Parameter Space Exploration for Gradient Boosting Regressor on Air Quality Dataset

grid_search_gradient_boosting_regressor_air_quality.py

#Compound list
y_predict  = ['PT08.S1(CO)','PT08.S2(NMHC)','PT08.S3(NOx)','PT08.S4(NO2)','PT08.S5(O3)']

#Select compound to optimize model for
compound = y_predict[0]

#Designate independent and dependent variables
x  = aq_final.drop([compound], axis = 1)
y  = aq_final[compound]
#Split data into test and training sets
X_train, X_test, y_train, y_test = train_test_split(x, y, test_size = 0.2, random_state = 42)
        
#Initiate Griadient  Boosting Regressors for ML model
gb = GradientBoostingRegressor(loss = 'absolute_error', random_state=42, max_features = 'auto')

#Setup values for parameters
grid_values = {
               'learning_rate':[1, 0.9, 0.8, 0.6, 0.5, 0.3, 0.1, 0.07, 0.05, 0.03, 0.01],
               'n_estimators':[10, 30, 50, 70, 90, 110, 130, 150, 170, 190, 200],
               'max_depth': [1,2,3,4,5,6,7,8,9,10,11],
              }

#Do the grid search
grid_clf_acc = GridSearchCV(gb, 
                            param_grid = grid_values, 
                            cv=5,
                            scoring = 'r2',
                            n_jobs=4,
                            return_train_score=True,
                            verbose=4)
                            
#Fit the mdoel using the results of the grid search                     
grid_clf_acc.fit(X_train, y_train)