Merge branch 'develop' into db_keep_orders

docs/requirements-docs.txt

@@ -1,2 +1,2 @@
-mkdocs-material==5.5.11
+mkdocs-material==5.5.12
 mdx_truly_sane_lists==1.2

docs/sql_cheatsheet.md

@@ -46,7 +46,7 @@ sqlite3
 ### Trade table structure
 
 ```sql
-CREATE TABLE trades
+CREATE TABLE trades(
     id INTEGER NOT NULL,
     exchange VARCHAR NOT NULL,
     pair VARCHAR NOT NULL,

docs/strategy-customization.md

@@ -483,6 +483,9 @@ if self.dp:
 ### Complete Data-provider sample
 
 ```python
+from freqtrade.strategy import IStrategy, merge_informative_pair
+from pandas import DataFrame
+
 class SampleStrategy(IStrategy):
     # strategy init stuff...
 
@@ -513,17 +516,12 @@ class SampleStrategy(IStrategy):
         # Get the 14 day rsi
         informative['rsi'] = ta.RSI(informative, timeperiod=14)
 
-        # Rename columns to be unique
-        informative.columns = [f"{col}_{inf_tf}" for col in informative.columns]
-        # Assuming inf_tf = '1d' - then the columns will now be:
-        # date_1d, open_1d, high_1d, low_1d, close_1d, rsi_1d
-
-        # Combine the 2 dataframes
-        # all indicators on the informative sample MUST be calculated before this point
-        dataframe = pd.merge(dataframe, informative, left_on='date', right_on=f'date_{inf_tf}', how='left')
-        # FFill to have the 1d value available in every row throughout the day.
-        # Without this, comparisons would only work once per day.
-        dataframe = dataframe.ffill()
+        # Use the helper function merge_informative_pair to safely merge the pair
+        # Automatically renames the columns and merges a shorter timeframe dataframe and a longer timeframe informative pair
+        # use ffill to have the 1d value available in every row throughout the day.
+        # Without this, comparisons between columns of the original and the informative pair would only work once per day.
+        # Full documentation of this method, see below
+        dataframe = merge_informative_pair(dataframe, informative, self.timeframe, inf_tf, ffill=True)
 
         # Calculate rsi of the original dataframe (5m timeframe)
         dataframe['rsi'] = ta.RSI(dataframe, timeperiod=14)
@@ -547,6 +545,69 @@ class SampleStrategy(IStrategy):
 
 ***
 
+## Helper functions
+
+### *merge_informative_pair()*
+
+This method helps you merge an informative pair to a regular dataframe without lookahead bias.
+It's there to help you merge the dataframe in a safe and consistent way.
+
+Options:
+
+- Rename the columns for you to create unique columns
+- Merge the dataframe without lookahead bias
+- Forward-fill (optional)
+
+All columns of the informative dataframe will be available on the returning dataframe in a renamed fashion:
+
+!!! Example "Column renaming"
+    Assuming `inf_tf = '1d'` the resulting columns will be:
+
+    ``` python
+    'date', 'open', 'high', 'low', 'close', 'rsi'                     # from the original dataframe
+    'date_1d', 'open_1d', 'high_1d', 'low_1d', 'close_1d', 'rsi_1d'   # from the informative dataframe
+    ```
+
+??? Example "Column renaming - 1h"
+    Assuming `inf_tf = '1h'` the resulting columns will be:
+
+    ``` python
+    'date', 'open', 'high', 'low', 'close', 'rsi'                     # from the original dataframe
+    'date_1h', 'open_1h', 'high_1h', 'low_1h', 'close_1h', 'rsi_1h'   # from the informative dataframe 
+    ```
+
+??? Example "Custom implementation"
+    A custom implementation for this is possible, and can be done as follows:
+
+    ``` python
+
+    # Shift date by 1 candle
+    # This is necessary since the data is always the "open date"
+    # and a 15m candle starting at 12:15 should not know the close of the 1h candle from 12:00 to 13:00
+    minutes = timeframe_to_minutes(inf_tf)
+    # Only do this if the timeframes are different:
+    informative['date_merge'] = informative["date"] + pd.to_timedelta(minutes, 'm')
+
+    # Rename columns to be unique
+    informative.columns = [f"{col}_{inf_tf}" for col in informative.columns]
+    # Assuming inf_tf = '1d' - then the columns will now be:
+    # date_1d, open_1d, high_1d, low_1d, close_1d, rsi_1d
+
+    # Combine the 2 dataframes
+    # all indicators on the informative sample MUST be calculated before this point
+    dataframe = pd.merge(dataframe, informative, left_on='date', right_on=f'date_merge_{inf_tf}', how='left')
+    # FFill to have the 1d value available in every row throughout the day.
+    # Without this, comparisons would only work once per day.
+    dataframe = dataframe.ffill()
+
+    ```
+
+!!! Warning "Informative timeframe < timeframe"
+    Using informative timeframes smaller than the dataframe timeframe is not recommended with this method, as it will not use any of the additional information this would provide.
+    To use the more detailed information properly, more advanced methods should be applied (which are out of scope for freqtrade documentation, as it'll depend on the respective need).
+
+***
+
 ## Additional data (Wallets)
 
