python_通过KNN来填充缺失值

python_通过KNN来填充缺失值

# 加载库
import numpy as np
from fancyimpute import KNN
from sklearn.preprocessing import StandardScaler
from sklearn.datasets import make_blobs

# 创建模拟特征矩阵
features, _ = make_blobs(n_samples = 1000,
                         n_features = 2,
                         random_state = 1)

# 标准化特征
scaler = StandardScaler()
standardized_features = scaler.fit_transform(features)
standardized_features
# 制造缺失值
true_value = standardized_features[0,0]
standardized_features[0,0] = np.nan
standardized_features
# 预测
features_knn_imputed = KNN(k=5, verbose=0).fit_transform(standardized_features)
# features_knn_imputed = KNN(k=5, verbose=0).complete(standardized_features)
features_knn_imputed
# #对比真实值和预测值
print("真实值:", true_value)
print("预测值:", features_knn_imputed[0,0])
# 加载库
import numpy as np
from fancyimpute import KNN
from sklearn.preprocessing import StandardScaler
from sklearn.datasets import make_blobs
​
# 创建模拟特征矩阵
features, _ = make_blobs(n_samples = 1000,
                         n_features = 2,
                         random_state = 1)
​
# 标准化特征
scaler = StandardScaler()
standardized_features = scaler.fit_transform(features)
standardized_features
# 制造缺失值
true_value = standardized_features[0,0]
standardized_features[0,0] = np.nan
standardized_features
# 预测
features_knn_imputed = KNN(k=5, verbose=0).fit_transform(standardized_features)
# features_knn_imputed = KNN(k=5, verbose=0).complete(standardized_features)
features_knn_imputed
# #对比真实值和预测值
print("真实值:", true_value)
print("预测值:", features_knn_imputed[0,0])
真实值: 0.8730186113995938
预测值: 1.0955332713113226