mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-28 19:27:47 +00:00
Mark Aron Szulyovszky
b1c04afb13
* refactor(Naming): use `primary_models` & `meta_labeling_models` * refactor(Naming): using primary * meta_labeling across config and in pipeline * feat(Pipeline): added back Ensemble models * fix(Pipeline): compiler error * fix(Config): typo * chore(Pipeline): removed unused averaging step * revert the changes in discretizing * chore(Pipeline): remove sharpe improvement logging * fix(Pipeline): ensemble predictions should be a pd.Series instead of a DataFrame * fix(Pipeline): discard unnecessary ensemble_probabilities * fix(Pipeline): fixes regarding various meta-labeling ensemble bugs * fix(Reporting): use the new naming convention * fix(Reporting): use the right variable * feat(Sweep): new sweep for ensemble models * fix(Sweep): config reference * fix(Config): simplified dev config * fix(Models): use the faster LR model * fix(Models): use LGBM in the meta-labeling model for speed * fix(Selection): always use the first model for feature selection, commented out caching from select_features() as it's close to redundant in terms of speed
43 lines
1.9 KiB
Python
43 lines
1.9 KiB
Python
from sklearn.feature_selection import RFE
|
|
from sklearn.model_selection import TimeSeriesSplit
|
|
import pandas as pd
|
|
from models.base import Model
|
|
from models.sklearn import 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) -> pd.DataFrame:
|
|
# 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) -> 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)
|
|
step = 0.05
|
|
selector = RFE(feat_selector_model, n_features_to_select= n_features_to_select, step=step)
|
|
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)
|