 The strategy provides access to the `Wallets` object. This contains the current balances on the exchange.

freqtrade/rpc/api_server.py

@@ -17,8 +17,9 @@ from werkzeug.serving import make_server
 
 from freqtrade.__init__ import __version__
 from freqtrade.constants import DATETIME_PRINT_FORMAT
-from freqtrade.rpc.rpc import RPC, RPCException
+from freqtrade.persistence import Trade
 from freqtrade.rpc.fiat_convert import CryptoToFiatConverter
+from freqtrade.rpc.rpc import RPC, RPCException
 
 logger = logging.getLogger(__name__)
 
@@ -70,6 +71,11 @@ def rpc_catch_errors(func: Callable[..., Any]):
     return func_wrapper
 
 
+def shutdown_session(exception=None):
+    # Remove scoped session
+    Trade.session.remove()
+
+
 class ApiServer(RPC):
     """
     This class runs api server and provides rpc.rpc functionality to it
@@ -104,6 +110,8 @@ class ApiServer(RPC):
         self.jwt = JWTManager(self.app)
         self.app.json_encoder = ArrowJSONEncoder
 
+        self.app.teardown_appcontext(shutdown_session)
+
         # Register application handling
         self.register_rest_rpc_urls()
 

freqtrade/strategy/__init__.py

@@ -1 +1,5 @@
-from freqtrade.strategy.interface import IStrategy  # noqa: F401
+# flake8: noqa: F401
+from freqtrade.exchange import (timeframe_to_minutes, timeframe_to_prev_date,
+                                timeframe_to_seconds, timeframe_to_next_date, timeframe_to_msecs)
+from freqtrade.strategy.interface import IStrategy
+from freqtrade.strategy.strategy_helper import merge_informative_pair

freqtrade/strategy/strategy_helper.py

@@ -0,0 +1,48 @@
+import pandas as pd
+from freqtrade.exchange import timeframe_to_minutes
+
+
+def merge_informative_pair(dataframe: pd.DataFrame, informative: pd.DataFrame,
+                           timeframe: str, timeframe_inf: str, ffill: bool = True) -> pd.DataFrame:
+    """
+    Correctly merge informative samples to the original dataframe, avoiding lookahead bias.
+
+    Since dates are candle open dates, merging a 15m candle that starts at 15:00, and a
+    1h candle that starts at 15:00 will result in all candles to know the close at 16:00
+    which they should not know.
+
+    Moves the date of the informative pair by 1 time interval forward.
+    This way, the 14:00 1h candle is merged to 15:00 15m candle, since the 14:00 1h candle is the
+    last candle that's closed at 15:00, 15:15, 15:30 or 15:45.
+
+    Assuming inf_tf = '1d' - then the resulting columns will be:
+    date_1d, open_1d, high_1d, low_1d, close_1d, rsi_1d
+
+    :param dataframe: Original dataframe
+    :param informative: Informative pair, most likely loaded via dp.get_pair_dataframe
+    :param timeframe: Timeframe of the original pair sample.
+    :param timeframe_inf: Timeframe of the informative pair sample.
+    :param ffill: Forwardfill missing values - optional but usually required
+    """
+
+    minutes_inf = timeframe_to_minutes(timeframe_inf)
+    minutes = timeframe_to_minutes(timeframe)
+    if minutes >= minutes_inf:
+        # No need to forwardshift if the timeframes are identical
+        informative['date_merge'] = informative["date"]
+    else:
+        informative['date_merge'] = informative["date"] + pd.to_timedelta(minutes_inf, 'm')
+
+    # Rename columns to be unique
+    informative.columns = [f"{col}_{timeframe_inf}" for col in informative.columns]
+
+    # Combine the 2 dataframes
+    # all indicators on the informative sample MUST be calculated before this point
+    dataframe = pd.merge(dataframe, informative, left_on='date',
+                         right_on=f'date_merge_{timeframe_inf}', how='left')
+    dataframe = dataframe.drop(f'date_merge_{timeframe_inf}', axis=1)
+
+    if ffill:
+        dataframe = dataframe.ffill()
+
+    return dataframe

requirements-common.txt

@@ -1,6 +1,6 @@
 # requirements without requirements installable via conda
 # mainly used for Raspberry pi installs
-ccxt==1.33.72
+ccxt==1.34.11
 SQLAlchemy==1.3.19
 python-telegram-bot==12.8
 arrow==0.16.0
@@ -14,7 +14,7 @@ tabulate==0.8.7
 pycoingecko==1.3.0
 jinja2==2.11.2
 tables==3.6.1
-blosc==1.9.1
+blosc==1.9.2
 
