Boruta | เลือกคุณลักษณะที่สำคัญด้วย Random Forest

import numpy as np
import pandas as pd
from sklearn.ensemble import RandomForestClassifier
from boruta import BorutaPy

# Load data
X = pd.read_csv("examples/test_X.csv", index_col=0).values
y = pd.read_csv("examples/test_y.csv", header=None, index_col=0).values.ravel()

# Random Forest
rf = RandomForestClassifier(n_jobs=-1, class_weight="balanced", max_depth=5)

# Boruta
feat_selector = BorutaPy(rf, n_estimators="auto", verbose=2, random_state=1)
feat_selector.fit(X, y)

print("Selected features:", feat_selector.support_)
print("Feature ranking:", feat_selector.ranking_)

# Keep only important features
X_filtered = feat_selector.transform(X)

from sklearn.datasets import make_classification
from xgboost import XGBClassifier

X, y = make_classification(
    n_samples=1000, n_features=10,
    n_informative=10, n_redundant=0, n_classes=2,
    random_state=0, shuffle=False
)
model = XGBClassifier(max_depth=4)

feat_selector = BorutaPy(model, n_estimators="auto", verbose=2, random_state=1)
feat_selector.fit(X, y)
X_filtered = feat_selector.transform(X)

print(f"{X.shape[1]} --> {X_filtered.shape[1]}")

X, y = make_classification(
    n_samples=2000, n_features=100,
    n_informative=10, n_redundant=0, n_classes=2,
    random_state=0, shuffle=False
)
model = XGBClassifier(max_depth=5)

feat_selector = BorutaPy(model, n_estimators="auto", verbose=2, random_state=1)
feat_selector.fit(X, y)
X_filtered = feat_selector.transform(X)

print(f"{X.shape[1]} --> {X_filtered.shape[1]}")