单变量特征选择

import pandas as pd
from numpy import set_printoptions
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2

data=pd.read_excel(‘C:\Users\Administrator\Desktop\test.xlsx’)
X=data[[‘country’,‘region’,‘provstate’,‘city’,‘specificity’,‘vicinity’,‘targtype1’,‘weaptype1’]]
Y=data[‘gname’]

ts=SelectKBest(score_func=chi2,k=4)
fit=ts.fit(X,Y)
set_printoptions(precision=4)
print(fit.scores_)
features=fit.transform(X)
print(features) #单变量特征选择

j=[‘country’,‘region’,‘provstate’,‘city’,‘specificity’,‘vicinity’,‘targtype1’,‘weaptype1’,‘gname’]
for i in j:
X[i] = X[i].to_string()
X.info() #将数据转化为字符型