python 如何通过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

from sklearn.impute import KNNImputer

data = [[2, 4, 8], [3, np.nan, 7], [5, 8, 3], [4, 3, 8]]

imputer = KNNImputer(n_neighbors=1)
imputer.fit_transform(data)

imputer = KNNImputer(n_neighbors=2)
imputer.fit_transform(data)

import numpy as np
import pandas as pd
import pandas_profiling as pp
import matplotlib.pyplot as plt
import seaborn as sns
sns.set(context="notebook", style="darkgrid")
import warnings
warnings.filterwarnings('ignore')
%matplotlib inline
 
from sklearn.impute import KNNImputer

#Loading the dataset
diabetes_data = pd.read_csv('pima-indians-diabetes.csv')
diabetes_data.columns = ['Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness', 
                       'Insulin', 'BMI', 'DiabetesPedigreeFunction', 'Age', 'Outcome']
diabetes_data.head()

diabetes_data_copy = diabetes_data.copy(deep=True)
diabetes_data_copy[['Glucose','BloodPressure','SkinThickness','Insulin','BMI']] = diabetes_data_copy[['Glucose','BloodPressure','SkinThickness','Insulin','BMI']].replace(0, np.NaN)
 
print(diabetes_data_copy.isnull().sum())

null_index = diabetes_data_copy.loc[diabetes_data_copy['BloodPressure'].isnull(), :].index
null_index

imputer = KNNImputer(n_neighbors=10)
diabetes_data_copy[['BloodPressure', 'DiabetesPedigreeFunction', 'Age']] = imputer.fit_transform(diabetes_data_copy[['BloodPressure', 'DiabetesPedigreeFunction', 'Age']])
print(diabetes_data_copy.isnull().sum())

diabetes_data_copy.iloc[null_index]