 # find first, C search in arrays
 py_find_1st==1.1.4

requirements-hyperopt.txt

@@ -3,8 +3,8 @@
 
 # Required for hyperopt
 scipy==1.5.2
-scikit-learn==0.23.1
-scikit-optimize==0.7.4
+scikit-learn==0.23.2
+scikit-optimize==0.8.1
 filelock==3.0.12
 joblib==0.16.0
-progressbar2==3.52.1
+progressbar2==3.53.1

requirements.txt

@@ -2,4 +2,4 @@
 -r requirements-common.txt
 
 numpy==1.19.1
-pandas==1.1.1
+pandas==1.1.2

tests/rpc/test_rpc_apiserver.py

@@ -435,7 +435,7 @@ def test_api_logs(botclient):
     assert len(rc.json) == 2
     assert 'logs' in rc.json
     # Using a fixed comparison here would make this test fail!
-    assert rc.json['log_count'] > 10
+    assert rc.json['log_count'] > 1
     assert len(rc.json['logs']) == rc.json['log_count']
 
     assert isinstance(rc.json['logs'][0], list)
@@ -471,6 +471,7 @@ def test_api_edge_disabled(botclient, mocker, ticker, fee, markets):
     assert rc.json == {"error": "Error querying _edge: Edge is not enabled."}
 
 
+@pytest.mark.usefixtures("init_persistence")
 def test_api_profit(botclient, mocker, ticker, fee, markets, limit_buy_order, limit_sell_order):
     ftbot, client = botclient
     patch_get_signal(ftbot, (True, False))
@@ -498,6 +499,7 @@ def test_api_profit(botclient, mocker, ticker, fee, markets, limit_buy_order, li
     assert rc.json['best_pair'] == ''
     assert rc.json['best_rate'] == 0
 
+    trade = Trade.query.first()
     trade.update(limit_sell_order)
 
     trade.close_date = datetime.utcnow()

tests/strategy/test_strategy_helpers.py

@@ -0,0 +1,88 @@
+import pandas as pd
+import numpy as np
+
+from freqtrade.strategy import merge_informative_pair, timeframe_to_minutes
+
+
+def generate_test_data(timeframe: str, size: int):
+    np.random.seed(42)
+    tf_mins = timeframe_to_minutes(timeframe)
+
+    base = np.random.normal(20, 2, size=size)
+
+    date = pd.period_range('2020-07-05', periods=size, freq=f'{tf_mins}min').to_timestamp()
+    df = pd.DataFrame({
+        'date': date,
+        'open': base,
+        'high': base + np.random.normal(2, 1, size=size),
+        'low': base - np.random.normal(2, 1, size=size),
+        'close': base + np.random.normal(0, 1, size=size),
+        'volume': np.random.normal(200, size=size)
+    }
+    )
+    df = df.dropna()
+    return df
+
+
+def test_merge_informative_pair():
+    data = generate_test_data('15m', 40)
+    informative = generate_test_data('1h', 40)
+
+    result = merge_informative_pair(data, informative, '15m', '1h', ffill=True)
+    assert isinstance(result, pd.DataFrame)
+    assert len(result) == len(data)
+    assert 'date' in result.columns
+    assert result['date'].equals(data['date'])
+    assert 'date_1h' in result.columns
+
+    assert 'open' in result.columns
+    assert 'open_1h' in result.columns
+    assert result['open'].equals(data['open'])
+
+    assert 'close' in result.columns
+    assert 'close_1h' in result.columns
+    assert result['close'].equals(data['close'])
+
+    assert 'volume' in result.columns
+    assert 'volume_1h' in result.columns
+    assert result['volume'].equals(data['volume'])
+
+    # First 4 rows are empty
+    assert result.iloc[0]['date_1h'] is pd.NaT
+    assert result.iloc[1]['date_1h'] is pd.NaT
+    assert result.iloc[2]['date_1h'] is pd.NaT
+    assert result.iloc[3]['date_1h'] is pd.NaT
+    # Next 4 rows contain the starting date (0:00)
+    assert result.iloc[4]['date_1h'] == result.iloc[0]['date']
+    assert result.iloc[5]['date_1h'] == result.iloc[0]['date']
+    assert result.iloc[6]['date_1h'] == result.iloc[0]['date']
+    assert result.iloc[7]['date_1h'] == result.iloc[0]['date']
+    # Next 4 rows contain the next Hourly date original date row 4
+    assert result.iloc[8]['date_1h'] == result.iloc[4]['date']
+
+
+def test_merge_informative_pair_same():
+    data = generate_test_data('15m', 40)
+    informative = generate_test_data('15m', 40)
+
+    result = merge_informative_pair(data, informative, '15m', '15m', ffill=True)
+    assert isinstance(result, pd.DataFrame)
+    assert len(result) == len(data)
+    assert 'date' in result.columns
+    assert result['date'].equals(data['date'])
+    assert 'date_15m' in result.columns
+
+    assert 'open' in result.columns
+    assert 'open_15m' in result.columns
+    assert result['open'].equals(data['open'])
+
+    assert 'close' in result.columns
+    assert 'close_15m' in result.columns
+    assert result['close'].equals(data['close'])
+
+    assert 'volume' in result.columns
+    assert 'volume_15m' in result.columns
+    assert result['volume'].equals(data['volume'])
+
+    # Dates match 1:1
+    assert result['date_15m'].equals(result['date'])