate_liquidation_price(
-                pair=pair,
-                open_rate=open_rate,
-                is_short=is_short,
-                amount=amount,
-                stake_amount=stake_amount,
-                wallet_balance=stake_amount,  # In isolated mode, stake-amount = wallet size
-                mm_ex_1=0.0,
-                upnl_ex_1=0.0,
-            )
-            return isolated_liq
-        else:
-            raise OperationalException(
-                "Freqtrade currently only supports futures for leverage trading.")
-
     def funding_fee_cutoff(self, open_date: datetime):
         """
         :param open_date: The open date for a trade
@@ -2530,8 +2557,13 @@ class Exchange:
             cache=False,
             drop_incomplete=False,
         )
-        funding_rates = candle_histories[funding_comb]
-        mark_rates = candle_histories[mark_comb]
+        try:
+            # we can't assume we always get histories - for example during exchange downtimes
+            funding_rates = candle_histories[funding_comb]
+            mark_rates = candle_histories[mark_comb]
+        except KeyError:
+            raise ExchangeError("Could not find funding rates.") from None
+
         funding_mark_rates = self.combine_funding_and_mark(
             funding_rates=funding_rates, mark_rates=mark_rates)
 
@@ -2611,6 +2643,8 @@ class Exchange:
         :param is_short: trade direction
         :param amount: Trade amount
         :param open_date: Open date of the trade
+        :return: funding fee since open_date
+        :raies: ExchangeError if something goes wrong.
         """
         if self.trading_mode == TradingMode.FUTURES:
             if self._config['dry_run']:
@@ -2622,7 +2656,7 @@ class Exchange:
         else:
             return 0.0
 
-    def get_or_calculate_liquidation_price(
+    def get_liquidation_price(
         self,
         pair: str,
         # Dry-run
@@ -2630,7 +2664,7 @@ class Exchange:
         is_short: bool,
         amount: float,  # Absolute value of position size
         stake_amount: float,
-        wallet_balance: float,  # Or margin balance
+        wallet_balance: float,
         mm_ex_1: float = 0.0,  # (Binance) Cross only
         upnl_ex_1: float = 0.0,  # (Binance) Cross only
     ) -> Optional[float]:
@@ -2641,8 +2675,9 @@ class Exchange:
             return None
         elif (self.trading_mode != TradingMode.FUTURES):
             raise OperationalException(
-                f"{self.name} does not support {self.margin_mode.value} {self.trading_mode.value}")
+                f"{self.name} does not support {self.margin_mode} {self.trading_mode}")
 
+        isolated_liq = None
         if self._config['dry_run'] or not self.exchange_has("fetchPositions"):
 
             isolated_liq = self.dry_run_liquidation_price(
@@ -2660,8 +2695,6 @@ class Exchange:
             if len(positions) > 0:
                 pos = positions[0]
                 isolated_liq = pos['liquidationPrice']
-            else:
-                return None
 
         if isolated_liq:
             buffer_amount = abs(open_rate - isolated_liq) * self.liquidation_buffer
@@ -2768,10 +2801,6 @@ def is_exchange_known_ccxt(exchange_name: str, ccxt_module: CcxtModuleType = Non
     return exchange_name in ccxt_exchanges(ccxt_module)
 
 
-def is_exchange_officially_supported(exchange_name: str) -> bool:
-    return exchange_name in SUPPORTED_EXCHANGES
-
-
 def ccxt_exchanges(ccxt_module: CcxtModuleType = None) -> List[str]:
     """
     Return the list of all exchanges known to ccxt
@@ -2905,7 +2934,7 @@ def amount_to_contracts(amount: float, contract_size: Optional[float]) -> float:
     :return: num-contracts
     """
     if contract_size and contract_size != 1:
-        return amount / contract_size
+        return float(FtPrecise(amount) / FtPrecise(contract_size))
     else:
         return amount
 
@@ -2919,7 +2948,7 @@ def contracts_to_amount(num_contracts: float, contract_size: Optional[float]) ->
     """
 
     if contract_size and contract_size != 1:
-        return num_contracts * contract_size
+        return float(FtPrecise(num_contracts) * FtPrecise(contract_size))
     else:
         return num_contracts
 

freqtrade/exchange/ftx.py

@@ -19,6 +19,7 @@ logger = logging.getLogger(__name__)
 class Ftx(Exchange):
 
     _ft_has: Dict = {
+        "order_time_in_force": ['GTC', 'IOC', 'PO'],
         "stoploss_on_exchange": True,
         "ohlcv_candle_limit": 1500,
         "ohlcv_require_since": True,

freqtrade/exchange/gateio.py

@@ -25,8 +25,7 @@ class Gateio(Exchange):
 
     _ft_has: Dict = {
         "ohlcv_candle_limit": 1000,
-        "time_in_force_parameter": "timeInForce",
-        "order_time_in_force": ['gtc', 'ioc'],
+        "order_time_in_force": ['GTC', 'IOC'],
         "stoploss_order_types": {"limit": "limit"},
         "stoploss_on_exchange": True,
     }
@@ -57,7 +56,7 @@ class Gateio(Exchange):
             ordertype: str,
             leverage: float,
             reduceOnly: bool,
-            time_in_force: str = 'gtc',
+            time_in_force: str = 'GTC',
             ) -> Dict:
         params = super()._get_params(
             side=side,
@@ -69,7 +68,7 @@ class Gateio(Exchange):
         if ordertype == 'market' and self.trading_mode == TradingMode.FUTURES:
             params['type'] = 'market'
             param = self._ft_has.get('time_in_force_parameter', '')
-            params.update({param: 'ioc'})
+            params.update({param: 'IOC'})
         return params
 
     def get_trades_for_order(self, order_id: str, pair: str, since: datetime,

freqtrade/exchange/kraken.py

@@ -171,7 +171,7 @@ class Kraken(Exchange):
         ordertype: str,
         leverage: float,
         reduceOnly: bool,
-        time_in_force: str = 'gtc'
+        time_in_force: str = 'GTC'
     ) -> Dict:
         params = super()._get_params(
             side=side,

freqtrade/exchange/kucoin.py

@@ -23,8 +23,7 @@ class Kucoin(Exchange):
         "stoploss_order_types": {"limit": "limit", "market": "market"},
         "l2_limit_range": [20, 100],
         "l2_limit_range_required": False,
-        "order_time_in_force": ['gtc', 'fok', 'ioc'],
-        "time_in_force_parameter": "timeInForce",
+        "order_time_in_force": ['GTC', 'FOK', 'IOC'],
         "ohlcv_candle_limit": 1500,
     }
 

freqtrade/exchange/okx.py

@@ -4,8 +4,7 @@ from typing import Dict, List, Optional, Tuple
 import ccxt
 
 from freqtrade.constants import BuySell
-from freqtrade.enums import MarginMode, TradingMode
-from freqtrade.enums.candletype import CandleType
+from freqtrade.enums import CandleType, MarginMode, TradingMode
 from freqtrade.exceptions import DDosProtection, OperationalException, TemporaryError
 from freqtrade.exchange import Exchange, date_minus_candles
 from freqtrade.exchange.common import retrier
@@ -72,13 +71,15 @@ class Okx(Exchange):
         try:
             if self.trading_mode == TradingMode.FUTURES and not self._config['dry_run']:
                 accounts = self._api.fetch_accounts()
+                self._log_exchange_response('fetch_accounts', accounts)
                 if len(accounts) > 0:
                     self.net_only = accounts[0].get('info', {}).get('posMode') == 'net_mode'
         except ccxt.DDoSProtection as e:
             raise DDosProtection(e) from e
         except (ccxt.NetworkError, ccxt.ExchangeError) as e:
             raise TemporaryError(
-                f'Could not set leverage due to {e.__class__.__name__}. Message: {e}') from e
+                f'Error in additional_exchange_init due to {e.__class__.__name__}. Message: {e}'
+                ) from e
         except ccxt.BaseError as e:
             raise OperationalException(e) from e
 
@@ -98,7 +99,7 @@ class Okx(Exchange):
         ordertype: str,
         leverage: float,
         reduceOnly: bool,
-        time_in_force: str = 'gtc',
+        time_in_force: str = 'GTC',
     ) -> Dict:
         params = super()._get_params(
             side=side,

freqtrade/freqai/base_models/BaseClassifierModel.py

@@ -1,4 +1,5 @@
 import logging
+from time import time
 from typing import Any, Tuple
 
 import numpy as np
@@ -21,34 +22,36 @@ class BaseClassifierModel(IFreqaiModel):
     """
 
     def train(
-        self, unfiltered_dataframe: DataFrame, pair: str, dk: FreqaiDataKitchen
+        self, unfiltered_df: DataFrame, pair: str, dk: FreqaiDataKitchen, **kwargs
     ) -> Any:
         """
         Filter the training data and train a model to it. Train makes heavy use of the datakitchen
         for storing, saving, loading, and analyzing the data.
-        :param unfiltered_dataframe: Full dataframe for the current training period
+        :param unfiltered_df: Full dataframe for the current training period
         :param metadata: pair metadata from strategy.
         :return:
         :model: Trained model which can be used to inference (self.predict)
         """
 
-        logger.info("-------------------- Starting training " f"{pair} --------------------")
+        logger.info(f"-------------------- Starting training {pair} --------------------")
+
+        start_time = time()
 
         # filter the features requested by user in the configuration file and elegantly handle NaNs
         features_filtered, labels_filtered = dk.filter_features(
-            unfiltered_dataframe,
+            unfiltered_df,
             dk.training_features_list,
             dk.label_list,
             training_filter=True,
         )
 
-        start_date = unfiltered_dataframe["date"].iloc[0].strftime("%Y-%m-%d")
-        end_date = unfiltered_dataframe["date"].iloc[-1].strftime("%Y-%m-%d")
+        start_date = unfiltered_df["date"].iloc[0].strftime("%Y-%m-%d")
+        end_date = unfiltered_df["date"].iloc[-1].strftime("%Y-%m-%d")
         logger.info(f"-------------------- Training on data from {start_date} to "
-                    f"{end_date}--------------------")
+                    f"{end_date} --------------------")
         # split data into train/test data.
         data_dictionary = dk.make_train_test_datasets(features_filtered, labels_filtered)
-        if not self.freqai_info.get('fit_live_predictions', 0) or not self.live:
+        if not self.freqai_info.get("fit_live_predictions", 0) or not self.live:
             dk.fit_labels()
         # normalize all data based on train_dataset only
         data_dictionary = dk.normalize_data(data_dictionary)
@@ -57,36 +60,39 @@ class BaseClassifierModel(IFreqaiModel):
         self.data_cleaning_train(dk)
 
         logger.info(
-            f'Training model on {len(dk.data_dictionary["train_features"].columns)}' " features"
+            f"Training model on {len(dk.data_dictionary['train_features'].columns)} features"
         )
-        logger.info(f'Training model on {len(data_dictionary["train_features"])} data points')
+        logger.info(f"Training model on {len(data_dictionary['train_features'])} data points")
 
-        model = self.fit(data_dictionary)
+        model = self.fit(data_dictionary, dk)
 
-        logger.info(f"--------------------done training {pair}--------------------")
+        end_time = time()
+
+        logger.info(f"-------------------- Done training {pair} "
+                    f"({end_time - start_time:.2f} secs) --------------------")
 
         return model
 
     def predict(
-        self, unfiltered_dataframe: DataFrame, dk: FreqaiDataKitchen, first: bool = False
+        self, unfiltered_df: DataFrame, dk: FreqaiDataKitchen, **kwargs
     ) -> Tuple[DataFrame, npt.NDArray[np.int_]]:
         """
         Filter the prediction features data and predict with it.
-        :param: unfiltered_dataframe: Full dataframe for the current backtest period.
+        :param: unfiltered_df: Full dataframe for the current backtest period.
         :return:
         :pred_df: dataframe containing the predictions
         :do_predict: np.array of 1s and 0s to indicate places where freqai needed to remove
         data (NaNs) or felt uncertain about data (PCA and DI index)
         """
 
-        dk.find_features(unfiltered_dataframe)
-        filtered_dataframe, _ = dk.filter_features(
-            unfiltered_dataframe, dk.training_features_list, training_filter=False
+        dk.find_features(unfiltered_df)
+        filtered_df, _ = dk.filter_features(
+            unfiltered_df, dk.training_features_list, training_filter=False
         )
-        filtered_dataframe = dk.normalize_data_from_metadata(filtered_dataframe)
-        dk.data_dictionary["prediction_features"] = filtered_dataframe
+        filtered_df = dk.normalize_data_from_metadata(filtered_df)
+        dk.data_dictionary["prediction_features"] = filtered_df
 
-        self.data_cleaning_predict(dk, filtered_dataframe)
+        self.data_cleaning_predict(dk)
 
         predictions = self.model.predict(dk.data_dictionary["prediction_features"])
         pred_df = DataFrame(predictions, columns=dk.label_list)

freqtrade/freqai/base_models/BaseRegressionModel.py

@@ -1,4 +1,5 @@
 import logging
+from time import time
 from typing import Any, Tuple
 
 import numpy as np
@@ -20,34 +21,36 @@ class BaseRegressionModel(IFreqaiModel):
     """
 
     def train(
-        self, unfiltered_dataframe: DataFrame, pair: str, dk: FreqaiDataKitchen
+        self, unfiltered_df: DataFrame, pair: str, dk: FreqaiDataKitchen, **kwargs
     ) -> Any:
         """
         Filter the training data and train a model to it. Train makes heavy use of the datakitchen
         for storing, saving, loading, and analyzing the data.
-        :param unfiltered_dataframe: Full dataframe for the current training period
+        :param unfiltered_df: Full dataframe for the current training period
         :param metadata: pair metadata from strategy.
         :return:
         :model: Trained model which can be used to inference (self.predict)
         """
 
-        logger.info("-------------------- Starting training " f"{pair} --------------------")
+        logger.info(f"-------------------- Starting training {pair} --------------------")
+
+        start_time = time()
 
