各位仙友欢迎评判指正：

#逻辑回归
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import OneHotEncoder
from sklearn.model_selection import train_test_split
import pandas as pd
from sklearn.model_selection import cross_val_score
import numpy as np
#读数据x = pd.read_csv('dataplace/all_feats.csv',usecols = [1,2,3])
#y存放标签
y = pd.read_csv('dataplace/all_feats.csv',usecols = [4])
#分成训练集和测试集，这里采用了28分
#x_train是训练集的数据，y_train是训练集的标签；x_test是测试集的数据，y_test是测试集的标签
x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.2)
"""
#训练集数据
x_cancer_train = pd.read_csv('dataplace/feats.csv',usecols = [1,2,3])
#训练集标签
y_cancer_train = pd.read_csv('dataplace/feats.csv',usecols = [4])
#测试集
x_cancer_test = pd.read_csv('dataplace/test_feats.csv',usecols=[1,2,3])
"""encoder = OneHotEncoder()
x_train = encoder.fit_transform(x_train).toarray()
x_test = encoder.transform(x_test).toarray()clf = LogisticRegression(solver='newton-cg')
clf.fit(x_train,y_train)
y_pred = clf.predict(x_test)
print(y_pred)score = cross_val_score(clf,x_train,y_train,cv = 5)
print(score)
print(np.mean(score))score1 = clf.score(x_test,y_test)
print(score1)