Implement merge_informative_pairs helper

freqtrade/strategy/__init__.py

@@ -2,3 +2,4 @@
 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_pairs

freqtrade/strategy/strategy_helper.py

@@ -0,0 +1,39 @@
+import pandas as pd
+from freqtrade.exchange import timeframe_to_minutes
+
+
+def merge_informative_pairs(dataframe: pd.DataFrame, informative: pd.DataFrame,
+                            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.
+
+    :param dataframe: Original dataframe
+    :param informative: Informative pair, most likely loaded via dp.get_pair_dataframe
+    :param timeframe_inf: Timeframe of the informative pair sample.
+    :param ffill: Forwardfill missing values - optional but usually required
+    """
+    # Rename columns to be unique
+
+    minutes = timeframe_to_minutes(timeframe_inf)
+    informative['date_merge'] = informative["date"] + pd.to_timedelta(minutes, 'm')
+
+    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

tests/strategy/test_strategy_helpers.py

@@ -0,0 +1,61 @@
+import pandas as pd
+import numpy as np
+
+from freqtrade.strategy import merge_informative_pairs, 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_pairs():
+    data = generate_test_data('15m', 40)
+    informative = generate_test_data('1h', 40)
+
+    result = merge_informative_pairs(data, informative, '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']