         # filter the features requested by user in the configuration file and elegantly handle NaNs
         features_filtered, labels_filtered = dk.filter_features(
-            unfiltered_dataframe,
+            unfiltered_df,
             dk.training_features_list,
             dk.label_list,
             training_filter=True,
         )
 
-        start_date = unfiltered_dataframe["date"].iloc[0].strftime("%Y-%m-%d")
-        end_date = unfiltered_dataframe["date"].iloc[-1].strftime("%Y-%m-%d")
+        start_date = unfiltered_df["date"].iloc[0].strftime("%Y-%m-%d")
+        end_date = unfiltered_df["date"].iloc[-1].strftime("%Y-%m-%d")
         logger.info(f"-------------------- Training on data from {start_date} to "
-                    f"{end_date}--------------------")
+                    f"{end_date} --------------------")
         # split data into train/test data.
         data_dictionary = dk.make_train_test_datasets(features_filtered, labels_filtered)
-        if not self.freqai_info.get('fit_live_predictions', 0) or not self.live:
+        if not self.freqai_info.get("fit_live_predictions", 0) or not self.live:
             dk.fit_labels()
         # normalize all data based on train_dataset only
         data_dictionary = dk.normalize_data(data_dictionary)
@@ -56,37 +59,40 @@ class BaseRegressionModel(IFreqaiModel):
         self.data_cleaning_train(dk)
 
         logger.info(
-            f'Training model on {len(dk.data_dictionary["train_features"].columns)}' " features"
+            f"Training model on {len(dk.data_dictionary['train_features'].columns)} features"
         )
-        logger.info(f'Training model on {len(data_dictionary["train_features"])} data points')
+        logger.info(f"Training model on {len(data_dictionary['train_features'])} data points")
 
-        model = self.fit(data_dictionary)
+        model = self.fit(data_dictionary, dk)
 
-        logger.info(f"--------------------done training {pair}--------------------")
+        end_time = time()
+
+        logger.info(f"-------------------- Done training {pair} "
+                    f"({end_time - start_time:.2f} secs) --------------------")
 
         return model
 
     def predict(
-        self, unfiltered_dataframe: DataFrame, dk: FreqaiDataKitchen, first: bool = False
+        self, unfiltered_df: DataFrame, dk: FreqaiDataKitchen, **kwargs
     ) -> Tuple[DataFrame, npt.NDArray[np.int_]]:
         """
         Filter the prediction features data and predict with it.
-        :param: unfiltered_dataframe: Full dataframe for the current backtest period.
+        :param: unfiltered_df: Full dataframe for the current backtest period.
         :return:
         :pred_df: dataframe containing the predictions
         :do_predict: np.array of 1s and 0s to indicate places where freqai needed to remove
         data (NaNs) or felt uncertain about data (PCA and DI index)
         """
 
-        dk.find_features(unfiltered_dataframe)
-        filtered_dataframe, _ = dk.filter_features(
-            unfiltered_dataframe, dk.training_features_list, training_filter=False
+        dk.find_features(unfiltered_df)
+        filtered_df, _ = dk.filter_features(
+            unfiltered_df, dk.training_features_list, training_filter=False
         )
-        filtered_dataframe = dk.normalize_data_from_metadata(filtered_dataframe)
-        dk.data_dictionary["prediction_features"] = filtered_dataframe
+        filtered_df = dk.normalize_data_from_metadata(filtered_df)
+        dk.data_dictionary["prediction_features"] = filtered_df
 
         # optional additional data cleaning/analysis
-        self.data_cleaning_predict(dk, filtered_dataframe)
+        self.data_cleaning_predict(dk)
 
         predictions = self.model.predict(dk.data_dictionary["prediction_features"])
         pred_df = DataFrame(predictions, columns=dk.label_list)

freqtrade/freqai/base_models/BaseTensorFlowModel.py

@@ -1,4 +1,5 @@
 import logging
+from time import time
 from typing import Any
 
 from pandas import DataFrame
@@ -17,34 +18,36 @@ class BaseTensorFlowModel(IFreqaiModel):
     """
 
     def train(
-        self, unfiltered_dataframe: DataFrame, pair: str, dk: FreqaiDataKitchen
+        self, unfiltered_df: DataFrame, pair: str, dk: FreqaiDataKitchen, **kwargs
     ) -> Any:
         """
         Filter the training data and train a model to it. Train makes heavy use of the datakitchen
         for storing, saving, loading, and analyzing the data.
-        :param unfiltered_dataframe: Full dataframe for the current training period
+        :param unfiltered_df: Full dataframe for the current training period
         :param metadata: pair metadata from strategy.
         :return:
         :model: Trained model which can be used to inference (self.predict)
         """
 
-        logger.info("-------------------- Starting training " f"{pair} --------------------")
+        logger.info(f"-------------------- Starting training {pair} --------------------")
+
+        start_time = time()
 
         # filter the features requested by user in the configuration file and elegantly handle NaNs
         features_filtered, labels_filtered = dk.filter_features(
-            unfiltered_dataframe,
+            unfiltered_df,
             dk.training_features_list,
             dk.label_list,
             training_filter=True,
         )
 
-        start_date = unfiltered_dataframe["date"].iloc[0].strftime("%Y-%m-%d")
-        end_date = unfiltered_dataframe["date"].iloc[-1].strftime("%Y-%m-%d")
+        start_date = unfiltered_df["date"].iloc[0].strftime("%Y-%m-%d")
+        end_date = unfiltered_df["date"].iloc[-1].strftime("%Y-%m-%d")
         logger.info(f"-------------------- Training on data from {start_date} to "
-                    f"{end_date}--------------------")
+                    f"{end_date} --------------------")
         # split data into train/test data.
         data_dictionary = dk.make_train_test_datasets(features_filtered, labels_filtered)
-        if not self.freqai_info.get('fit_live_predictions', 0) or not self.live:
+        if not self.freqai_info.get("fit_live_predictions", 0) or not self.live:
             dk.fit_labels()
         # normalize all data based on train_dataset only
         data_dictionary = dk.normalize_data(data_dictionary)
@@ -53,12 +56,15 @@ class BaseTensorFlowModel(IFreqaiModel):
         self.data_cleaning_train(dk)
 
         logger.info(
-            f'Training model on {len(dk.data_dictionary["train_features"].columns)}' " features"
+            f"Training model on {len(dk.data_dictionary['train_features'].columns)} features"
         )
-        logger.info(f'Training model on {len(data_dictionary["train_features"])} data points')
+        logger.info(f"Training model on {len(data_dictionary['train_features'])} data points")
 
-        model = self.fit(data_dictionary)
+        model = self.fit(data_dictionary, dk)
 
-        logger.info(f"--------------------done training {pair}--------------------")
+        end_time = time()
+
+        logger.info(f"-------------------- Done training {pair} "
+                    f"({end_time - start_time:.2f} secs) --------------------")
 
         return model

freqtrade/freqai/base_models/FreqaiMultiOutputRegressor.py

@@ -0,0 +1,64 @@
+from joblib import Parallel
+from sklearn.multioutput import MultiOutputRegressor, _fit_estimator
+from sklearn.utils.fixes import delayed
+from sklearn.utils.validation import has_fit_parameter
+
+
+class FreqaiMultiOutputRegressor(MultiOutputRegressor):
+
+    def fit(self, X, y, sample_weight=None, fit_params=None):
+        """Fit the model to data, separately for each output variable.
+        Parameters
+        ----------
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
+            The input data.
+        y : {array-like, sparse matrix} of shape (n_samples, n_outputs)
+            Multi-output targets. An indicator matrix turns on multilabel
+            estimation.
+        sample_weight : array-like of shape (n_samples,), default=None
+            Sample weights. If `None`, then samples are equally weighted.
+            Only supported if the underlying regressor supports sample
+            weights.
+        fit_params : A list of dicts for the fit_params
+            Parameters passed to the ``estimator.fit`` method of each step.
+            Each dict may contain same or different values (e.g. different
+            eval_sets or init_models)
+            .. versionadded:: 0.23
+        Returns
+        -------
+        self : object
+            Returns a fitted instance.
+        """
+
+        if not hasattr(self.estimator, "fit"):
+            raise ValueError("The base estimator should implement a fit method")
+
+        y = self._validate_data(X="no_validation", y=y, multi_output=True)
+
+        if y.ndim == 1:
+            raise ValueError(
+                "y must have at least two dimensions for "
+                "multi-output regression but has only one."
+            )
+
+        if sample_weight is not None and not has_fit_parameter(
+            self.estimator, "sample_weight"
+        ):
+            raise ValueError("Underlying estimator does not support sample weights.")
+
+        if not fit_params:
+            fit_params = [None] * y.shape[1]
+
+        self.estimators_ = Parallel(n_jobs=self.n_jobs)(
+            delayed(_fit_estimator)(
+                self.estimator, X, y[:, i], sample_weight, **fit_params[i]
+            )
+            for i in range(y.shape[1])
+        )
+
+        if hasattr(self.estimators_[0], "n_features_in_"):
+            self.n_features_in_ = self.estimators_[0].n_features_in_
+        if hasattr(self.estimators_[0], "feature_names_in_"):
+            self.feature_names_in_ = self.estimators_[0].feature_names_in_
+
+        return

freqtrade/freqai/data_drawer.py

@@ -16,6 +16,7 @@ from numpy.typing import NDArray
 from pandas import DataFrame
 
 from freqtrade.configuration import TimeRange
+from freqtrade.constants import Config
 from freqtrade.data.history import load_pair_history
 from freqtrade.exceptions import OperationalException
 from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
@@ -27,9 +28,7 @@ logger = logging.getLogger(__name__)
 
 class pair_info(TypedDict):
     model_filename: str
-    first: bool
     trained_timestamp: int
-    priority: int
     data_path: str
     extras: dict
 
@@ -58,7 +57,7 @@ class FreqaiDataDrawer:
     Juha Nykänen @suikula, Wagner Costa @wagnercosta, Johan Vlugt @Jooopieeert
     """
 
-    def __init__(self, full_path: Path, config: dict, follow_mode: bool = False):
+    def __init__(self, full_path: Path, config: Config, follow_mode: bool = False):
 
         self.config = config
         self.freqai_info = config.get("freqai", {})
@@ -76,6 +75,8 @@ class FreqaiDataDrawer:
             self.full_path / f"follower_dictionary-{self.follower_name}.json"
         )
         self.historic_predictions_path = Path(self.full_path / "historic_predictions.pkl")
+        self.historic_predictions_bkp_path = Path(
+            self.full_path / "historic_predictions.backup.pkl")
         self.pair_dictionary_path = Path(self.full_path / "pair_dictionary.json")
         self.follow_mode = follow_mode
         if follow_mode:
@@ -89,7 +90,7 @@ class FreqaiDataDrawer:
         self.old_DBSCAN_eps: Dict[str, float] = {}
         self.empty_pair_dict: pair_info = {
                 "model_filename": "", "trained_timestamp": 0,
-                "priority": 1, "first": True, "data_path": "", "extras": {}}
+                "data_path": "", "extras": {}}
 
     def load_drawer_from_disk(self):
         """
@@ -118,13 +119,21 @@ class FreqaiDataDrawer:
         """
         exists = self.historic_predictions_path.is_file()
         if exists:
-            with open(self.historic_predictions_path, "rb") as fp:
-                self.historic_predictions = cloudpickle.load(fp)
-            logger.info(
-                f"Found existing historic predictions at {self.full_path}, but beware "
-                "that statistics may be inaccurate if the bot has been offline for "
-                "an extended period of time."
-            )
+            try:
+                with open(self.historic_predictions_path, "rb") as fp:
+                    self.historic_predictions = cloudpickle.load(fp)
+                logger.info(
+                    f"Found existing historic predictions at {self.full_path}, but beware "
+                    "that statistics may be inaccurate if the bot has been offline for "
+                    "an extended period of time."
+                )
+            except EOFError:
+                logger.warning(
+                    'Historical prediction file was corrupted. Trying to load backup file.')
+                with open(self.historic_predictions_bkp_path, "rb") as fp:
+                    self.historic_predictions = cloudpickle.load(fp)
+                logger.warning('FreqAI successfully loaded the backup historical predictions file.')
+
         elif not self.follow_mode:
             logger.info("Could not find existing historic_predictions, starting from scratch")
         else:
@@ -142,6 +151,9 @@ class FreqaiDataDrawer:
         with open(self.historic_predictions_path, "wb") as fp:
             cloudpickle.dump(self.historic_predictions, fp, protocol=cloudpickle.DEFAULT_PROTOCOL)
 
+        # create a backup
+        shutil.copy(self.historic_predictions_path, self.historic_predictions_bkp_path)
+
     def save_drawer_to_disk(self):
         """
         Save data drawer full of all pair model metadata in present model folder.
@@ -203,7 +215,6 @@ class FreqaiDataDrawer:
             self.pair_dict[pair] = self.empty_pair_dict.copy()
             model_filename = ""
             trained_timestamp = 0
-            self.pair_dict[pair]["priority"] = len(self.pair_dict)
 
         if not data_path_set and self.follow_mode:
             logger.warning(
@@ -223,18 +234,9 @@ class FreqaiDataDrawer:
             return
         else:
             self.pair_dict[metadata["pair"]] = self.empty_pair_dict.copy()
-            self.pair_dict[metadata["pair"]]["priority"] = len(self.pair_dict)
 
             return
 
-    def pair_to_end_of_training_queue(self, pair: str) -> None:
-        # march all pairs up in the queue
-        with self.pair_dict_lock:
-            for p in self.pair_dict:
-                self.pair_dict[p]["priority"] -= 1
-            # send pair to end of queue
-            self.pair_dict[pair]["priority"] = len(self.pair_dict)
-
     def set_initial_return_values(self, pair: str, pred_df: DataFrame) -> None:
         """
         Set the initial return values to the historical predictions dataframe. This avoids needing
@@ -255,7 +257,7 @@ class FreqaiDataDrawer:
 
     def append_model_predictions(self, pair: str, predictions: DataFrame,
                                  do_preds: NDArray[np.int_],
-                                 dk: FreqaiDataKitchen, len_df: int) -> None:
+                                 dk: FreqaiDataKitchen, strat_df: DataFrame) -> None:
         """
         Append model predictions to historic predictions dataframe, then set the
         strategy return dataframe to the tail of the historic predictions. The length of
@@ -264,6 +266,7 @@ class FreqaiDataDrawer:
         historic predictions.
         """
 
