mirror of
https://github.com/webclinic017/drift.git
synced 2026-08-01 13:17:47 +00:00
Mark Aron Szulyovszky
9488e92597
* feature(MetaLabeling): added hacky prototype * fix(MetaLabeling): drop index until first valid X & y * fix(MetaLabeling): transform both X & y before feature selection * fix(MetaLabeling): got feature selection to work * fix(MetaLabeling): correct values for meta_y * feat(MetaLabeling): created predictions multiplied by bet sizes * feat(Pipeline): print out averaged result * fix(Evaluation): correctly deal with non-discretized data * fix(Pipeline): use the right column names * refactor(Pipeline): move out meta-labeling * refactor(Pipeline): complete refactoring * feat(CI): post results to PR * fix(Pipeline): use the correct filename * chore(Config): removed now redundant feature_selection flag * feat(Models): added SVC * fix(Pipeline): accidentally switched two return values * feat(Sweep): prepared sweep_meta.yaml, moved report_results() into a separate file * fix(Pipeline): wrong function name * fix(Sweep): yaml + run_sweep * fix(Sweep): typo in name * fix(Reporting): only save averaged results * feat(MetaLabeling): use optional meta-labeling step for every lvl1 models, before averaging * feat(Reporting): print out sharpe improvement in meta-labeling step * fix(Sweep): adjusted config, defaulted to good defaults * fix(Sweep): adjusted sweep
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) -> 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, 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)
|