house_prices.py 文件源码

def predicted_vs_actual_sale_price_xgb(self, xgb_params, x_train, y_train, seed, title_name):
        # Split the training data into an extra set of test
        x_train_split, x_test_split, y_train_split, y_test_split = train_test_split(x_train, y_train)
        dtrain_split = xgb.DMatrix(x_train_split, label=y_train_split)
        dtest_split = xgb.DMatrix(x_test_split)

        res = xgb.cv(xgb_params, dtrain_split, num_boost_round=1000, nfold=4, seed=seed, stratified=False,
                     early_stopping_rounds=25, verbose_eval=10, show_stdv=True)

        best_nrounds = res.shape[0] - 1
        print(np.shape(x_train_split), np.shape(x_test_split), np.shape(y_train_split), np.shape(y_test_split))
        gbdt = xgb.train(xgb_params, dtrain_split, best_nrounds)
        y_predicted = gbdt.predict(dtest_split)
        plt.figure(figsize=(10, 5))
        plt.scatter(y_test_split, y_predicted, s=20)
        rmse_pred_vs_actual = self.rmse(y_predicted, y_test_split)
        plt.title(''.join([title_name, ', Predicted vs. Actual.', ' rmse = ', str(rmse_pred_vs_actual)]))
        plt.xlabel('Actual Sale Price')
        plt.ylabel('Predicted Sale Price')
        plt.plot([min(y_test_split), max(y_test_split)], [min(y_test_split), max(y_test_split)])
        plt.tight_layout()