+        len_df = len(strat_df)
         index = self.historic_predictions[pair].index[-1:]
         columns = self.historic_predictions[pair].columns
 
@@ -291,6 +294,15 @@ class FreqaiDataDrawer:
             for return_str in rets:
                 df[return_str].iloc[-1] = rets[return_str]
 
+        # this logic carries users between version without needing to
+        # change their identifier
+        if 'close_price' not in df.columns:
+            df['close_price'] = np.nan
+            df['date_pred'] = np.nan
+
+        df['close_price'].iloc[-1] = strat_df['close'].iloc[-1]
+        df['date_pred'].iloc[-1] = strat_df['date'].iloc[-1]
+
         self.model_return_values[pair] = df.tail(len_df).reset_index(drop=True)
 
     def attach_return_values_to_return_dataframe(
@@ -311,6 +323,7 @@ class FreqaiDataDrawer:
         """
 
         dk.find_features(dataframe)
+        dk.find_labels(dataframe)
 
         full_labels = dk.label_list + dk.unique_class_list
 
@@ -342,7 +355,7 @@ class FreqaiDataDrawer:
         for dir in model_folders:
             result = pattern.match(str(dir.name))
             if result is None:
-                break
+                continue
             coin = result.group(1)
             timestamp = result.group(2)
 
@@ -374,7 +387,27 @@ class FreqaiDataDrawer:
         if self.config.get("freqai", {}).get("purge_old_models", False):
             self.purge_old_models()
 
-    # Functions pulled back from FreqaiDataKitchen because they relied on DataDrawer
+    def save_metadata(self, dk: FreqaiDataKitchen) -> None:
+        """
+        Saves only metadata for backtesting studies if user prefers
+        not to save model data. This saves tremendous amounts of space
+        for users generating huge studies.
+        This is only active when `save_backtest_models`: false (not default)
+        """
+        if not dk.data_path.is_dir():
+            dk.data_path.mkdir(parents=True, exist_ok=True)
+
+        save_path = Path(dk.data_path)
+
+        dk.data["data_path"] = str(dk.data_path)
+        dk.data["model_filename"] = str(dk.model_filename)
+        dk.data["training_features_list"] = list(dk.data_dictionary["train_features"].columns)
+        dk.data["label_list"] = dk.label_list
+
+        with open(save_path / f"{dk.model_filename}_metadata.json", "w") as fp:
+            rapidjson.dump(dk.data, fp, default=self.np_encoder, number_mode=rapidjson.NM_NATIVE)
+
+        return
 
     def save_data(self, model: Any, coin: str, dk: FreqaiDataKitchen) -> None:
         """
@@ -400,7 +433,7 @@ class FreqaiDataDrawer:
 
         dk.data["data_path"] = str(dk.data_path)
         dk.data["model_filename"] = str(dk.model_filename)
-        dk.data["training_features_list"] = list(dk.data_dictionary["train_features"].columns)
+        dk.data["training_features_list"] = dk.training_features_list
         dk.data["label_list"] = dk.label_list
         # store the metadata
         with open(save_path / f"{dk.model_filename}_metadata.json", "w") as fp:
@@ -428,6 +461,16 @@ class FreqaiDataDrawer:
 
         return
 
+    def load_metadata(self, dk: FreqaiDataKitchen) -> None:
+        """
+        Load only metadata into datakitchen to increase performance during
+        presaved backtesting (prediction file loading).
+        """
+        with open(dk.data_path / f"{dk.model_filename}_metadata.json", "r") as fp:
+            dk.data = json.load(fp)
+            dk.training_features_list = dk.data["training_features_list"]
+            dk.label_list = dk.data["label_list"]
+
     def load_data(self, coin: str, dk: FreqaiDataKitchen) -> Any:
         """
         loads all data required to make a prediction on a sub-train time range
@@ -477,7 +520,7 @@ class FreqaiDataDrawer:
                 f"Unable to load model, ensure model exists at " f"{dk.data_path} "
             )
 
-        if self.config["freqai"]["feature_parameters"]["principal_component_analysis"]:
+        if self.config["freqai"]["feature_parameters"].get("principal_component_analysis", False):
             dk.pca = cloudpickle.load(
                 open(dk.data_path / f"{dk.model_filename}_pca_object.pkl", "rb")
             )
@@ -573,9 +616,9 @@ class FreqaiDataDrawer:
             pairs = self.freqai_info["feature_parameters"].get(
                 "include_corr_pairlist", []
             )
-
             for tf in self.freqai_info["feature_parameters"].get("include_timeframes"):
-                base_dataframes[tf] = dk.slice_dataframe(timerange, historic_data[pair][tf])
+                base_dataframes[tf] = dk.slice_dataframe(
+                    timerange, historic_data[pair][tf]).reset_index(drop=True)
                 if pairs:
                     for p in pairs:
                         if pair in p:
@@ -584,7 +627,7 @@ class FreqaiDataDrawer:
                             corr_dataframes[p] = {}
                         corr_dataframes[p][tf] = dk.slice_dataframe(
                             timerange, historic_data[p][tf]
-                        )
+                        ).reset_index(drop=True)
 
         return corr_dataframes, base_dataframes
 

freqtrade/freqai/data_kitchen.py

@@ -1,7 +1,8 @@
 import copy
-import datetime
 import logging
 import shutil
+from datetime import datetime, timezone
+from math import cos, sin
 from pathlib import Path
 from typing import Any, Dict, List, Tuple
 
@@ -9,6 +10,7 @@ import numpy as np
 import numpy.typing as npt
 import pandas as pd
 from pandas import DataFrame
+from scipy import stats
 from sklearn import linear_model
 from sklearn.cluster import DBSCAN
 from sklearn.metrics.pairwise import pairwise_distances
@@ -16,8 +18,7 @@ from sklearn.model_selection import train_test_split
 from sklearn.neighbors import NearestNeighbors
 
 from freqtrade.configuration import TimeRange
-from freqtrade.data.dataprovider import DataProvider
-from freqtrade.data.history.history_utils import refresh_backtest_ohlcv_data
+from freqtrade.constants import Config
 from freqtrade.exceptions import OperationalException
 from freqtrade.exchange import timeframe_to_seconds
 from freqtrade.strategy.interface import IStrategy
@@ -57,7 +58,7 @@ class FreqaiDataKitchen:
 
     def __init__(
         self,
-        config: Dict[str, Any],
+        config: Config,
         live: bool = False,
         pair: str = "",
     ):
@@ -71,6 +72,8 @@ class FreqaiDataKitchen:
         self.label_list: List = []
         self.training_features_list: List = []
         self.model_filename: str = ""
+        self.backtesting_results_path = Path()
+        self.backtest_predictions_folder: str = "backtesting_predictions"
         self.live = live
         self.pair = pair
 
@@ -96,6 +99,7 @@ class FreqaiDataKitchen:
         self.train_dates: DataFrame = pd.DataFrame()
         self.unique_classes: Dict[str, list] = {}
         self.unique_class_list: list = []
+        self.spice_dataframe: DataFrame = None
 
     def set_paths(
         self,
@@ -131,20 +135,15 @@ class FreqaiDataKitchen:
         """
         feat_dict = self.freqai_config["feature_parameters"]
 
+        if 'shuffle' not in self.freqai_config['data_split_parameters']:
+            self.freqai_config["data_split_parameters"].update({'shuffle': False})
+
         weights: npt.ArrayLike
         if feat_dict.get("weight_factor", 0) > 0:
             weights = self.set_weights_higher_recent(len(filtered_dataframe))
         else:
             weights = np.ones(len(filtered_dataframe))
 
-        if feat_dict.get("stratify_training_data", 0) > 0:
-            stratification = np.zeros(len(filtered_dataframe))
-            for i in range(1, len(stratification)):
-                if i % feat_dict.get("stratify_training_data", 0) == 0:
-                    stratification[i] = 1
-        else:
-            stratification = None
-
         if self.freqai_config.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
             (
                 train_features,
@@ -157,7 +156,6 @@ class FreqaiDataKitchen:
                 filtered_dataframe[: filtered_dataframe.shape[0]],
                 labels,
                 weights,
-                stratify=stratification,
                 **self.config["freqai"]["data_split_parameters"],
             )
         else:
@@ -168,13 +166,21 @@ class FreqaiDataKitchen:
             train_labels = labels
             train_weights = weights
 
-        return self.build_data_dictionary(
-            train_features, test_features, train_labels, test_labels, train_weights, test_weights
-        )
+        # Simplest way to reverse the order of training and test data:
+        if self.freqai_config['feature_parameters'].get('reverse_train_test_order', False):
+            return self.build_data_dictionary(
+                test_features, train_features, test_labels,
+                train_labels, test_weights, train_weights
+                )
+        else:
+            return self.build_data_dictionary(
+                train_features, test_features, train_labels,
+                test_labels, train_weights, test_weights
+            )
 
     def filter_features(
         self,
-        unfiltered_dataframe: DataFrame,
+        unfiltered_df: DataFrame,
         training_feature_list: List,
         label_list: List = list(),
         training_filter: bool = True,
@@ -185,31 +191,35 @@ class FreqaiDataKitchen:
         0s in the prediction dataset. However, prediction dataset do_predict will reflect any
         row that had a NaN and will shield user from that prediction.
         :params:
-        :unfiltered_dataframe: the full dataframe for the present training period
+        :unfiltered_df: the full dataframe for the present training period
         :training_feature_list: list, the training feature list constructed by
         self.build_feature_list() according to user specified parameters in the configuration file.
         :labels: the labels for the dataset
         :training_filter: boolean which lets the function know if it is training data or
         prediction data to be filtered.
         :returns:
-        :filtered_dataframe: dataframe cleaned of NaNs and only containing the user
+        :filtered_df: dataframe cleaned of NaNs and only containing the user
         requested feature set.
         :labels: labels cleaned of NaNs.
         """
-        filtered_dataframe = unfiltered_dataframe.filter(training_feature_list, axis=1)
-        filtered_dataframe = filtered_dataframe.replace([np.inf, -np.inf], np.nan)
+        filtered_df = unfiltered_df.filter(training_feature_list, axis=1)
+        filtered_df = filtered_df.replace([np.inf, -np.inf], np.nan)
 
-        drop_index = pd.isnull(filtered_dataframe).any(1)  # get the rows that have NaNs,
+        drop_index = pd.isnull(filtered_df).any(axis=1)  # get the rows that have NaNs,
         drop_index = drop_index.replace(True, 1).replace(False, 0)  # pep8 requirement.
         if (training_filter):
+            const_cols = list((filtered_df.nunique() == 1).loc[lambda x: x].index)
+            if const_cols:
+                filtered_df = filtered_df.filter(filtered_df.columns.difference(const_cols))
+                logger.warning(f"Removed features {const_cols} with constant values.")
             # we don't care about total row number (total no. datapoints) in training, we only care
             # about removing any row with NaNs
             # if labels has multiple columns (user wants to train multiple modelEs), we detect here
-            labels = unfiltered_dataframe.filter(label_list, axis=1)
-            drop_index_labels = pd.isnull(labels).any(1)
+            labels = unfiltered_df.filter(label_list, axis=1)
+            drop_index_labels = pd.isnull(labels).any(axis=1)
             drop_index_labels = drop_index_labels.replace(True, 1).replace(False, 0)
-            dates = unfiltered_dataframe['date']
-            filtered_dataframe = filtered_dataframe[
+            dates = unfiltered_df['date']
+            filtered_df = filtered_df[
                 (drop_index == 0) & (drop_index_labels == 0)
             ]  # dropping values
             labels = labels[
@@ -219,13 +229,13 @@ class FreqaiDataKitchen:
                 (drop_index == 0) & (drop_index_labels == 0)
             ]
             logger.info(
-                f"dropped {len(unfiltered_dataframe) - len(filtered_dataframe)} training points"
-                f" due to NaNs in populated dataset {len(unfiltered_dataframe)}."
+                f"dropped {len(unfiltered_df) - len(filtered_df)} training points"
+                f" due to NaNs in populated dataset {len(unfiltered_df)}."
             )
-            if (1 - len(filtered_dataframe) / len(unfiltered_dataframe)) > 0.1 and self.live:
-                worst_indicator = str(unfiltered_dataframe.count().idxmin())
+            if (1 - len(filtered_df) / len(unfiltered_df)) > 0.1 and self.live:
+                worst_indicator = str(unfiltered_df.count().idxmin())
                 logger.warning(
-                    f" {(1 - len(filtered_dataframe)/len(unfiltered_dataframe)) * 100:.0f} percent "
+                    f" {(1 - len(filtered_df)/len(unfiltered_df)) * 100:.0f} percent "
                     " of training data dropped due to NaNs, model may perform inconsistent "
                     f"with expectations. Verify {worst_indicator}"
                 )
@@ -234,9 +244,9 @@ class FreqaiDataKitchen:
         else:
             # we are backtesting so we need to preserve row number to send back to strategy,
             # so now we use do_predict to avoid any prediction based on a NaN
-            drop_index = pd.isnull(filtered_dataframe).any(1)
+            drop_index = pd.isnull(filtered_df).any(axis=1)
             self.data["filter_drop_index_prediction"] = drop_index
-            filtered_dataframe.fillna(0, inplace=True)
+            filtered_df.fillna(0, inplace=True)
             # replacing all NaNs with zeros to avoid issues in 'prediction', but any prediction
             # that was based on a single NaN is ultimately protected from buys with do_predict
             drop_index = ~drop_index
@@ -245,11 +255,11 @@ class FreqaiDataKitchen:
                 logger.info(
                     "dropped %s of %s prediction data points due to NaNs.",
                     len(self.do_predict) - self.do_predict.sum(),
-                    len(filtered_dataframe),
+                    len(filtered_df),
                 )
             labels = []
 
