对2个numpy数组进行洗牌和拆分,以保持它们之间的顺序

我会这样做的

def split(x, y, train_ratio=0.7):
  x_size = x.shape[0]
  train_size = int(x_size * train_ratio)
  test_size = x_size - train_size
  train_indices = np.random.choice(x_size, size=train_size, replace=False)
  mask = np.zeros(x_size, dtype=bool)
  mask[train_indices] = True
  x_train, y_train = x[mask], y[mask]
  x_test, y_test = x[~mask], y[~mask]
  return (x_train, y_train), (x_test, y_test)

然后用掩模选择训练样本和测试样本。

train_test_split

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.33)

sklearn.model_selection.train_test_split

import numpy as np

def my_train_test_split(X, Y, train_ratio=0.8):
    """return X_train, Y_train, X_test, Y_test"""
    n = X.shape[0]
    split = int(n * train_ratio)
    index = np.arange(n)
    np.random.shuffle(index)
    return X[index[:split]], Y[index[:split]], X[index[split:]], Y[index[split:]]