Merge pull request #3744 from freqtrade/fix/infomrativesample

fix Informative pair documentation

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