-        return filtered_dataframe, labels
+        return filtered_df, labels
 
     def build_data_dictionary(
         self,
@@ -281,6 +291,7 @@ class FreqaiDataKitchen:
         :returns:
         :data_dictionary: updated dictionary with standardized values.
         """
+
         # standardize the data by training stats
         train_max = data_dictionary["train_features"].max()
         train_min = data_dictionary["train_features"].min()
@@ -314,10 +325,24 @@ class FreqaiDataKitchen:
                     - 1
                 )
 
-            self.data[f"{item}_max"] = train_labels_max  # .to_dict()
-            self.data[f"{item}_min"] = train_labels_min  # .to_dict()
+            self.data[f"{item}_max"] = train_labels_max
+            self.data[f"{item}_min"] = train_labels_min
         return data_dictionary
 
+    def normalize_single_dataframe(self, df: DataFrame) -> DataFrame:
+
+        train_max = df.max()
+        train_min = df.min()
+        df = (
+            2 * (df - train_min) / (train_max - train_min) - 1
+        )
+
+        for item in train_max.keys():
+            self.data[item + "_max"] = train_max[item]
+            self.data[item + "_min"] = train_min[item]
+
+        return df
+
     def normalize_data_from_metadata(self, df: DataFrame) -> DataFrame:
         """
         Normalize a set of data using the mean and standard deviation from
@@ -337,7 +362,7 @@ class FreqaiDataKitchen:
 
     def denormalize_labels_from_metadata(self, df: DataFrame) -> DataFrame:
         """
-        Normalize a set of data using the mean and standard deviation from
+        Denormalize a set of data using the mean and standard deviation from
         the associated training data.
         :param df: Dataframe of predictions to be denormalized
         """
@@ -376,7 +401,7 @@ class FreqaiDataKitchen:
         config_timerange = TimeRange.parse_timerange(self.config["timerange"])
         if config_timerange.stopts == 0:
             config_timerange.stopts = int(
-                datetime.datetime.now(tz=datetime.timezone.utc).timestamp()
+                datetime.now(tz=timezone.utc).timestamp()
             )
         timerange_train = copy.deepcopy(full_timerange)
         timerange_backtest = copy.deepcopy(full_timerange)
@@ -393,8 +418,8 @@ class FreqaiDataKitchen:
             timerange_train.stopts = timerange_train.startts + train_period_days
 
             first = False
-            start = datetime.datetime.utcfromtimestamp(timerange_train.startts)
-            stop = datetime.datetime.utcfromtimestamp(timerange_train.stopts)
+            start = datetime.fromtimestamp(timerange_train.startts, tz=timezone.utc)
+            stop = datetime.fromtimestamp(timerange_train.stopts, tz=timezone.utc)
             tr_training_list.append(start.strftime("%Y%m%d") + "-" + stop.strftime("%Y%m%d"))
             tr_training_list_timerange.append(copy.deepcopy(timerange_train))
 
@@ -407,8 +432,8 @@ class FreqaiDataKitchen:
             if timerange_backtest.stopts > config_timerange.stopts:
                 timerange_backtest.stopts = config_timerange.stopts
 
-            start = datetime.datetime.utcfromtimestamp(timerange_backtest.startts)
-            stop = datetime.datetime.utcfromtimestamp(timerange_backtest.stopts)
+            start = datetime.fromtimestamp(timerange_backtest.startts, tz=timezone.utc)
+            stop = datetime.fromtimestamp(timerange_backtest.stopts, tz=timezone.utc)
             tr_backtesting_list.append(start.strftime("%Y%m%d") + "-" + stop.strftime("%Y%m%d"))
             tr_backtesting_list_timerange.append(copy.deepcopy(timerange_backtest))
 
@@ -428,10 +453,11 @@ class FreqaiDataKitchen:
                    it is sliced down to just the present training period.
         """
 
-        start = datetime.datetime.fromtimestamp(timerange.startts, tz=datetime.timezone.utc)
-        stop = datetime.datetime.fromtimestamp(timerange.stopts, tz=datetime.timezone.utc)
+        start = datetime.fromtimestamp(timerange.startts, tz=timezone.utc)
+        stop = datetime.fromtimestamp(timerange.stopts, tz=timezone.utc)
         df = df.loc[df["date"] >= start, :]
-        df = df.loc[df["date"] <= stop, :]
+        if not self.live:
+            df = df.loc[df["date"] < stop, :]
 
         return df
 
@@ -444,22 +470,23 @@ class FreqaiDataKitchen:
 
         from sklearn.decomposition import PCA  # avoid importing if we dont need it
 
-        n_components = self.data_dictionary["train_features"].shape[1]
-        pca = PCA(n_components=n_components)
+        pca = PCA(0.999)
         pca = pca.fit(self.data_dictionary["train_features"])
-        n_keep_components = np.argmin(pca.explained_variance_ratio_.cumsum() < 0.999)
-        pca2 = PCA(n_components=n_keep_components)
+        n_keep_components = pca.n_components_
         self.data["n_kept_components"] = n_keep_components
-        pca2 = pca2.fit(self.data_dictionary["train_features"])
+        n_components = self.data_dictionary["train_features"].shape[1]
         logger.info("reduced feature dimension by %s", n_components - n_keep_components)
-        logger.info("explained variance %f", np.sum(pca2.explained_variance_ratio_))
-        train_components = pca2.transform(self.data_dictionary["train_features"])
+        logger.info("explained variance %f", np.sum(pca.explained_variance_ratio_))
 
+        train_components = pca.transform(self.data_dictionary["train_features"])
         self.data_dictionary["train_features"] = pd.DataFrame(
             data=train_components,
             columns=["PC" + str(i) for i in range(0, n_keep_components)],
             index=self.data_dictionary["train_features"].index,
         )
+        # normalsing transformed training features
+        self.data_dictionary["train_features"] = self.normalize_single_dataframe(
+            self.data_dictionary["train_features"])
 
         # keeping a copy of the non-transformed features so we can check for errors during
         # model load from disk
@@ -467,15 +494,18 @@ class FreqaiDataKitchen:
         self.training_features_list = self.data_dictionary["train_features"].columns
 
         if self.freqai_config.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
-            test_components = pca2.transform(self.data_dictionary["test_features"])
+            test_components = pca.transform(self.data_dictionary["test_features"])
             self.data_dictionary["test_features"] = pd.DataFrame(
                 data=test_components,
                 columns=["PC" + str(i) for i in range(0, n_keep_components)],
                 index=self.data_dictionary["test_features"].index,
             )
+            # normalise transformed test feature to transformed training features
+            self.data_dictionary["test_features"] = self.normalize_data_from_metadata(
+                self.data_dictionary["test_features"])
 
         self.data["n_kept_components"] = n_keep_components
-        self.pca = pca2
+        self.pca = pca
 
         logger.info(f"PCA reduced total features from  {n_components} to {n_keep_components}")
 
@@ -496,6 +526,9 @@ class FreqaiDataKitchen:
             columns=["PC" + str(i) for i in range(0, self.data["n_kept_components"])],
             index=filtered_dataframe.index,
         )
+        # normalise transformed predictions to transformed training features
+        self.data_dictionary["prediction_features"] = self.normalize_data_from_metadata(
+            self.data_dictionary["prediction_features"])
 
     def compute_distances(self) -> float:
         """
@@ -521,7 +554,6 @@ class FreqaiDataKitchen:
             "outlier_protection_percentage", 30)
         outlier_pct = (dropped_pts.sum() / len(dropped_pts)) * 100
         if outlier_pct >= outlier_protection_pct:
-            self.svm_model = None
             return outlier_pct
         else:
             return 0.0
@@ -571,6 +603,7 @@ class FreqaiDataKitchen:
                         f"SVM detected {outlier_pct:.2f}% of the points as outliers. "
                         f"Keeping original dataset."
                 )
+                self.svm_model = None
                 return
 
             self.data_dictionary["train_features"] = self.data_dictionary["train_features"][
@@ -622,9 +655,9 @@ class FreqaiDataKitchen:
         is an outlier.
         """
 
-        from math import cos, sin
-
         if predict:
+            if not self.data['DBSCAN_eps']:
+                return
             train_ft_df = self.data_dictionary['train_features']
             pred_ft_df = self.data_dictionary['prediction_features']
             num_preds = len(pred_ft_df)
@@ -694,6 +727,7 @@ class FreqaiDataKitchen:
                         f"DBSCAN detected {outlier_pct:.2f}% of the points as outliers. "
                         f"Keeping original dataset."
                 )
+                self.data['DBSCAN_eps'] = 0
                 return
 
             self.data_dictionary['train_features'] = self.data_dictionary['train_features'][
@@ -713,6 +747,126 @@ class FreqaiDataKitchen:
 
         return
 
+    def compute_inlier_metric(self, set_='train') -> None:
+        """
+        Compute inlier metric from backwards distance distributions.
+        This metric defines how well features from a timepoint fit
+        into previous timepoints.
+        """
+
+        def normalise(dataframe: DataFrame, key: str) -> DataFrame:
+            if set_ == 'train':
+                min_value = dataframe.min()
+                max_value = dataframe.max()
+                self.data[f'{key}_min'] = min_value
+                self.data[f'{key}_max'] = max_value
+            else:
+                min_value = self.data[f'{key}_min']
+                max_value = self.data[f'{key}_max']
+            return (dataframe - min_value) / (max_value - min_value)
+
+        no_prev_pts = self.freqai_config["feature_parameters"]["inlier_metric_window"]
+
+        if set_ == 'train':
+            compute_df = copy.deepcopy(self.data_dictionary['train_features'])
+        elif set_ == 'test':
+            compute_df = copy.deepcopy(self.data_dictionary['test_features'])
+        else:
+            compute_df = copy.deepcopy(self.data_dictionary['prediction_features'])
+
+        compute_df_reindexed = compute_df.reindex(
+            index=np.flip(compute_df.index)
+        )
+
+        pairwise = pd.DataFrame(
+            np.triu(
+                pairwise_distances(compute_df_reindexed, n_jobs=self.thread_count)
+            ),
+            columns=compute_df_reindexed.index,
+            index=compute_df_reindexed.index
+        )
+        pairwise = pairwise.round(5)
+
+        column_labels = [
+            '{}{}'.format('d', i) for i in range(1, no_prev_pts + 1)
+        ]
+        distances = pd.DataFrame(
+            columns=column_labels, index=compute_df.index
+        )
+
+        for index in compute_df.index[no_prev_pts:]:
+            current_row = pairwise.loc[[index]]
+            current_row_no_zeros = current_row.loc[
+                :, (current_row != 0).any(axis=0)
+            ]
+            distances.loc[[index]] = current_row_no_zeros.iloc[
+                :, :no_prev_pts
+            ]
+        distances = distances.replace([np.inf, -np.inf], np.nan)
+        drop_index = pd.isnull(distances).any(axis=1)
+        distances = distances[drop_index == 0]
+
+        inliers = pd.DataFrame(index=distances.index)
+        for key in distances.keys():
+            current_distances = distances[key].dropna()
+            current_distances = normalise(current_distances, key)
+            if set_ == 'train':
+                fit_params = stats.weibull_min.fit(current_distances)
+                self.data[f'{key}_fit_params'] = fit_params
+            else:
+                fit_params = self.data[f'{key}_fit_params']
+            quantiles = stats.weibull_min.cdf(current_distances, *fit_params)
+
+            df_inlier = pd.DataFrame(
+                {key: quantiles}, index=distances.index
+            )
+            inliers = pd.concat(
+                [inliers, df_inlier], axis=1
+            )
+
+        inlier_metric = pd.DataFrame(
+            data=inliers.sum(axis=1) / no_prev_pts,
+            columns=['%-inlier_metric'],
+            index=compute_df.index
+        )
+
+        inlier_metric = (2 * (inlier_metric - inlier_metric.min()) /
+                         (inlier_metric.max() - inlier_metric.min()) - 1)
+
+        if set_ in ('train', 'test'):
+            inlier_metric = inlier_metric.iloc[no_prev_pts:]
+            compute_df = compute_df.iloc[no_prev_pts:]
+            self.remove_beginning_points_from_data_dict(set_, no_prev_pts)
+            self.data_dictionary[f'{set_}_features'] = pd.concat(
+                [compute_df, inlier_metric], axis=1)
+        else:
+            self.data_dictionary['prediction_features'] = pd.concat(
+                [compute_df, inlier_metric], axis=1)
+            self.data_dictionary['prediction_features'].fillna(0, inplace=True)
+
+        logger.info('Inlier metric computed and added to features.')
+
+        return None
+
+    def remove_beginning_points_from_data_dict(self, set_='train', no_prev_pts: int = 10):
+        features = self.data_dictionary[f'{set_}_features']
+        weights = self.data_dictionary[f'{set_}_weights']
+        labels = self.data_dictionary[f'{set_}_labels']
+        self.data_dictionary[f'{set_}_weights'] = weights[no_prev_pts:]
+        self.data_dictionary[f'{set_}_features'] = features.iloc[no_prev_pts:]
+        self.data_dictionary[f'{set_}_labels'] = labels.iloc[no_prev_pts:]
+
+    def add_noise_to_training_features(self) -> None:
+        """
+        Add noise to train features to reduce the risk of overfitting.
+        """
+        mu = 0  # no shift
+        sigma = self.freqai_config["feature_parameters"]["noise_standard_deviation"]
+        compute_df = self.data_dictionary['train_features']
+        noise = np.random.normal(mu, sigma, [compute_df.shape[0], compute_df.shape[1]])
+        self.data_dictionary['train_features'] += noise
+        return
+
     def find_features(self, dataframe: DataFrame) -> None:
         """
         Find features in the strategy provided dataframe
@@ -722,11 +876,15 @@ class FreqaiDataKitchen:
         """
         column_names = dataframe.columns
         features = [c for c in column_names if "%" in c]
-        labels = [c for c in column_names if "&" in c]
+
         if not features:
             raise OperationalException("Could not find any features!")
 
