DataFrame 数据集切分

DataFrame 数据集切分

#方式1

  	from sklearn.model_selection import train_test_split 

	 # split train set and test set
    data_train, data_test = train_test_split(data, test_size=0.2, random_state=1234)

    # split validate set and test set
    data_test, data_val = train_test_split(data_test, test_size=0.5, random_state=1234)

#方式2

	n_ratings = data.shape[0]
    test = np.random.choice(n_ratings, size=int(train_test_ratio * n_ratings),
                            replace=False)  
    test_idx = np.zeros(n_ratings, dtype=bool)
    test_idx[test] = True
    tp_test = data[test_idx]
    tp_train = data[~test_idx]

    n_ratings = tp_test.shape[0]
    test_valid = np.random.choice(n_ratings, size=int(test_valid_ratio * n_ratings),
                             replace=False)  ##replace:True表示可以取相同数字，False表示不可以取相同数字
    valid_idx = np.zeros(n_ratings, dtype=bool)
    valid_idx[test_valid] = True
    tp_valid = tp_test[valid_idx]
    tp_train = tp_test[~valid_idx]