PYTHON

sample randomforest hyperparameter tuning

# Define the dictionary 'params_rf'
params_rf = {
             'n_estimators': [100, 350, 500],
             'max_features': ['log2', 'auto', 'sqrt'],
             'min_samples_leaf': [2, 10, 30], 
             }
# Import GridSearchCV
from sklearn.model_selection import GridSearchCV

# Instantiate grid_rf
grid_rf = GridSearchCV(estimator=...base_randomforest_model...,
                       param_grid=params_rf,
                       scoring='neg_mean_squared_error',
                       cv=3,
                       verbose=1,
                       n_jobs=-1)
                       
#Train the model
grid_rf.fit(X_train, y_train)

# Import mean_squared_error from sklearn.metrics as MSE 
from sklearn.metrics import mean_squared_error as MSE

# Extract the best estimator
best_model = grid_rf.best_estimator_

# Predict test set labels
y_pred = best_model.predict(X_test)

# Compute rmse_test
rmse_test = MSE(y_test, y_pred)**(1/2)

# Print rmse_test
print('Test RMSE of best model: {:.3f}'.format(rmse_test))