缺失值填充2——python 热卡填充（Hot deck imputation）、冷卡填充（Cold deck imputation）

基本概念

热卡填充：在完整数据中找到一个与它最相似的对象，用最相似的值填充当前值

冷卡填充：通过其他途径找到能填充缺失部分的值

热卡填充其实就是使用KNN去预测的一种特殊形式，KNN是参考K个，而热卡填充是参考最近的1个，所以热卡填充可以用KNN做，关键代码是：

from sklearn.impute import KNNImputer

hot_deck_imputer = KNNImputer(n_neighbors=2, weights="uniform")  # 虽然看着是用KNN，但是参数固定：n_neighbors=2
dataframe = hot_deck_imputer.fit_transform(dataframe)

示例代码

import pandas as pd
import numpy as np


def hot_deck_imputation(dataframe: pd.DataFrame):
    from sklearn.impute import KNNImputer
    hot_deck_imputer = KNNImputer(n_neighbors=2, weights="uniform")  # 虽然看着是用KNN，但是参数固定：n_neighbors=2
    new_df = hot_deck_imputer.fit_transform(dataframe)
    return new_df


def get_dataset():
    """得到数据
    :return data_x：有缺失值的数据
    :return true_value：缺失数据的原始真实值
    :return data_y：原问题中待预测的label
    """
    import copy
    from sklearn.datasets import make_classification
    data_x, data_y = make_classification(n_samples=100, n_classes=4, n_features=6, n_informative=4,
                                         random_state=0)  # 6个特征
    data_x = pd.DataFrame(data_x)
    data_x.columns = ['x1', 'x2', 'x3', 'x4', 'x5', 'miss_line']
    true_data = copy.deepcopy(data_x)
    # 在miss_line这一列删除20%的数据
    drop_index = data_x.sample(frac=0.2).index
    data_x.loc[drop_index, "miss_line"] = np.nan
    true_value = true_data.loc[drop_index, 'miss_line']  # 空值的真实值
    return data_x, true_value, data_y


if __name__ == '__main__':
    value_x, true_value_x, value_y = get_dataset()
    fill_df = hot_deck_imputation(value_x)