Python利用逻辑回归分类器对乳腺肿瘤进行良性/恶性预测实战（超详细 附源码）

import pandas as pd
import numpy as np
column_names=['number','Cl_Thickness','Unif_cell_size','Unif_cell_shape','Marg_Adhesion','Sing_epith_cell_size','Bare_nuclei','Bland_chromation','Norm_nuclei','Mitoses','Class']
data=pd.read_csv('breast-cancer-wisconsin.data',names=column_names)
display(data.head())
data=data.replachow='any')
print(data.shape)
from sklearn.model_selection import train_test_split
# 划分训练集与测试集
X_train,X_test,y_train,y_test=train_test_split(data[column_names[1:10]],data[column_names[10]],test_size=0.25,random_state=33)
printlearn.preprocessing import StandardScaler
ss=StandardScaler()
X_train=ss.fit_transform(X_train)
X_test=ss.transform(X_test)
print(X_train.mean())
from sklearn.linear_model import LogisticRegression
from sklearn.linear_model import SGDClassifier
lr=Logitrain,y_train)
lr_y_predict=lr.predict(X_test)
sgdc.fit(X_train,y_train)
sgdc_y_predict=sgdc.predict(X_test)
from sklearn.metrics import classification_report
print('Accuracy of LR Classifier:',lr.score(X_test,y_test))
print(classification_report(y_test,lr_y_predict,target_names=['Benign','Malignant']))
print('Accuracy of SGD Classifier:',sgdc.score(X_test,y_test))
print(classification_report(y_test,sgdc_y_predict,target_names=['Benign','Malignant']))