SVM进行乳腺癌预测

 import matplotlib

    
 import pandas as pd
    
 import seaborn as sns
    
 import matplotlib.pyplot as plt
    
 from sklearn.model_selection import train_test_split
    
 from sklearn import svm
    
 from sklearn.preprocessing import StandardScaler
    
 import numpy as np
    
 #加载数据源
    
 data = pd.read_csv(r'C:\Users\john\Desktop\暑假论文\乳腺癌预测SVM\breast_cancer_data-master\breast_cancer_data-master\data.csv')
    
    
    
    
    代码解释

 data.info()

    
 data.columns
    
    
    
    
    代码解释

 #id没有实际意思，去掉

    
 data.drop('id',axis=1,inplace=True)#inplace=True不创建新的对象，直接对原始对象进行修改；
    
 #diagnosis字段的取值即分类结果为B或M，可以用0和1来替代
    
 data['diagnosis'] = data['diagnosis'].map({'M':1,'B':0})
    
 #后面30个字段可以分成3组
    
 featurs_mean = list(data.columns[1:11])
    
 featurs_se = list(data.columns[12:21])
    
 featurs_worst = list(data.columns[22:31])
    
    
    
    
    代码解释

 #肿瘤结果可视化

    
 #看整体良性，恶行肿瘤的诊断情况
    
 sns.countplot(data['diagnosis'],label='Count')
    
 plt.show()
    
 #看整体良性、恶性肿瘤的诊断情况
    
 corr = data[featurs_mean].corr()
    
 plt.figure(figsize=(14,14))
    
 sns.heatmap(corr,annot=True)     #annot = True 显示每个方格的数据
    
 plt.show()
    
    
    
    
    代码解释

 features_remain = ['radius_mean','texture_mean','smoothness_mean','compactness_mean',

    
                'symmetry_mean','fractal_dimension_mean']
    
    
    
    
    代码解释

 #模型训练

    
 #抽取30%数据作为测试集，其他作为训练集
    
 train,test = train_test_split(data,test_size=0.3)
    
 train_x = train[features_remain]
    
 train_y = train['diagnosis']
    
 test_x = test[features_remain]
    
 test_y = test['diagnosis']
    
  
    
 #采用Z-score规范化数据，保证每个特征维度均值为0，方差为1
    
 ss = StandardScaler()
    
 train_x = ss.fit_transform(train_x)
    
 test_x = ss.transform(test_x)
    
  
    
 #创建SVM分类器
    
 model = svm.SVC()
    
 #训练
    
 model.fit(train_x,train_y)
    
 #测试集做预测
    
 prediction = model.predict(test_x)
    
 print('训练集准确率：',model.score(train_x,train_y))
    
 print('测试集准确率：',model.score(test_x,test_y))
    
  
    
 #LinearSVC()
    
 model = svm.LinearSVC()
    
 #训练
    
 model.fit(train_x,train_y)
    
 #测试集做预测
    
 prediction = model.predict(test_x)
    
 print('训练集准确率：',model.score(train_x,train_y))
    
 print('测试集准确率：',model.score(test_x,test_y))
    
    
    
    
    代码解释