gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-21 06:48:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Mark Aron Szulyovszky
2022-01-26 23:22:43 +01:00
committed by GitHub
parent 1042c82333
commit 42a1bc59cb
65 changed files with 759 additions and 276571 deletions
Download Patch File Download Diff File Expand all files Collapse all files
feature_extractors/feature_extractors.py
+14 -17
View File
@@ -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)