gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-13 19:08:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(DataLoader): caching MVP, added ability to use standard scaling for exogenous data, scaling is now also done before feature selection (#105)

Browse Source 
* 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
This commit is contained in:
Mark Aron Szulyovszky
2022-01-04 11:44:35 +01:00
committed by GitHub
parent 867269df2b
commit 1cd0119589
27 changed files with 324 additions and 206 deletions
Download Patch File Download Diff File Expand all files Collapse all files
feature_selection/feature_selection.py
+21 -4
View File
@@ -2,14 +2,31 @@ from sklearn.feature_selection import RFE
from sklearn.model_selection import TimeSeriesSplit
import pandas as pd
from models.base import Model, SKLearnModel
from sklearn.decomposition import PCA
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(X: pd.DataFrame, y: pd.Series, model: Model, n_features_to_select: int, backup_model: SKLearnModel) -> pd.DataFrame:
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:
@@ -17,7 +34,7 @@ def select_features(X: pd.DataFrame, y: pd.Series, model: Model, n_features_to_s
# 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, y)
print("Kept %d features out of %d" % (selector.n_features_, X.shape[1]))
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)