         self.training_features_list = features
+
+    def find_labels(self, dataframe: DataFrame) -> None:
+        column_names = dataframe.columns
+        labels = [c for c in column_names if "&" in c]
         self.label_list = labels
 
     def check_if_pred_in_training_spaces(self) -> None:
@@ -751,18 +909,10 @@ class FreqaiDataKitchen:
             0,
         )
 
-        outlier_pct = self.get_outlier_percentage(1 - do_predict)
-        if outlier_pct:
-            logger.warning(
-                    f"DI detected {outlier_pct:.2f}% of the points as outliers. "
-                    f"Keeping original dataset."
-            )
-            return
-
         if (len(do_predict) - do_predict.sum()) > 0:
             logger.info(
                 f"DI tossed {len(do_predict) - do_predict.sum()} predictions for "
-                "being too far from training data"
+                "being too far from training data."
             )
 
         self.do_predict += do_predict
@@ -777,9 +927,10 @@ class FreqaiDataKitchen:
         weights = np.exp(-np.arange(num_weights) / (wfactor * num_weights))[::-1]
         return weights
 
-    def append_predictions(self, predictions: DataFrame, do_predict: npt.ArrayLike) -> None:
+    def get_predictions_to_append(self, predictions: DataFrame,
+                                  do_predict: npt.ArrayLike) -> DataFrame:
         """
-        Append backtest prediction from current backtest period to all previous periods
+        Get backtest prediction from current backtest period
         """
 
         append_df = DataFrame()
@@ -794,13 +945,18 @@ class FreqaiDataKitchen:
         if self.freqai_config["feature_parameters"].get("DI_threshold", 0) > 0:
             append_df["DI_values"] = self.DI_values
 
+        return append_df
+
+    def append_predictions(self, append_df: DataFrame) -> None:
+        """
+        Append backtest prediction from current backtest period to all previous periods
+        """
+
         if self.full_df.empty:
             self.full_df = append_df
         else:
             self.full_df = pd.concat([self.full_df, append_df], axis=0)
 
-        return
-
     def fill_predictions(self, dataframe):
         """
         Back fill values to before the backtesting range so that the dataframe matches size
@@ -816,7 +972,6 @@ class FreqaiDataKitchen:
 
         to_keep = [col for col in dataframe.columns if not col.startswith("&")]
         self.return_dataframe = pd.concat([dataframe[to_keep], self.full_df], axis=1)
-
         self.full_df = DataFrame()
 
         return
@@ -840,14 +995,14 @@ class FreqaiDataKitchen:
                                        "Please indicate the end date of your desired backtesting. "
                                        "timerange.")
             # backtest_timerange.stopts = int(
-            #     datetime.datetime.now(tz=datetime.timezone.utc).timestamp()
+            #     datetime.now(tz=timezone.utc).timestamp()
             # )
 
         backtest_timerange.startts = (
             backtest_timerange.startts - backtest_period_days * SECONDS_IN_DAY
         )
-        start = datetime.datetime.utcfromtimestamp(backtest_timerange.startts)
-        stop = datetime.datetime.utcfromtimestamp(backtest_timerange.stopts)
+        start = datetime.fromtimestamp(backtest_timerange.startts, tz=timezone.utc)
+        stop = datetime.fromtimestamp(backtest_timerange.stopts, tz=timezone.utc)
         full_timerange = start.strftime("%Y%m%d") + "-" + stop.strftime("%Y%m%d")
 
         self.full_path = Path(
@@ -873,7 +1028,7 @@ class FreqaiDataKitchen:
         :return:
             bool = If the model is expired or not.
         """
-        time = datetime.datetime.now(tz=datetime.timezone.utc).timestamp()
+        time = datetime.now(tz=timezone.utc).timestamp()
         elapsed_time = (time - trained_timestamp) / 3600  # hours
         max_time = self.freqai_config.get("expiration_hours", 0)
         if max_time > 0:
@@ -885,7 +1040,7 @@ class FreqaiDataKitchen:
         self, trained_timestamp: int
     ) -> Tuple[bool, TimeRange, TimeRange]:
 
-        time = datetime.datetime.now(tz=datetime.timezone.utc).timestamp()
+        time = datetime.now(tz=timezone.utc).timestamp()
         trained_timerange = TimeRange()
         data_load_timerange = TimeRange()
 
@@ -900,9 +1055,7 @@ class FreqaiDataKitchen:
         # We notice that users like to use exotic indicators where
         # they do not know the required timeperiod. Here we include a factor
         # of safety by multiplying the user considered "max" by 2.
-        max_period = self.freqai_config["feature_parameters"].get(
-            "indicator_max_period_candles", 20
-        ) * 2
+        max_period = self.config.get('startup_candle_count', 20) * 2
         additional_seconds = max_period * max_tf_seconds
 
         if trained_timestamp != 0:
@@ -948,31 +1101,6 @@ class FreqaiDataKitchen:
 
         self.model_filename = f"cb_{coin.lower()}_{int(trained_timerange.stopts)}"
 
-    def download_all_data_for_training(self, timerange: TimeRange, dp: DataProvider) -> None:
-        """
-        Called only once upon start of bot to download the necessary data for
-        populating indicators and training the model.
-        :param timerange: TimeRange = The full data timerange for populating the indicators
-                                      and training the model.
-        :param dp: DataProvider instance attached to the strategy
-        """
-        new_pairs_days = int((timerange.stopts - timerange.startts) / SECONDS_IN_DAY)
-        if not dp._exchange:
-            # Not realistic - this is only called in live mode.
-            raise OperationalException("Dataprovider did not have an exchange attached.")
-        refresh_backtest_ohlcv_data(
-            dp._exchange,
-            pairs=self.all_pairs,
-            timeframes=self.freqai_config["feature_parameters"].get("include_timeframes"),
-            datadir=self.config["datadir"],
-            timerange=timerange,
-            new_pairs_days=new_pairs_days,
-            erase=False,
-            data_format=self.config.get("dataformat_ohlcv", "json"),
-            trading_mode=self.config.get("trading_mode", "spot"),
-            prepend=self.config.get("prepend_data", False),
-        )
-
     def set_all_pairs(self) -> None:
 
         self.all_pairs = copy.deepcopy(
@@ -1077,7 +1205,8 @@ class FreqaiDataKitchen:
 
     def get_unique_classes_from_labels(self, dataframe: DataFrame) -> None:
 
-        self.find_features(dataframe)
+        # self.find_features(dataframe)
+        self.find_labels(dataframe)
 
         for key in self.label_list:
             if dataframe[key].dtype == object:
@@ -1086,3 +1215,56 @@ class FreqaiDataKitchen:
         if self.unique_classes:
             for label in self.unique_classes:
                 self.unique_class_list += list(self.unique_classes[label])
+
+    def save_backtesting_prediction(
+        self, append_df: DataFrame
+    ) -> None:
+        """
+        Save prediction dataframe from backtesting to h5 file format
+        :param append_df: dataframe for backtesting period
+        """
+        full_predictions_folder = Path(self.full_path / self.backtest_predictions_folder)
+        if not full_predictions_folder.is_dir():
+            full_predictions_folder.mkdir(parents=True, exist_ok=True)
+
+        append_df.to_hdf(self.backtesting_results_path, key='append_df', mode='w')
+
+    def get_backtesting_prediction(
+        self
+    ) -> DataFrame:
+        """
+        Get prediction dataframe from h5 file format
+        """
+        append_df = pd.read_hdf(self.backtesting_results_path)
+        return append_df
+
+    def check_if_backtest_prediction_exists(
+        self
+    ) -> bool:
+        """
+        Check if a backtesting prediction already exists
+        :param dk: FreqaiDataKitchen
+        :return:
+        :boolean: whether the prediction file exists or not.
+        """
+        path_to_predictionfile = Path(self.full_path /
+                                      self.backtest_predictions_folder /
+                                      f"{self.model_filename}_prediction.h5")
+        self.backtesting_results_path = path_to_predictionfile
+
+        file_exists = path_to_predictionfile.is_file()
+        if file_exists:
+            logger.info(f"Found backtesting prediction file at {path_to_predictionfile}")
+        else:
+            logger.info(
+                f"Could not find backtesting prediction file at {path_to_predictionfile}"
+            )
+        return file_exists
+
+    def spice_extractor(self, indicator: str, dataframe: DataFrame) -> npt.NDArray:
+        if indicator in dataframe.columns:
+            return np.array(dataframe[indicator])
+        else:
+            logger.warning(f'User asked spice_rack for {indicator}, '
+                           f'but it is not available. Returning 0s')
+            return np.zeros(len(dataframe.index))

freqtrade/freqai/freqai_interface.py

@@ -1,13 +1,13 @@
-# import contextlib
-import datetime
 import logging
 import shutil
 import threading
 import time
 from abc import ABC, abstractmethod
+from collections import deque
+from datetime import datetime, timezone
 from pathlib import Path
 from threading import Lock
-from typing import Any, Dict, Tuple
+from typing import Any, Dict, List, Tuple
 
 import numpy as np
 import pandas as pd
@@ -15,11 +15,13 @@ from numpy.typing import NDArray
 from pandas import DataFrame
 
 from freqtrade.configuration import TimeRange
+from freqtrade.constants import DATETIME_PRINT_FORMAT, Config
 from freqtrade.enums import RunMode
 from freqtrade.exceptions import OperationalException
 from freqtrade.exchange import timeframe_to_seconds
 from freqtrade.freqai.data_drawer import FreqaiDataDrawer
 from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
+from freqtrade.freqai.utils import plot_feature_importance
 from freqtrade.strategy.interface import IStrategy
 
 
@@ -27,13 +29,6 @@ pd.options.mode.chained_assignment = None
 logger = logging.getLogger(__name__)
 
 
-def threaded(fn):
-    def wrapper(*args, **kwargs):
-        threading.Thread(target=fn, args=args, kwargs=kwargs).start()
-
-    return wrapper
-
-
 class IFreqaiModel(ABC):
     """
     Class containing all tools for training and prediction in the strategy.
@@ -57,7 +52,7 @@ class IFreqaiModel(ABC):
     Juha Nykänen @suikula, Wagner Costa @wagnercosta, Johan Vlugt @Jooopieeert
     """
 
-    def __init__(self, config: Dict[str, Any]) -> None:
+    def __init__(self, config: Config) -> None:
 
         self.config = config
         self.assert_config(self.config)
@@ -66,22 +61,28 @@ class IFreqaiModel(ABC):
             "data_split_parameters", {})
         self.model_training_parameters: Dict[str, Any] = config.get("freqai", {}).get(
             "model_training_parameters", {})
-        self.feature_parameters = config.get("freqai", {}).get("feature_parameters")
         self.retrain = False
         self.first = True
         self.set_full_path()
         self.follow_mode: bool = self.freqai_info.get("follow_mode", False)
+        self.save_backtest_models: bool = self.freqai_info.get("save_backtest_models", True)
+        if self.save_backtest_models:
+            logger.info('Backtesting module configured to save all models.')
         self.dd = FreqaiDataDrawer(Path(self.full_path), self.config, self.follow_mode)
         self.identifier: str = self.freqai_info.get("identifier", "no_id_provided")
         self.scanning = False
+        self.ft_params = self.freqai_info["feature_parameters"]
         self.keras: bool = self.freqai_info.get("keras", False)
-        if self.keras and self.freqai_info.get("feature_parameters", {}).get("DI_threshold", 0):
-            self.freqai_info["feature_parameters"]["DI_threshold"] = 0
+        if self.keras and self.ft_params.get("DI_threshold", 0):
+            self.ft_params["DI_threshold"] = 0
             logger.warning("DI threshold is not configured for Keras models yet. Deactivating.")
         self.CONV_WIDTH = self.freqai_info.get("conv_width", 2)
+        if self.ft_params.get("inlier_metric_window", 0):
+            self.CONV_WIDTH = self.ft_params.get("inlier_metric_window", 0) * 2
         self.pair_it = 0
         self.pair_it_train = 0
         self.total_pairs = len(self.config.get("exchange", {}).get("pair_whitelist"))
+        self.train_queue = self._set_train_queue()
         self.last_trade_database_summary: DataFrame = {}
         self.current_trade_database_summary: DataFrame = {}
         self.analysis_lock = Lock()
@@ -90,8 +91,19 @@ class IFreqaiModel(ABC):
         self.begin_time: float = 0
         self.begin_time_train: float = 0
         self.base_tf_seconds = timeframe_to_seconds(self.config['timeframe'])
+        self.continual_learning = self.freqai_info.get('continual_learning', False)
+        self.plot_features = self.ft_params.get("plot_feature_importances", 0)
+        self.spice_rack_open: bool = False
+        self._threads: List[threading.Thread] = []
+        self._stop_event = threading.Event()
 
-    def assert_config(self, config: Dict[str, Any]) -> None:
+    def __getstate__(self):
+        """
+        Return an empty state to be pickled in hyperopt
+        """
+        return ({})
+
+    def assert_config(self, config: Config) -> None:
 
         if not config.get("freqai", {}):
             raise OperationalException("No freqai parameters found in configuration file.")
@@ -124,14 +136,13 @@ class IFreqaiModel(ABC):
         elif not self.follow_mode:
             self.dk = FreqaiDataKitchen(self.config, self.live, metadata["pair"])
             logger.info(f"Training {len(self.dk.training_timeranges)} timeranges")
-            with self.analysis_lock:
-                dataframe = self.dk.use_strategy_to_populate_indicators(
-                    strategy, prediction_dataframe=dataframe, pair=metadata["pair"]
-                )
+            dataframe = self.dk.use_strategy_to_populate_indicators(
+                strategy, prediction_dataframe=dataframe, pair=metadata["pair"]
+            )
             dk = self.start_backtesting(dataframe, metadata, self.dk)
 
         dataframe = dk.remove_features_from_df(dk.return_dataframe)
-        self.clean_up()
+        # self.clean_up()
         if self.live:
             self.inference_timer('stop')
         return dataframe
@@ -145,39 +156,70 @@ class IFreqaiModel(ABC):
         self.model = None
         self.dk = None
 
