mirror of
https://github.com/webclinic017/drift.git
synced 2026-08-05 07:07:46 +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
15 lines
715 B
Python
15 lines
715 B
Python
from fracdiff.sklearn import FracdiffStat
|
|
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:
|
|
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:
|
|
series = feature_fractional_differentiation(df, period, is_log_return)
|
|
return apply_log_if_necessary_series(series, "fracdiff")
|
|
|