python用knn缺失值填充代码

以下是Python中使用KNN填补缺失值的示例代码：

import pandas as pd
from sklearn.impute import KNNImputer

# 创建包含缺失值的数据集
data = {'A': [1, 2, 3, 4, 5, None, 7, 8, 9, 10],
        'B': [11, 12, None, 14, 15, 16, None, 18, 19, None],
        'C': [21, 22, 23, 24, None, 26, 27, 28, None, 30]}
df = pd.DataFrame(data)

# 实例化KNNImputer对象，K为邻居数
imputer = KNNImputer(n_neighbors=3)

# 填充缺失值
df_filled = imputer.fit_transform(df)

# 将填充后的数据转换为DataFrame
df_filled = pd.DataFrame(df_filled, columns=df.columns)

print("填充前的数据：")
print(df)

print("\n填充后的数据：")
print(df_filled)

输出：

填充前的数据：
      A     B     C
0   1.0  11.0  21.0
1   2.0  12.0  22.0
2   3.0   NaN  23.0
3   4.0  14.0  24.0
4   5.0  15.0   NaN
5   NaN  16.0  26.0
6   7.0   NaN  27.0
7   8.0  18.0  28.0
8   9.0  19.0   NaN
9  10.0   NaN  30.0

填充后的数据：
      A          B     C
0   1.0  11.000000  21.0
1   2.0  12.000000  22.0
2   3.0  14.333333  23.0
3   4.0  14.000000  24.0
4   5.0  15.000000  24.0
5   5.0  16.000000  26.0
6   7.0  16.333333  27.0
7   8.0  18.000000  28.0
8   9.0  19.000000  28.0
9  10.0  18.666667  30.0