-    @threaded
-    def start_scanning(self, strategy: IStrategy) -> None:
+    def shutdown(self):
+        """
+        Cleans up threads on Shutdown, set stop event. Join threads to wait
+        for current training iteration.
+        """
+        logger.info("Stopping FreqAI")
+        self._stop_event.set()
+
+        logger.info("Waiting on Training iteration")
+        for _thread in self._threads:
+            _thread.join()
+
+    def start_scanning(self, *args, **kwargs) -> None:
+        """
+        Start `self._start_scanning` in a separate thread
+        """
+        _thread = threading.Thread(target=self._start_scanning, args=args, kwargs=kwargs)
+        self._threads.append(_thread)
+        _thread.start()
+
+    def _start_scanning(self, strategy: IStrategy) -> None:
         """
         Function designed to constantly scan pairs for retraining on a separate thread (intracandle)
         to improve model youth. This function is agnostic to data preparation/collection/storage,
         it simply trains on what ever data is available in the self.dd.
         :param strategy: IStrategy = The user defined strategy class
         """
-        while 1:
+        while not self._stop_event.is_set():
             time.sleep(1)
-            for pair in self.config.get("exchange", {}).get("pair_whitelist"):
+            pair = self.train_queue[0]
 
-                (_, trained_timestamp, _) = self.dd.get_pair_dict_info(pair)
+            # ensure pair is avaialble in dp
+            if pair not in strategy.dp.current_whitelist():
+                self.train_queue.popleft()
+                logger.warning(f'{pair} not in current whitelist, removing from train queue.')
+                continue
 
-                if self.dd.pair_dict[pair]["priority"] != 1:
-                    continue
-                dk = FreqaiDataKitchen(self.config, self.live, pair)
-                dk.set_paths(pair, trained_timestamp)
-                (
-                    retrain,
-                    new_trained_timerange,
-                    data_load_timerange,
-                ) = dk.check_if_new_training_required(trained_timestamp)
-                dk.set_paths(pair, new_trained_timerange.stopts)
+            (_, trained_timestamp, _) = self.dd.get_pair_dict_info(pair)
 
-                if retrain:
-                    self.train_timer('start')
-                    self.train_model_in_series(
+            dk = FreqaiDataKitchen(self.config, self.live, pair)
+            dk.set_paths(pair, trained_timestamp)
+            (
+                retrain,
+                new_trained_timerange,
+                data_load_timerange,
+            ) = dk.check_if_new_training_required(trained_timestamp)
+            dk.set_paths(pair, new_trained_timerange.stopts)
+
+            if retrain:
+                self.train_timer('start')
+                try:
+                    self.extract_data_and_train_model(
                         new_trained_timerange, pair, strategy, dk, data_load_timerange
                     )
-                    self.train_timer('stop')
+                except Exception as msg:
+                    logger.warning(f"Training {pair} raised exception {msg.__class__.__name__}. "
+                                   f"Message: {msg}, skipping.")
 
-            self.dd.save_historic_predictions_to_disk()
+                self.train_timer('stop')
+
+                # only rotate the queue after the first has been trained.
+                self.train_queue.rotate(-1)
+
+                self.dd.save_historic_predictions_to_disk()
 
     def start_backtesting(
         self, dataframe: DataFrame, metadata: dict, dk: FreqaiDataKitchen
@@ -204,7 +246,8 @@ class IFreqaiModel(ABC):
         # following tr_train. Both of these windows slide through the
         # entire backtest
         for tr_train, tr_backtest in zip(dk.training_timeranges, dk.backtesting_timeranges):
-            (_, _, _) = self.dd.get_pair_dict_info(metadata["pair"])
+            pair = metadata["pair"]
+            (_, _, _) = self.dd.get_pair_dict_info(pair)
             train_it += 1
             total_trains = len(dk.backtesting_timeranges)
             self.training_timerange = tr_train
@@ -212,40 +255,53 @@ class IFreqaiModel(ABC):
             dataframe_backtest = dk.slice_dataframe(tr_backtest, dataframe)
 
             trained_timestamp = tr_train
-            tr_train_startts_str = datetime.datetime.utcfromtimestamp(tr_train.startts).strftime(
-                "%Y-%m-%d %H:%M:%S"
-            )
-            tr_train_stopts_str = datetime.datetime.utcfromtimestamp(tr_train.stopts).strftime(
-                "%Y-%m-%d %H:%M:%S"
-            )
+            tr_train_startts_str = datetime.fromtimestamp(
+                                                tr_train.startts,
+                                                tz=timezone.utc).strftime(DATETIME_PRINT_FORMAT)
+            tr_train_stopts_str = datetime.fromtimestamp(
+                                                tr_train.stopts,
+                                                tz=timezone.utc).strftime(DATETIME_PRINT_FORMAT)
             logger.info(
-                f"Training {metadata['pair']}, {self.pair_it}/{self.total_pairs} pairs"
+                f"Training {pair}, {self.pair_it}/{self.total_pairs} pairs"
                 f" from {tr_train_startts_str} to {tr_train_stopts_str}, {train_it}/{total_trains} "
                 "trains"
             )
 
+            trained_timestamp_int = int(trained_timestamp.stopts)
             dk.data_path = Path(
-                dk.full_path
-                /
-                f"sub-train-{metadata['pair'].split('/')[0]}_{int(trained_timestamp.stopts)}"
+                dk.full_path / f"sub-train-{pair.split('/')[0]}_{trained_timestamp_int}"
                 )
-            if not self.model_exists(
-                metadata["pair"], dk, trained_timestamp=int(trained_timestamp.stopts)
-            ):
+
+            dk.set_new_model_names(pair, trained_timestamp)
+
+            if dk.check_if_backtest_prediction_exists():
+                self.dd.load_metadata(dk)
                 dk.find_features(dataframe_train)
-                self.model = self.train(dataframe_train, metadata["pair"], dk)
-                self.dd.pair_dict[metadata["pair"]]["trained_timestamp"] = int(
-                    trained_timestamp.stopts)
-                dk.set_new_model_names(metadata["pair"], trained_timestamp)
-                self.dd.save_data(self.model, metadata["pair"], dk)
+                self.check_if_feature_list_matches_strategy(dk)
+                append_df = dk.get_backtesting_prediction()
+                dk.append_predictions(append_df)
             else:
-                self.model = self.dd.load_data(metadata["pair"], dk)
+                if not self.model_exists(dk):
+                    dk.find_features(dataframe_train)
+                    dk.find_labels(dataframe_train)
+                    self.model = self.train(dataframe_train, pair, dk)
+                    self.dd.pair_dict[pair]["trained_timestamp"] = int(
+                        trained_timestamp.stopts)
+                    if self.plot_features:
+                        plot_feature_importance(self.model, pair, dk, self.plot_features)
+                    if self.save_backtest_models:
+                        logger.info('Saving backtest model to disk.')
+                        self.dd.save_data(self.model, pair, dk)
+                    else:
+                        logger.info('Saving metadata to disk.')
+                        self.dd.save_metadata(dk)
+                else:
+                    self.model = self.dd.load_data(pair, dk)
 
-            self.check_if_feature_list_matches_strategy(dataframe_train, dk)
-
-            pred_df, do_preds = self.predict(dataframe_backtest, dk)
-
-            dk.append_predictions(pred_df, do_preds)
+                pred_df, do_preds = self.predict(dataframe_backtest, dk)
+                append_df = dk.get_predictions_to_append(pred_df, do_preds)
+                dk.append_predictions(append_df)
+                dk.save_backtesting_prediction(append_df)
 
         dk.fill_predictions(dataframe)
 
@@ -290,14 +346,8 @@ class IFreqaiModel(ABC):
             )
             dk.set_paths(metadata["pair"], new_trained_timerange.stopts)
 
-            # download candle history if it is not already in memory
+            # load candle history into memory if it is not yet.
             if not self.dd.historic_data:
-                logger.info(
-                    "Downloading all training data for all pairs in whitelist and "
-                    "corr_pairlist, this may take a while if you do not have the "
-                    "data saved"
-                )
-                dk.download_all_data_for_training(data_load_timerange, strategy.dp)
                 self.dd.load_all_pair_histories(data_load_timerange, dk)
 
             if not self.scanning:
@@ -326,8 +376,7 @@ class IFreqaiModel(ABC):
             self.dd.return_null_values_to_strategy(dataframe, dk)
             return dk
 
-        # ensure user is feeding the correct indicators to the model
-        self.check_if_feature_list_matches_strategy(dataframe, dk)
+        dk.find_labels(dataframe)
 
         self.build_strategy_return_arrays(dataframe, dk, metadata["pair"], trained_timestamp)
 
@@ -345,7 +394,7 @@ class IFreqaiModel(ABC):
             # allows FreqUI to show full return values.
             pred_df, do_preds = self.predict(dataframe, dk)
             if pair not in self.dd.historic_predictions:
-                self.set_initial_historic_predictions(pred_df, dk, pair)
+                self.set_initial_historic_predictions(pred_df, dk, pair, dataframe)
             self.dd.set_initial_return_values(pair, pred_df)
 
             dk.return_dataframe = self.dd.attach_return_values_to_return_dataframe(pair, dataframe)
@@ -366,13 +415,13 @@ class IFreqaiModel(ABC):
 
         if self.freqai_info.get('fit_live_predictions_candles', 0) and self.live:
             self.fit_live_predictions(dk, pair)
-        self.dd.append_model_predictions(pair, pred_df, do_preds, dk, len(dataframe))
+        self.dd.append_model_predictions(pair, pred_df, do_preds, dk, dataframe)
         dk.return_dataframe = self.dd.attach_return_values_to_return_dataframe(pair, dataframe)
 
         return
 
     def check_if_feature_list_matches_strategy(
-        self, dataframe: DataFrame, dk: FreqaiDataKitchen
+        self, dk: FreqaiDataKitchen
     ) -> None:
         """
         Ensure user is passing the proper feature set if they are reusing an `identifier` pointing
@@ -381,40 +430,49 @@ class IFreqaiModel(ABC):
         :param dk: FreqaiDataKitchen = non-persistent data container/analyzer for
                    current coin/bot loop
         """
-        dk.find_features(dataframe)
+
         if "training_features_list_raw" in dk.data:
             feature_list = dk.data["training_features_list_raw"]
         else:
-            feature_list = dk.training_features_list
+            feature_list = dk.data['training_features_list']
+
         if dk.training_features_list != feature_list:
             raise OperationalException(
                 "Trying to access pretrained model with `identifier` "
                 "but found different features furnished by current strategy."
                 "Change `identifier` to train from scratch, or ensure the"
                 "strategy is furnishing the same features as the pretrained"
-                "model"
+                "model. In case of --strategy-list, please be aware that FreqAI "
+                "requires all strategies to maintain identical "
+                "populate_any_indicator() functions"
             )
 
     def data_cleaning_train(self, dk: FreqaiDataKitchen) -> None:
         """
-        Base data cleaning method for train
-        Any function inside this method should drop training data points from the filtered_dataframe
-        based on user decided logic. See FreqaiDataKitchen::use_SVM_to_remove_outliers() for an
-        example of how outlier data points are dropped from the dataframe used for training.
+        Base data cleaning method for train.
+        Functions here improve/modify the input data by identifying outliers,
+        computing additional metrics, adding noise, reducing dimensionality etc.
         """
 
-        if self.freqai_info["feature_parameters"].get(
+        ft_params = self.freqai_info["feature_parameters"]
+
+        if ft_params.get('inlier_metric_window', 0):
+            dk.compute_inlier_metric(set_='train')
+            if self.freqai_info["data_split_parameters"]["test_size"] > 0:
+                dk.compute_inlier_metric(set_='test')
+
+        if ft_params.get(
             "principal_component_analysis", False
         ):
             dk.principal_component_analysis()
 
-        if self.freqai_info["feature_parameters"].get("use_SVM_to_remove_outliers", False):
+        if ft_params.get("use_SVM_to_remove_outliers", False):
             dk.use_SVM_to_remove_outliers(predict=False)
 
-        if self.freqai_info["feature_parameters"].get("DI_threshold", 0):
+        if ft_params.get("DI_threshold", 0):
             dk.data["avg_mean_dist"] = dk.compute_distances()
 
-        if self.freqai_info["feature_parameters"].get("use_DBSCAN_to_remove_outliers", False):
+        if ft_params.get("use_DBSCAN_to_remove_outliers", False):
             if dk.pair in self.dd.old_DBSCAN_eps:
                 eps = self.dd.old_DBSCAN_eps[dk.pair]
             else:
@@ -422,39 +480,37 @@ class IFreqaiModel(ABC):
             dk.use_DBSCAN_to_remove_outliers(predict=False, eps=eps)
             self.dd.old_DBSCAN_eps[dk.pair] = dk.data['DBSCAN_eps']
 
