Ensemble models for extra votes
The LassoCV() model selected 22 out of 32 features. Not bad, but not a spectacular dimensionality reduction either. Let's use two more models to select the 10 features they consider most important using the Recursive Feature Eliminator (RFE).
The standardized training and test data has been pre-loaded for you as X_train, X_test, y_train, and y_test.
Cet exercice fait partie du cours
Dimensionality Reduction in Python
Exercice interactif pratique
Essayez cet exercice en complétant cet exemple de code.
from sklearn.feature_selection import RFE
from sklearn.ensemble import GradientBoostingRegressor
# Select 10 features with RFE on a GradientBoostingRegressor, drop 3 features on each step
rfe_gb = RFE(estimator=____,
n_features_to_select=____, step=____, verbose=1)
rfe_gb.fit(X_train, y_train)