文章目录
- shuffle data
shuffle data
随机打乱数据
将数据随机打乱后再训练，有助于模型的训练，否则模型应该更倾向于预测为后半部分的分类（二分类问题中）
import randomdef shuffleData(X, y, seed=None):random.seed(seed)index = [i for i in range(len(X))]random.shuffle(index)print(index)X = X[index]y = y[index]return X, ydef shuffle_data_list_dict(data_list_dict: dict, seed=None):train_X, train_y = shuffleData(data_list_dict["train_X"], data_list_dict["train_y"], seed)test_X, test_y = shuffleData(data_list_dict["test_X"], data_list_dict["test_y"], seed)return {'train_X': train_X, 'train_y': train_y, 'test_X': test_X, 'test_y': test_y}