-    def data_cleaning_predict(self, dk: FreqaiDataKitchen, dataframe: DataFrame) -> None:
+        if self.freqai_info["feature_parameters"].get('noise_standard_deviation', 0):
+            dk.add_noise_to_training_features()
+
+    def data_cleaning_predict(self, dk: FreqaiDataKitchen) -> None:
         """
         Base data cleaning method for predict.
-        These functions each modify dk.do_predict, which is a dataframe with equal length
-        to the number of candles coming from and returning to the strategy. Inside do_predict,
-         1 allows prediction and < 0 signals to the strategy that the model is not confident in
-         the prediction.
-         See FreqaiDataKitchen::remove_outliers() for an example
-        of how the do_predict vector is modified. do_predict is ultimately passed back to strategy
-        for buy signals.
+        Functions here are complementary to the functions of data_cleaning_train.
         """
-        if self.freqai_info["feature_parameters"].get(
+        ft_params = self.freqai_info["feature_parameters"]
+
+        # ensure user is feeding the correct indicators to the model
+        self.check_if_feature_list_matches_strategy(dk)
+
+        if ft_params.get('inlier_metric_window', 0):
+            dk.compute_inlier_metric(set_='predict')
+
+        if ft_params.get(
             "principal_component_analysis", False
         ):
-            dk.pca_transform(dataframe)
+            dk.pca_transform(dk.data_dictionary['prediction_features'])
 
-        if self.freqai_info["feature_parameters"].get("use_SVM_to_remove_outliers", False):
+        if ft_params.get("use_SVM_to_remove_outliers", False):
             dk.use_SVM_to_remove_outliers(predict=True)
 
-        if self.freqai_info["feature_parameters"].get("DI_threshold", 0):
+        if ft_params.get("DI_threshold", 0):
             dk.check_if_pred_in_training_spaces()
 
-        if self.freqai_info["feature_parameters"].get("use_DBSCAN_to_remove_outliers", False):
+        if ft_params.get("use_DBSCAN_to_remove_outliers", False):
             dk.use_DBSCAN_to_remove_outliers(predict=True)
 
-    def model_exists(
-        self,
-        pair: str,
-        dk: FreqaiDataKitchen,
-        trained_timestamp: int = None,
-        model_filename: str = "",
-        scanning: bool = False,
-    ) -> bool:
+    def model_exists(self, dk: FreqaiDataKitchen) -> bool:
         """
         Given a pair and path, check if a model already exists
         :param pair: pair e.g. BTC/USD
@@ -462,16 +518,11 @@ class IFreqaiModel(ABC):
         :return:
         :boolean: whether the model file exists or not.
         """
-        coin, _ = pair.split("/")
-
-        if not self.live:
-            dk.model_filename = model_filename = f"cb_{coin.lower()}_{trained_timestamp}"
-
-        path_to_modelfile = Path(dk.data_path / f"{model_filename}_model.joblib")
+        path_to_modelfile = Path(dk.data_path / f"{dk.model_filename}_model.joblib")
         file_exists = path_to_modelfile.is_file()
-        if file_exists and not scanning:
+        if file_exists:
             logger.info("Found model at %s", dk.data_path / dk.model_filename)
-        elif not scanning:
+        else:
             logger.info("Could not find model at %s", dk.data_path / dk.model_filename)
         return file_exists
 
@@ -485,7 +536,7 @@ class IFreqaiModel(ABC):
             Path(self.full_path, Path(self.config["config_files"][0]).name),
         )
 
-    def train_model_in_series(
+    def extract_data_and_train_model(
         self,
         new_trained_timerange: TimeRange,
         pair: str,
@@ -518,21 +569,22 @@ class IFreqaiModel(ABC):
 
         # find the features indicated by strategy and store in datakitchen
         dk.find_features(unfiltered_dataframe)
+        dk.find_labels(unfiltered_dataframe)
 
         model = self.train(unfiltered_dataframe, pair, dk)
 
         self.dd.pair_dict[pair]["trained_timestamp"] = new_trained_timerange.stopts
         dk.set_new_model_names(pair, new_trained_timerange)
-        self.dd.pair_dict[pair]["first"] = False
-        if self.dd.pair_dict[pair]["priority"] == 1 and self.scanning:
-            self.dd.pair_to_end_of_training_queue(pair)
         self.dd.save_data(model, pair, dk)
 
+        if self.plot_features:
+            plot_feature_importance(model, pair, dk, self.plot_features)
+
         if self.freqai_info.get("purge_old_models", False):
             self.dd.purge_old_models()
 
     def set_initial_historic_predictions(
-        self, pred_df: DataFrame, dk: FreqaiDataKitchen, pair: str
+        self, pred_df: DataFrame, dk: FreqaiDataKitchen, pair: str, strat_df: DataFrame
     ) -> None:
         """
         This function is called only if the datadrawer failed to load an
@@ -575,9 +627,12 @@ class IFreqaiModel(ABC):
         for return_str in dk.data['extra_returns_per_train']:
             hist_preds_df[return_str] = 0
 
+        hist_preds_df['close_price'] = strat_df['close']
+        hist_preds_df['date_pred'] = strat_df['date']
+
         # # for keras type models, the conv_window needs to be prepended so
         # # viewing is correct in frequi
-        if self.freqai_info.get('keras', False):
+        if self.freqai_info.get('keras', False) or self.ft_params.get('inlier_metric_window', 0):
             n_lost_points = self.freqai_info.get('conv_width', 2)
             zeros_df = DataFrame(np.zeros((n_lost_points, len(hist_preds_df.columns))),
                                  columns=hist_preds_df.columns)
@@ -619,8 +674,8 @@ class IFreqaiModel(ABC):
                 logger.info(
                     f'Total time spent inferencing pairlist {self.inference_time:.2f} seconds')
                 if self.inference_time > 0.25 * self.base_tf_seconds:
-                    logger.warning('Inference took over 25/% of the candle time. Reduce pairlist to'
-                                   ' avoid blinding open trades and degrading performance.')
+                    logger.warning("Inference took over 25% of the candle time. Reduce pairlist to"
+                                   " avoid blinding open trades and degrading performance.")
                 self.pair_it = 0
                 self.inference_time = 0
         return
@@ -643,21 +698,68 @@ class IFreqaiModel(ABC):
                 self.train_time = 0
         return
 
+    def get_init_model(self, pair: str) -> Any:
+        if pair not in self.dd.model_dictionary or not self.continual_learning:
+            init_model = None
+        else:
+            init_model = self.dd.model_dictionary[pair]
+
+        return init_model
+
+    def _set_train_queue(self):
+        """
+        Sets train queue from existing train timestamps if they exist
+        otherwise it sets the train queue based on the provided whitelist.
+        """
+        current_pairlist = self.config.get("exchange", {}).get("pair_whitelist")
+        if not self.dd.pair_dict:
+            logger.info('Set fresh train queue from whitelist. '
+                        f'Queue: {current_pairlist}')
+            return deque(current_pairlist)
+
+        best_queue = deque()
+
+        pair_dict_sorted = sorted(self.dd.pair_dict.items(),
+                                  key=lambda k: k[1]['trained_timestamp'])
+        for pair in pair_dict_sorted:
+            if pair[0] in current_pairlist:
+                best_queue.append(pair[0])
+        for pair in current_pairlist:
+            if pair not in best_queue:
+                best_queue.appendleft(pair)
+
+        logger.info('Set existing queue from trained timestamps. '
+                    f'Best approximation queue: {best_queue}')
+        return best_queue
+
+    def spice_rack(self, indicator: str, dataframe: DataFrame,
+                   metadata: dict, strategy: IStrategy) -> NDArray:
+        if not self.spice_rack_open:
+            dataframe = self.start(dataframe, metadata, strategy)
+            self.dk.spice_dataframe = dataframe
+            self.spice_rack_open = True
+            return self.dk.spice_extractor(indicator, dataframe)
+        else:
+            return self.dk.spice_extractor(indicator, self.dk.spice_dataframe)
+
+    def close_spice_rack(self):
+        self.spice_rack_open = False
     # Following methods which are overridden by user made prediction models.
     # See freqai/prediction_models/CatboostPredictionModel.py for an example.
 
     @abstractmethod
-    def train(self, unfiltered_dataframe: DataFrame, pair: str, dk: FreqaiDataKitchen) -> Any:
+    def train(self, unfiltered_df: DataFrame, pair: str,
+              dk: FreqaiDataKitchen, **kwargs) -> Any:
         """
         Filter the training data and train a model to it. Train makes heavy use of the datahandler
         for storing, saving, loading, and analyzing the data.
-        :param unfiltered_dataframe: Full dataframe for the current training period
+        :param unfiltered_df: Full dataframe for the current training period
         :param metadata: pair metadata from strategy.
         :return: Trained model which can be used to inference (self.predict)
         """
 
     @abstractmethod
-    def fit(self, data_dictionary: Dict[str, Any]) -> Any:
+    def fit(self, data_dictionary: Dict[str, Any], dk: FreqaiDataKitchen, **kwargs) -> Any:
         """
         Most regressors use the same function names and arguments e.g. user
         can drop in LGBMRegressor in place of CatBoostRegressor and all data
@@ -670,11 +772,11 @@ class IFreqaiModel(ABC):
 
     @abstractmethod
     def predict(
-        self, dataframe: DataFrame, dk: FreqaiDataKitchen, first: bool = True
+        self, unfiltered_df: DataFrame, dk: FreqaiDataKitchen, **kwargs
     ) -> Tuple[DataFrame, NDArray[np.int_]]:
         """
         Filter the prediction features data and predict with it.
-        :param unfiltered_dataframe: Full dataframe for the current backtest period.
+        :param unfiltered_df: Full dataframe for the current backtest period.
         :param dk: FreqaiDataKitchen = Data management/analysis tool associated to present pair only
         :param first: boolean = whether this is the first prediction or not.
         :return:

freqtrade/freqai/prediction_models/CatboostClassifier.py

@@ -3,7 +3,8 @@ from typing import Any, Dict
 
 from catboost import CatBoostClassifier, Pool
 
-from freqtrade.freqai.prediction_models.BaseClassifierModel import BaseClassifierModel
+from freqtrade.freqai.base_models.BaseClassifierModel import BaseClassifierModel
+from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
 
 
 logger = logging.getLogger(__name__)
@@ -16,7 +17,7 @@ class CatboostClassifier(BaseClassifierModel):
     has its own DataHandler where data is held, saved, loaded, and managed.
     """
 
-    def fit(self, data_dictionary: Dict) -> Any:
+    def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
         """
         User sets up the training and test data to fit their desired model here
         :params:
@@ -36,6 +37,8 @@ class CatboostClassifier(BaseClassifierModel):
             **self.model_training_parameters,
         )
 
-        cbr.fit(train_data)
+        init_model = self.get_init_model(dk.pair)
+
+        cbr.fit(train_data, init_model=init_model)
 
         return cbr

freqtrade/freqai/prediction_models/CatboostRegressor.py

@@ -1,10 +1,10 @@
-import gc
 import logging
 from typing import Any, Dict
 
 from catboost import CatBoostRegressor, Pool
 
-from freqtrade.freqai.prediction_models.BaseRegressionModel import BaseRegressionModel
+from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
+from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
 
 
 logger = logging.getLogger(__name__)
@@ -17,7 +17,7 @@ class CatboostRegressor(BaseRegressionModel):
     has its own DataHandler where data is held, saved, loaded, and managed.
     """
 
-    def fit(self, data_dictionary: Dict) -> Any:
+    def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
         """
         User sets up the training and test data to fit their desired model here
         :param data_dictionary: the dictionary constructed by DataHandler to hold
@@ -38,16 +38,13 @@ class CatboostRegressor(BaseRegressionModel):
                 weight=data_dictionary["test_weights"],
             )
 
+        init_model = self.get_init_model(dk.pair)
+
         model = CatBoostRegressor(
             allow_writing_files=False,
             **self.model_training_parameters,
         )
 
-        model.fit(X=train_data, eval_set=test_data)
-
-        # some evidence that catboost pools have memory leaks:
-        # https://github.com/catboost/catboost/issues/1835
-        del train_data, test_data
-        gc.collect()
+        model.fit(X=train_data, eval_set=test_data, init_model=init_model)
 
         return model

freqtrade/freqai/prediction_models/CatboostRegressorMultiTarget.py

@@ -1,10 +1,11 @@
 import logging
 from typing import Any, Dict
 
-from catboost import CatBoostRegressor  # , Pool
-from sklearn.multioutput import MultiOutputRegressor
+from catboost import CatBoostRegressor, Pool
 
-from freqtrade.freqai.prediction_models.BaseRegressionModel import BaseRegressionModel
+from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
+from freqtrade.freqai.base_models.FreqaiMultiOutputRegressor import FreqaiMultiOutputRegressor
+from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
 
 
 logger = logging.getLogger(__name__)
@@ -17,7 +18,7 @@ class CatboostRegressorMultiTarget(BaseRegressionModel):
     has its own DataHandler where data is held, saved, loaded, and managed.
     """
 
-    def fit(self, data_dictionary: Dict) -> Any:
+    def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
         """
         User sets up the training and test data to fit their desired model here
         :param data_dictionary: the dictionary constructed by DataHandler to hold
@@ -31,14 +32,37 @@ class CatboostRegressorMultiTarget(BaseRegressionModel):
 
         X = data_dictionary["train_features"]
         y = data_dictionary["train_labels"]
-        eval_set = (data_dictionary["test_features"], data_dictionary["test_labels"])
+
         sample_weight = data_dictionary["train_weights"]
 
