from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split

# Configure and train model
model = RandomForestClassifier(
    n_estimators=200,
    max_depth=12,
    max_features='sqrt',
    random_state=42
)
model.fit(X_train, y_train)
predictions = model.predict(X_test)

import pandas as pd
import numpy as np

# Feature importance
importances = model.feature_importances_
indices = np.argsort(importances)[::-1]
for i in range(10):
    print(f'{names[indices[i]]}')

accuracy = accuracy_score(y_test, predictions)
print(f'Accuracy: {accuracy:.4f}')

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.25
)

# Cross-validation
scores = cross_val_score(model, X, y, cv=5)
print(f'CV Mean: {scores.mean():.4f}')

df = pd.read_csv('dataset.csv')
X = df.drop('target', axis=1)

from sklearn.metrics import classification_report

model = RandomForestClassifier(
    n_estimators=200,
    min_samples_split=5,
    n_jobs=-1
)
model.fit(X_train, y_train)

# Evaluate performance
predictions = model.predict(X_test)
print(classification_report(y_test, predictions))