python实现训练集和测试集分割

shuffle矩阵合并

import numpy as np

def train_test_split(X, y, ratio, seed):
    assert X.shape[0] == y.shape[0]
    assert 0.0 <= ratio <= 1.0

    if seed:
        np.random.seed(seed)

    data=np.hstack((X,y.reshape(X.shape[0],-1)))
    np.random.shuffle(data)

    train=data[:int(len(y) * ratio)]
    test=data[int(len(y) * ratio):]

    return train[:,:-1], train[:,-1], test[:,:-1], test[:,-1]

shuffle索引

import numpy as np

def train_test_split(X, y, ratio, seed):
    assert X.shape[0] == y.shape[0]
    assert 0.0 <= ratio <= 1.0

    if seed:
        np.random.seed(seed)
    shuffle_index = np.random.permutation(len(y))

    train_index = shuffle_index[:int(len(y) * ratio)]
    test_index = shuffle_index[int(len(y) * ratio):]

    return X[train_index], y[train_index], X[test_index], y[test_index]