-        model = MultiOutputRegressor(estimator=cbr)
-        model.fit(X=X, y=y, sample_weight=sample_weight)  # , eval_set=eval_set)
+        eval_sets = [None] * y.shape[1]
 
         if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
-            train_score = model.score(X, y)
-            test_score = model.score(*eval_set)
-            logger.info(f"Train score {train_score}, Test score {test_score}")
+            eval_sets = [None] * data_dictionary['test_labels'].shape[1]
+
+            for i in range(data_dictionary['test_labels'].shape[1]):
+                eval_sets[i] = Pool(
+                    data=data_dictionary["test_features"],
+                    label=data_dictionary["test_labels"].iloc[:, i],
+                    weight=data_dictionary["test_weights"],
+                )
+
+        init_model = self.get_init_model(dk.pair)
+
+        if init_model:
+            init_models = init_model.estimators_
+        else:
+            init_models = [None] * y.shape[1]
+
+        fit_params = []
+        for i in range(len(eval_sets)):
+            fit_params.append(
+                {'eval_set': eval_sets[i],  'init_model': init_models[i]})
+
+        model = FreqaiMultiOutputRegressor(estimator=cbr)
+        thread_training = self.freqai_info.get('multitarget_parallel_training', False)
+        if thread_training:
+            model.n_jobs = y.shape[1]
+        model.fit(X=X, y=y, sample_weight=sample_weight, fit_params=fit_params)
+
         return model

freqtrade/freqai/prediction_models/LightGBMClassifier.py

@@ -3,7 +3,8 @@ from typing import Any, Dict
 
 from lightgbm import LGBMClassifier
 
-from freqtrade.freqai.prediction_models.BaseClassifierModel import BaseClassifierModel
+from freqtrade.freqai.base_models.BaseClassifierModel import BaseClassifierModel
+from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
 
 
 logger = logging.getLogger(__name__)
@@ -16,7 +17,7 @@ class LightGBMClassifier(BaseClassifierModel):
     has its own DataHandler where data is held, saved, loaded, and managed.
     """
 
-    def fit(self, data_dictionary: Dict) -> Any:
+    def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
         """
         User sets up the training and test data to fit their desired model here
         :params:
@@ -35,9 +36,11 @@ class LightGBMClassifier(BaseClassifierModel):
         y = data_dictionary["train_labels"].to_numpy()[:, 0]
         train_weights = data_dictionary["train_weights"]
 
+        init_model = self.get_init_model(dk.pair)
+
         model = LGBMClassifier(**self.model_training_parameters)
 
         model.fit(X=X, y=y, eval_set=eval_set, sample_weight=train_weights,
-                  eval_sample_weight=[test_weights])
+                  eval_sample_weight=[test_weights], init_model=init_model)
 
         return model

freqtrade/freqai/prediction_models/LightGBMRegressor.py

@@ -3,7 +3,8 @@ from typing import Any, Dict
 
 from lightgbm import LGBMRegressor
 
-from freqtrade.freqai.prediction_models.BaseRegressionModel import BaseRegressionModel
+from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
+from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
 
 
 logger = logging.getLogger(__name__)
@@ -16,7 +17,7 @@ class LightGBMRegressor(BaseRegressionModel):
     has its own DataHandler where data is held, saved, loaded, and managed.
     """
 
-    def fit(self, data_dictionary: Dict) -> Any:
+    def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
         """
         Most regressors use the same function names and arguments e.g. user
         can drop in LGBMRegressor in place of CatBoostRegressor and all data
@@ -35,9 +36,11 @@ class LightGBMRegressor(BaseRegressionModel):
         y = data_dictionary["train_labels"]
         train_weights = data_dictionary["train_weights"]
 
+        init_model = self.get_init_model(dk.pair)
+
         model = LGBMRegressor(**self.model_training_parameters)
 
         model.fit(X=X, y=y, eval_set=eval_set, sample_weight=train_weights,
-                  eval_sample_weight=[eval_weights])
+                  eval_sample_weight=[eval_weights], init_model=init_model)
 
         return model

freqtrade/freqai/prediction_models/LightGBMRegressorMultiTarget.py

@@ -2,9 +2,10 @@ import logging
 from typing import Any, Dict
 
 from lightgbm import LGBMRegressor
-from sklearn.multioutput import MultiOutputRegressor
 
-from freqtrade.freqai.prediction_models.BaseRegressionModel import BaseRegressionModel
+from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
+from freqtrade.freqai.base_models.FreqaiMultiOutputRegressor import FreqaiMultiOutputRegressor
+from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
 
 
 logger = logging.getLogger(__name__)
@@ -17,7 +18,7 @@ class LightGBMRegressorMultiTarget(BaseRegressionModel):
     has its own DataHandler where data is held, saved, loaded, and managed.
     """
 
-    def fit(self, data_dictionary: Dict) -> Any:
+    def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
         """
         User sets up the training and test data to fit their desired model here
         :param data_dictionary: the dictionary constructed by DataHandler to hold
@@ -28,12 +29,36 @@ class LightGBMRegressorMultiTarget(BaseRegressionModel):
 
         X = data_dictionary["train_features"]
         y = data_dictionary["train_labels"]
-        eval_set = (data_dictionary["test_features"], data_dictionary["test_labels"])
         sample_weight = data_dictionary["train_weights"]
 
-        model = MultiOutputRegressor(estimator=lgb)
-        model.fit(X=X, y=y, sample_weight=sample_weight)  # , eval_set=eval_set)
-        train_score = model.score(X, y)
-        test_score = model.score(*eval_set)
-        logger.info(f"Train score {train_score}, Test score {test_score}")
+        eval_weights = None
+        eval_sets = [None] * y.shape[1]
+
+        if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
+            eval_weights = [data_dictionary["test_weights"]]
+            eval_sets = [(None, None)] * data_dictionary['test_labels'].shape[1]  # type: ignore
+            for i in range(data_dictionary['test_labels'].shape[1]):
+                eval_sets[i] = (  # type: ignore
+                    data_dictionary["test_features"],
+                    data_dictionary["test_labels"].iloc[:, i]
+                )
+
+        init_model = self.get_init_model(dk.pair)
+        if init_model:
+            init_models = init_model.estimators_
+        else:
+            init_models = [None] * y.shape[1]
+
+        fit_params = []
+        for i in range(len(eval_sets)):
+            fit_params.append(
+                {'eval_set': eval_sets[i], 'eval_sample_weight': eval_weights,
+                 'init_model': init_models[i]})
+
+        model = FreqaiMultiOutputRegressor(estimator=lgb)
+        thread_training = self.freqai_info.get('multitarget_parallel_training', False)
+        if thread_training:
+            model.n_jobs = y.shape[1]
+        model.fit(X=X, y=y, sample_weight=sample_weight, fit_params=fit_params)
+
         return model

freqtrade/freqai/prediction_models/XGBoostClassifier.py

@@ -0,0 +1,85 @@
+import logging
+from typing import Any, Dict, Tuple
+
+import numpy as np
+import numpy.typing as npt
+import pandas as pd
+from pandas import DataFrame
+from pandas.api.types import is_integer_dtype
+from sklearn.preprocessing import LabelEncoder
+from xgboost import XGBClassifier
+
+from freqtrade.freqai.base_models.BaseClassifierModel import BaseClassifierModel
+from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
+
+
+logger = logging.getLogger(__name__)
+
+
+class XGBoostClassifier(BaseClassifierModel):
+    """
+    User created prediction model. The class needs to override three necessary
+    functions, predict(), train(), fit(). The class inherits ModelHandler which
+    has its own DataHandler where data is held, saved, loaded, and managed.
+    """
+
+    def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
+        """
+        User sets up the training and test data to fit their desired model here
+        :params:
+        :data_dictionary: the dictionary constructed by DataHandler to hold
+        all the training and test data/labels.
+        """
+
+        X = data_dictionary["train_features"].to_numpy()
+        y = data_dictionary["train_labels"].to_numpy()[:, 0]
+
+        le = LabelEncoder()
+        if not is_integer_dtype(y):
+            y = pd.Series(le.fit_transform(y), dtype="int64")
+
+        if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) == 0:
+            eval_set = None
+        else:
+            test_features = data_dictionary["test_features"].to_numpy()
+            test_labels = data_dictionary["test_labels"].to_numpy()[:, 0]
+
+            if not is_integer_dtype(test_labels):
+                test_labels = pd.Series(le.transform(test_labels), dtype="int64")
+
+            eval_set = [(test_features, test_labels)]
+
+        train_weights = data_dictionary["train_weights"]
+
+        init_model = self.get_init_model(dk.pair)
+
+        model = XGBClassifier(**self.model_training_parameters)
+
+        model.fit(X=X, y=y, eval_set=eval_set, sample_weight=train_weights,
+                  xgb_model=init_model)
+
+        return model
+
+    def predict(
+        self, unfiltered_df: DataFrame, dk: FreqaiDataKitchen, **kwargs
+    ) -> Tuple[DataFrame, npt.NDArray[np.int_]]:
+        """
+        Filter the prediction features data and predict with it.
+        :param: unfiltered_df: Full dataframe for the current backtest period.
+        :return:
+        :pred_df: dataframe containing the predictions
+        :do_predict: np.array of 1s and 0s to indicate places where freqai needed to remove
+        data (NaNs) or felt uncertain about data (PCA and DI index)
+        """
+
+        (pred_df, dk.do_predict) = super().predict(unfiltered_df, dk, **kwargs)
+
+        le = LabelEncoder()
+        label = dk.label_list[0]
+        labels_before = list(dk.data['labels_std'].keys())
+        labels_after = le.fit_transform(labels_before).tolist()
+        pred_df[label] = le.inverse_transform(pred_df[label])
+        pred_df = pred_df.rename(
+            columns={labels_after[i]: labels_before[i] for i in range(len(labels_before))})
+
+        return (pred_df, dk.do_predict)

freqtrade/freqai/prediction_models/XGBoostRegressor.py

@@ -0,0 +1,45 @@
+import logging
+from typing import Any, Dict
+
+from xgboost import XGBRegressor
+
+from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
+from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
+
+
+logger = logging.getLogger(__name__)
+
+
+class XGBoostRegressor(BaseRegressionModel):
+    """
+    User created prediction model. The class needs to override three necessary
+    functions, predict(), train(), fit(). The class inherits ModelHandler which
+    has its own DataHandler where data is held, saved, loaded, and managed.
+    """
+
+    def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
+        """
+        User sets up the training and test data to fit their desired model here
+        :param data_dictionary: the dictionary constructed by DataHandler to hold
+                                all the training and test data/labels.
+        """
+
+        X = data_dictionary["train_features"]
+        y = data_dictionary["train_labels"]
+
+        if self.freqai_info.get("data_split_parameters", {}).get("test_size", 0.1) == 0:
+            eval_set = None
+        else:
+            eval_set = [(data_dictionary["test_features"], data_dictionary["test_labels"])]
+            eval_weights = [data_dictionary['test_weights']]
+
+        sample_weight = data_dictionary["train_weights"]
+
+        xgb_model = self.get_init_model(dk.pair)
+
+        model = XGBRegressor(**self.model_training_parameters)
+
+        model.fit(X=X, y=y, sample_weight=sample_weight, eval_set=eval_set,
+                  sample_weight_eval_set=eval_weights, xgb_model=xgb_model)
+
+        return model

freqtrade/freqai/prediction_models/XGBoostRegressorMultiTarget.py

@@ -0,0 +1,63 @@
+import logging
+from typing import Any, Dict
+
+from xgboost import XGBRegressor
+
+from freqtrade.freqai.base_models.BaseRegressionModel import BaseRegressionModel
+from freqtrade.freqai.base_models.FreqaiMultiOutputRegressor import FreqaiMultiOutputRegressor
+from freqtrade.freqai.data_kitchen import FreqaiDataKitchen
+
+
+logger = logging.getLogger(__name__)
+
+
+class XGBoostRegressorMultiTarget(BaseRegressionModel):
+    """
+    User created prediction model. The class needs to override three necessary
+    functions, predict(), train(), fit(). The class inherits ModelHandler which
+    has its own DataHandler where data is held, saved, loaded, and managed.
+    """
+
+    def fit(self, data_dictionary: Dict, dk: FreqaiDataKitchen, **kwargs) -> Any:
+        """
+        User sets up the training and test data to fit their desired model here
+        :param data_dictionary: the dictionary constructed by DataHandler to hold
+                                all the training and test data/labels.
+        """
+
+        xgb = XGBRegressor(**self.model_training_parameters)
+
+        X = data_dictionary["train_features"]
+        y = data_dictionary["train_labels"]
+        sample_weight = data_dictionary["train_weights"]
+
+        eval_weights = None
+        eval_sets = [None] * y.shape[1]
+
+        if self.freqai_info.get('data_split_parameters', {}).get('test_size', 0.1) != 0:
+            eval_weights = [data_dictionary["test_weights"]]
+            for i in range(data_dictionary['test_labels'].shape[1]):
+                eval_sets[i] = [(  # type: ignore
+                    data_dictionary["test_features"],
+                    data_dictionary["test_labels"].iloc[:, i]
+                )]
+
+        init_model = self.get_init_model(dk.pair)
+        if init_model:
+            init_models = init_model.estimators_
+        else:
+            init_models = [None] * y.shape[1]
+
+        fit_params = []
+        for i in range(len(eval_sets)):
+            fit_params.append(
+                {'eval_set': eval_sets[i], 'sample_weight_eval_set': eval_weights,
+                 'xgb_model': init_models[i]})
+
+        model = FreqaiMultiOutputRegressor(estimator=xgb)
+        thread_training = self.freqai_info.get('multitarget_parallel_training', False)
+        if thread_training:
+            model.n_jobs = y.shape[1]
+        model.fit(X=X, y=y, sample_weight=sample_weight, fit_params=fit_params)
+
+        return model

freqtrade/freqai/spice_rack/lightgbm_config.json

@@ -0,0 +1,37 @@
+{
+
+    "freqai": {
+        "enabled": true,
+        "purge_old_models": true,
+        "train_period_days": 4,
+        "backtest_period_days": 1,
+        "identifier": "spicy-id",
+        "feature_parameters": {
+            "include_timeframes": [
+                "30m",
+                "1h",
+                "4h"
+            ],
+            "include_corr_pairlist": [
+                "BTC/USD",
+                "ETH/USD"
+            ],
+            "label_period_candles": 20,
+            "include_shifted_candles": 2,
+            "DI_threshold": 0.9,
+            "weight_factor": 0.9,
+            "principal_component_analysis": true,
+            "indicator_periods_candles": [
+                10,
+                20
+            ]
+        },
+        "data_split_parameters": {
+            "test_size": 0,
+            "random_state": 1
+        },
+        "model_training_parameters": {
+            "n_estimators": 800
+        }
+    }
+}