starbucks_post_7.py

params = {'n_estimators' : [10, 50, 100], 'max_depth' : [5, 10, 30, 80], \
          'max_features': [1, 3, 8, 15], 'min_samples_split': [3, 5, 10, 30, 50, 100]}

g_rfm = RandomForestRegressor(random_state=1024);
g_src = GridSearchCV(g_rfm, params, verbose=10, cv=5, scoring='r2');
g_src.fit(X_train, y_train)

print(g_src.best_params_)

tuned_rf_model = RandomForestRegressor(max_depth=30, max_features=3, min_samples_split=100, n_estimators=100);
tuned_rf_model.fit(X_train, y_train);
y_preds_tuned = tuned_rf_model.predict(X_test);

print(r2_score(y_test, y_preds_tuned))