Stock_Prediction_Model_Random_Forrest.py 文件源码

def prepare_train_test_data(self, data_feature, LabelColumnName):
        firstloop = 1
        for ticker, data in data_feature.items():
            X, y = preprocessing_data(self.paras, data[0], LabelColumnName, one_hot_label_proc=False)
            X_train_temp, X_test_temp, y_train_temp, y_test_temp = train_test_split(X, y, test_size=0.3)
            # print('Train shape X:', X_train_temp.shape, ',y:', y_train_temp.shape)
            # print('Test shape X:', X_test_temp.shape, ',y:', y_test_temp.shape)

            if firstloop == 1:
                firstloop = 0
                X_train = X_train_temp
                X_test = X_test_temp
                y_train = y_train_temp
                y_test = y_test_temp
            else:
                X_train = np.append(X_train, X_train_temp, 0)
                X_test = np.append(X_test, X_test_temp, 0)
                y_train = np.append(y_train, y_train_temp, 0)
                y_test = np.append(y_test, y_test_temp, 0)

        #print('Train shape X:', X_train.shape, ',y:', y_train.shape)
        #print('Test shape X:', X_test.shape, ',y:', y_test.shape)
        return X_train, y_train, X_test, y_test