feat(Events): added EventFilter, EventLabeller (#186)

feature_extractors/feature_extractor_presets.py

@@ -1,7 +1,7 @@
-from feature_extractors.feature_extractors import feature_lag, feature_mom, feature_ROC, feature_RSI, feature_STOD, feature_STOK, feature_expanding_zscore, feature_vol, feature_day_of_month, feature_day_of_week, feature_month, feature_debug_future_lookahead
-from utils.types import FeatureExtractorConfig
-from utils.helpers import flatten
-from feature_extractors.fractional_differentiation import feature_fractional_differentiation, feature_fractional_differentiation_log
+
+from .types import FeatureExtractorConfig
+from .feature_extractors import feature_lag, feature_mom, feature_ROC, feature_RSI, feature_STOD, feature_STOK, feature_expanding_zscore, feature_vol, feature_day_of_month, feature_day_of_week, feature_month, feature_debug_future_lookahead
+from .fractional_differentiation import feature_fractional_differentiation, feature_fractional_differentiation_log
 
 __presets = dict(
     debug_future_lookahead = [('debug_future', feature_debug_future_lookahead, [1])],

feature_extractors/feature_extractors.py

@@ -3,46 +3,43 @@ import numpy as np
 from feature_extractors.utils import get_close_low_high
 from feature_extractors.utils import apply_log_if_necessary_series
 
-def feature_debug_future_lookahead(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
+def feature_debug_future_lookahead(df: pd.DataFrame, period: int) -> pd.Series:
     return df['returns'].shift(-period)
 
-def feature_lag(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
+def feature_lag(df: pd.DataFrame, period: int) -> pd.Series:
     assert period > 0
     return df['returns'].shift(period)
 
-def feature_expanding_zscore(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
+def feature_expanding_zscore(df: pd.DataFrame, period: int) -> pd.Series:
     close = df['close']
     return (close - close.expanding(period).mean()) / close.expanding(period).std()
 
-def feature_day_of_week(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.DataFrame:
+def feature_day_of_week(df: pd.DataFrame, period: int) -> pd.DataFrame:
     return pd.get_dummies(pd.DatetimeIndex(df.index).dayofweek, drop_first=True, prefix="date_day_week").set_index(df.index)
 
-def feature_day_of_month(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.DataFrame:
+def feature_day_of_month(df: pd.DataFrame, period: int) -> pd.DataFrame:
     return pd.get_dummies(pd.DatetimeIndex(df.index).day, drop_first=True, prefix="date_day_month").set_index(df.index)
 
-def feature_month(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.DataFrame:
+def feature_month(df: pd.DataFrame, period: int) -> pd.DataFrame:
     return pd.get_dummies(pd.DatetimeIndex(df.index).month, drop_first=True, prefix="date_month").set_index(df.index)
 
-def feature_vol(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
+def feature_vol(df: pd.DataFrame, period: int) -> pd.Series:
     return df['returns'].rolling(period).std() * (252**0.5)
 
-def feature_mom(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
-    if is_log_return:
-        return np.log(df['close']).diff(period)
-    else:
-        return df['close'].pct_change(period)
+def feature_mom(df: pd.DataFrame, period: int) -> pd.Series:
+    return np.log(df['close']).diff(period)
 
-def feature_STOK(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
+def feature_STOK(df: pd.DataFrame, period: int) -> pd.Series:
     close, low, high = get_close_low_high(df)
 
     STOK = ((close - low.rolling(period).min()) / (high.rolling(period).max() - low.rolling(period).min())) * 100
     return apply_log_if_necessary_series(STOK, "stok")
 
-def feature_STOD(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
-    stok = feature_STOK(df, period, is_log_return)
+def feature_STOD(df: pd.DataFrame, period: int) -> pd.Series:
+    stok = feature_STOK(df, period)
     return stok.rolling(3).mean()
 
-def feature_RSI(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
+def feature_RSI(df: pd.DataFrame, period: int) -> pd.Series:
     returns = df['returns']
     delta = returns.diff().dropna()
     u=delta*0
@@ -55,7 +52,7 @@ def feature_RSI(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series
     d.ewm(com=period-1, adjust=False).mean()
     return apply_log_if_necessary_series(100-100/(1+rs), "rsi")
 
-def feature_ROC(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
+def feature_ROC(df: pd.DataFrame, period: int) -> pd.Series:
     returns = df['returns']
     M = returns.diff(period - 1)
     N = returns.shift(period - 1)

feature_extractors/fractional_differentiation.py

@@ -3,13 +3,13 @@ import pandas as pd
 import numpy as np
 from feature_extractors.utils import apply_log_if_necessary_series
 
-def feature_fractional_differentiation(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
+def feature_fractional_differentiation(df: pd.DataFrame, period: int) -> pd.Series:
     frac_diff = FracdiffStat(window = period)
     input_series = df["close"].to_numpy().reshape(-1, 1)
     result = frac_diff.fit_transform(input_series)
     return pd.Series(result.squeeze(), index = df.index)
 
-def feature_fractional_differentiation_log(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
+def feature_fractional_differentiation_log(df: pd.DataFrame, period: int) -> pd.Series:
     series = feature_fractional_differentiation(df, period, is_log_return)
     return apply_log_if_necessary_series(series, "fracdiff")
     

feature_extractors/ta.py

@@ -2,7 +2,7 @@ import pandas_ta as ta
 import pandas as pd
 from feature_extractors.utils import get_close_low_high
 
-def feature_EBSW(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
+def feature_EBSW(df: pd.DataFrame, period: int) -> pd.Series:
     close, low, high = get_close_low_high(df)
 
     return ta.ebsw(close, period)

feature_extractors/types.py

@@ -0,0 +1,9 @@
+from typing import Callable, Union, Literal
+import pandas as pd
+
+Period = int
+IsLogReturn = bool
+FeatureExtractor = Callable[[pd.DataFrame, Period], Union[pd.DataFrame, pd.Series]]
+Name = str
+FeatureExtractorConfig = tuple[Name, FeatureExtractor, list[Period]]
+ScalerTypes = Literal['normalize', 'minmax', 'standardize', 'none']