逻辑斯特回归---良性/恶性肿瘤的分类_sas编程判断肿瘤良性与恶性的关系

逻辑斯特回归---良性/恶性肿瘤的分类

#!/usr/bin/python
# -*- coding:utf-8 -*-
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report
def mylogistic():
    column = ['Sample code number', 'Clump Thickness', 'Uniformity of Cell Size', 'Uniformity of Cell Shape',
              'Marginal Adhesion', 'Single Epithelial Cell Size', 'Bare Nuclei', 'Bland Chromatin', 'Normal Nucleoli',
              'Mitoses', 'Class']
    data=pd.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data",names=column)
    # print(data.info())
    data=data.replace(to_replace="?",value=np.nan)
    print(data.shape)
    data=data.dropna()
    print(data.shape)
    x_train,x_test,y_train,y_test=train_test_split(data[column[1:10]],data[column[10]],test_size=0.25,random_state=30)
 
    ss=StandardScaler()
 
    # 对目标值不进行分类
    x_train=ss.fit_transform(x_train)
    x_test=ss.transform(x_test)
 
    lr=LogisticRegression()
    lr.fit(x_train,y_train)
 
    y_predict=lr.predict(x_test)
 
    print("准确率：",lr.score(x_test,y_test))
    print("召回率：",classification_report(y_test,y_predict,labels=[2,4],target_names=["良性","恶性"]))
 
    pass
 
if __name__ == '__main__':
    print("hello")
    mylogistic()