PYTHON

random forest algorithm

# Import RandomForestRegressor
from sklearn.ensemble import RandomForestRegressor

# Instantiate rf
rf = RandomForestRegressor(n_estimators=25,
                           random_state=2)
                           
# Fit rf to the training set            
rf.fit(X_train, y_train) 
# Import mean_squared_error as MSE
from sklearn.metrics import mean_squared_error as MSE

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

# Evaluate the test set RMSE
rmse_test = MSE(y_test, y_pred)**(1/2)

# Print rmse_test
print('Test set RMSE of rf: {:.2f}'.format(rmse_test))
# Create a pd.Series of features importances
importances = pd.Series(data=rf.feature_importances_,
                        index= X_train.columns)

# Sort importances
importances_sorted = importances.sort_values()

# Draw a horizontal barplot of importances_sorted
importances_sorted.plot(kind='barh', color='lightgreen')
plt.title('Features Importances')
plt.show()