python 特征筛选

from sklearn.feature_selection import VarianceThreshold,SelectKBest,chi2
from sklearn.datasets import load_iris
import pandas as pd


X,y = load_iris(return_X_y=True) 
X_df = pd.DataFrame(X,columns=list("ABCD"))

(chi2,pval) = chi2(X_df,y)

dict_feature = {}
for i,j in zip(X_df.columns.values,chi2):
    dict_feature[i]=j

#对字典按照values排序
ls = sorted(dict_feature.items(),key=lambda item:item[1],reverse=True)

#特征选取数量
k =2
ls_new_feature=[]
for i in range(k):
    ls_new_feature.append(ls[i][0])


X_new = X_df[ls_new_feature]




from sklearn.feature_selection import VarianceThreshold,SelectKBest,chi2
from sklearn.datasets import load_iris
import pandas as pd
from sklearn.feature_selection import mutual_info_classif

#用于度量特征和离散目标的互信息
X,y = load_iris(return_X_y=True) 
X_df = pd.DataFrame(X,columns=list("ABCD"))

feature_cat = ["A","D"]
discrete_features =  []
fe