用于输入具有线性相关性的缺失值的代码

import numpy as np
from sklearn.linear_model import LinearRegression

# 生成随机数据
np.random.seed(0)
n_samples = 1000
n_features = 5
X = np.random.rand(n_samples, n_features)
coef = np.random.rand(n_features)
y = np.dot(X, coef)

# 生成缺失值
missing_ratio = 0.2
missing_mask = np.random.rand(n_samples, n_features) < missing_ratio
X_missing = X.copy()
X_missing[missing_mask] = np.nan

# 使用线性回归填充缺失值
model = LinearRegression()
for feature in range(n_features):
    X_feature = X_missing[:, feature]
    y_feature = y.copy()
    feature_mask = ~np.isnan(X_feature)
    X_feature = X_feature[feature_mask].reshape(-1, 1)
    y_feature = y_feature[feature_mask]
    model.fit(X_feature, y_feature)
    X_missing[~feature_mask, feature] = model.predict(X_missing[~feature_mask, feature].reshape(-1, 1))

print("原始数据：")
print(X[:5, :])
print("\n带缺失值的数据：")
print(X_missing[:5, :])