boruta

import numpy as np from sklearn.ensemble import RandomForestClassifier from sklearn.datasets import load_breast_cancer from boruta import BorutaPy # Load dataset data = load_breast_cancer() X = data.data y = data.target # Initialize a Random Forest classifier (estimator for Boruta) forest = RandomForestClassifier(n_jobs=-1, class_weight='balanced', max_depth=5, random_state=42) # Initialize BorutaPy # n_estimators='auto' automatically determines the number of trees # verbose controls output: 0=no, 1=some, 2=detailed feat_selector = BorutaPy(forest, n_estimators='auto', verbose=2, random_state=42) # Fit Boruta on training data # Note: X and y must be numpy arrays feat_selector.fit(X, y) # Print results print("\n----- BorutaPy Results -----") print(f"Selected features: {np.where(feat_selector.support_)[0]}") print(f"Feature ranking: {feat_selector.ranking_}") # Transform the dataset to include only selected features X_filtered = feat_selector.transform(X) print(f"Shape of original X: {X.shape}") print(f"Shape of filtered X: {X_filtered.shape}")