在Python中实现引导的内存有效方法?

只需创建索引,它将分割原始特性和目标,并在每次需要引导数据集时应用这些索引。

import numpy as np
from sklearn.datasets import load_boston


def get_bootstrap_indices(dataset, datasets: int):
    for _ in range(datasets):
        yield np.random.choice(np.arange(len(dataset)), size=len(dataset), replace=True)


dataset = load_boston().data
print(f"Original dataset shape: {dataset.shape}")

for indices in get_bootstrap_indices(dataset, 10):
    print(dataset[indices].shape)