mirror of
https://github.com/webclinic017/drift.git
synced 2026-08-03 22:27:47 +00:00
Mark Aron Szulyovszky
1cd0119589
* fix(FeatureExtractor): apply log to transform some series to normality * feat(DataLoader): add ability of not returning returns when they're not needed (exogenous data), applied log to certain features * feat(FeatureExtractors): added standard scaling for exogenous data * feat(FeatureSelection): scale data with the passed in scaler before doing feature-selection * fix(Config): sweep config * feat(Models): output probability, store it * feat(Core): added caching to select_features() and load_data() * fix(Dependencies): added diskcache * fix(Training): error when creating results DF * feat(Models): added xgboost, fixed tests * refactor(Cache): moved hashing to a separate function, created wrapper functions to separate business logic and caching * fix(Tests): new syntax * fix(Model): XGboost can't handle -1 class, so we'll use the deprecated label_encoder fornow * fix(Model): XGBoost config * feat(Cache): add run_clear_cache script * fix(Pipeline) accidentally re-instatiating all_predictions for each asset
64 lines
3.1 KiB
Python
64 lines
3.1 KiB
Python
import pandas as pd
|
|
import numpy as np
|
|
from feature_extractors.utils import get_close_low_high
|
|
from feature_extractors.utils import apply_log_if_necessary_series
|
|
from sklearn.preprocessing import StandardScaler
|
|
|
|
def feature_debug_future_lookahead(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
|
|
return df['returns'].shift(-period)
|
|
|
|
def feature_lag(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
|
|
assert period > 0
|
|
return df['returns'].shift(period)
|
|
|
|
def feature_standard_scaling(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
|
|
scaler = StandardScaler()
|
|
return pd.Series(scaler.fit_transform(df['close'].to_numpy().reshape(-1, 1)).squeeze(), index = df.index)
|
|
|
|
def feature_day_of_week(df: pd.DataFrame, period: int, is_log_return: bool) -> 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:
|
|
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:
|
|
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:
|
|
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_STOK(df: pd.DataFrame, period: int, is_log_return: bool) -> 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)
|
|
return stok.rolling(3).mean()
|
|
|
|
def feature_RSI(df: pd.DataFrame, period: int, is_log_return: bool) -> pd.Series:
|
|
returns = df['returns']
|
|
delta = returns.diff().dropna()
|
|
u=delta*0
|
|
d = u.copy()
|
|
u[delta > 0] = delta[delta > 0]
|
|
d[delta < 0] = -delta[delta < 0]
|
|
u[u.index[period-1]] = np.mean( u[:period] ) #first value is sum of avg gains u = u.drop(u.index[:(period-1)])
|
|
d[d.index[period-1]] = np.mean( d[:period] ) #first value is sum of avg losses d = d.drop(d.index[:(period-1)])
|
|
rs = u.ewm(com=period-1, adjust=False).mean() / \
|
|
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:
|
|
returns = df['returns']
|
|
M = returns.diff(period - 1)
|
|
N = returns.shift(period - 1)
|
|
roc = pd.Series(((M / N) * 100), name = 'ROC_' + str(period))
|
|
return apply_log_if_necessary_series(roc, "roc") |