mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-28 11:17:47 +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
41 lines
1.8 KiB
Python
41 lines
1.8 KiB
Python
from sklearn.feature_selection import RFE
|
|
from sklearn.model_selection import TimeSeriesSplit
|
|
import pandas as pd
|
|
from models.base import Model, SKLearnModel
|
|
from utils.scaler import get_scaler
|
|
from utils.types import ScalerTypes
|
|
from utils.hashing import hash_df, hash_series
|
|
from diskcache import Cache
|
|
cache = Cache(".cachedir/feature_selection")
|
|
|
|
def select_features(**kwargs):
|
|
hashed = kwargs['data_config_hash'] + kwargs['model'].get_name() + str(kwargs['n_features_to_select']) + kwargs['backup_model'].get_name() + kwargs['scaling']
|
|
if hashed in cache:
|
|
return cache.get(hashed)
|
|
else:
|
|
return_value = __select_features(**kwargs)
|
|
cache[hashed] = return_value
|
|
return return_value
|
|
|
|
def __select_features(X: pd.DataFrame, y: pd.Series, model: Model, n_features_to_select: int, backup_model: SKLearnModel, scaling: ScalerTypes, data_config_hash: str) -> pd.DataFrame:
|
|
''' Select features using RFECV, returns a pd.DataFrame (X) with only the selected features.'''
|
|
if model.model_type != 'ml': return X
|
|
|
|
# 2. Recursive feature selection
|
|
cv = TimeSeriesSplit(n_splits=5)
|
|
scaler = get_scaler(scaling)
|
|
X_scaled = X.copy()
|
|
if scaler is not None:
|
|
X_scaled = scaler.fit_transform(X_scaled)
|
|
|
|
feat_selector_model = model.model
|
|
if hasattr(feat_selector_model, 'feature_importances_') == False and hasattr(feat_selector_model, 'coef_') == False:
|
|
feat_selector_model = backup_model.model
|
|
|
|
# selector = RFECV(feat_selector_model, cv = cv, step=5, min_features_to_select=min_features_to_select)
|
|
selector = RFE(feat_selector_model, n_features_to_select= n_features_to_select)
|
|
selector = selector.fit(X_scaled, y)
|
|
print("Kept %d features out of %d" % (selector.n_features_, X_scaled.shape[1]))
|
|
|
|
return pd.DataFrame(X[X.columns[selector.support_]], index= X.index)
|