Merge branch 'develop' into add-single-precision-freqai

This commit is contained in:
Emre 2022-11-05 19:15:12 +03:00 committed by GitHub
commit 06a2957837
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 30 additions and 6 deletions

View File

@ -19,6 +19,7 @@ Mandatory parameters are marked as **Required** and have to be set in one of the
| `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`. | `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`. | `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`.
| `convert_df_to_float32` | Recast all numeric columns to float32, with the objective of reducing ram/disk usage and decreasing train/inference timing. <br> **Datatype:** Boolean. <br> Default: `False`. | `convert_df_to_float32` | Recast all numeric columns to float32, with the objective of reducing ram/disk usage and decreasing train/inference timing. <br> **Datatype:** Boolean. <br> Default: `False`.
| `write_metrics_to_disk` | Collect train timings, inference timings and cpu usage in json file. <br> **Datatype:** Boolean. <br> Default: `False`
| | **Feature parameters** | | **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. | `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_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).
@ -38,7 +39,6 @@ Mandatory parameters are marked as **Required** and have to be set in one of the
| `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`. | `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`. | `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). | `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).
| `write_metrics_to_disk` | Collect train timings, inference timings and cpu usage in json file. <br> **Datatype:** Boolean. <br> Default: `False`
| | **Data split parameters** | | **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. | `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. | `test_size` | The fraction of data that should be used for testing instead of training. <br> **Datatype:** Positive float < 1.

View File

@ -102,6 +102,11 @@ class IDataHandler(ABC):
:return: (min, max) :return: (min, max)
""" """
data = self._ohlcv_load(pair, timeframe, None, candle_type) data = self._ohlcv_load(pair, timeframe, None, candle_type)
if data.empty:
return (
datetime.fromtimestamp(0, tz=timezone.utc),
datetime.fromtimestamp(0, tz=timezone.utc)
)
return data.iloc[0]['date'].to_pydatetime(), data.iloc[-1]['date'].to_pydatetime() return data.iloc[0]['date'].to_pydatetime(), data.iloc[-1]['date'].to_pydatetime()
@abstractmethod @abstractmethod

View File

@ -1,6 +1,7 @@
# pragma pylint: disable=missing-docstring, protected-access, C0103 # pragma pylint: disable=missing-docstring, protected-access, C0103
import re import re
from datetime import datetime, timezone
from pathlib import Path from pathlib import Path
from unittest.mock import MagicMock from unittest.mock import MagicMock
@ -154,6 +155,23 @@ def test_jsondatahandler_ohlcv_load(testdatadir, caplog):
assert df.columns.equals(df1.columns) assert df.columns.equals(df1.columns)
def test_datahandler_ohlcv_data_min_max(testdatadir):
dh = JsonDataHandler(testdatadir)
min_max = dh.ohlcv_data_min_max('UNITTEST/BTC', '5m', 'spot')
assert len(min_max) == 2
# Empty pair
min_max = dh.ohlcv_data_min_max('UNITTEST/BTC', '8m', 'spot')
assert len(min_max) == 2
assert min_max[0] == datetime.fromtimestamp(0, tz=timezone.utc)
assert min_max[0] == min_max[1]
# Empty pair2
min_max = dh.ohlcv_data_min_max('NOPAIR/XXX', '4m', 'spot')
assert len(min_max) == 2
assert min_max[0] == datetime.fromtimestamp(0, tz=timezone.utc)
assert min_max[0] == min_max[1]
def test_datahandler__check_empty_df(testdatadir, caplog): def test_datahandler__check_empty_df(testdatadir, caplog):
dh = JsonDataHandler(testdatadir) dh = JsonDataHandler(testdatadir)
expected_text = r"Price jump in UNITTEST/USDT, 1h, spot between" expected_text = r"Price jump in UNITTEST/USDT, 1h, spot between"

View File

@ -788,13 +788,14 @@ def test_backtest_one(default_conf, fee, mocker, testdatadir) -> None:
assert len(t['orders']) == 2 assert len(t['orders']) == 2
ln = data_pair.loc[data_pair["date"] == t["open_date"]] ln = data_pair.loc[data_pair["date"] == t["open_date"]]
# Check open trade rate alignes to open rate # Check open trade rate alignes to open rate
assert ln is not None assert not ln.empty
assert round(ln.iloc[0]["open"], 6) == round(t["open_rate"], 6) assert round(ln.iloc[0]["open"], 6) == round(t["open_rate"], 6)
# check close trade rate alignes to close rate or is between high and low # check close trade rate alignes to close rate or is between high and low
ln = data_pair.loc[data_pair["date"] == t["close_date"]] ln1 = data_pair.loc[data_pair["date"] == t["close_date"]]
assert (round(ln.iloc[0]["open"], 6) == round(t["close_rate"], 6) or assert not ln1.empty
round(ln.iloc[0]["low"], 6) < round( assert (round(ln1.iloc[0]["open"], 6) == round(t["close_rate"], 6) or
t["close_rate"], 6) < round(ln.iloc[0]["high"], 6)) round(ln1.iloc[0]["low"], 6) < round(
t["close_rate"], 6) < round(ln1.iloc[0]["high"], 6))
def test_backtest_timedout_entry_orders(default_conf, fee, mocker, testdatadir) -> None: def test_backtest_timedout_entry_orders(default_conf, fee, mocker, testdatadir) -> None: