Machine Learning | 基于逻辑回归做二分类进行癌症预测

导入包

  

   

    

     

    
    

     

      import pandas as pd
     
    
   

    

     

    
    

     

      import numpy as np
     
    
   

    

     

    
    

     

      from sklearn.datasets import load_boston
     
    
   

    

     

    
    

     

      from sklearn.linear_model import LinearRegression, SGDRegressor,  Ridge, LogisticRegression
     
    
   

    

     

    
    

     

      from sklearn.model_selection import train_test_split
     
    
   

    

     

    
    

     

      from sklearn.preprocessing import StandardScaler
     
    
   

    

     

    
    

     

      from sklearn.metrics import mean_squared_error, classification_report
     
    
   

    

     

    
    

     

      from sklearn.externals import joblib
     
    
  
 

构造列标签名字 

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']
 

读取数据 

  

   

    

     

    
    

     

      data = pd.read_csv("breast-cancer-wisconsin.csv", names=column)
     
    
   

    

     

    
    

     

      data.head()
     
    
  
 

 缺失值进行处理

  

   

    

     

    
    

     

      data = data.replace(to_replace='?', value=np.nan)
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      data = data.dropna()
     
    
  
 

数据的分割

x_train, x_test, y_train, y_test = train_test_split(data[column[1:10]], data[column[10]], test_size=0.25)
 

标准化处理

  

   

    

     

    
    

     

      std = StandardScaler()
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      x_train = std.fit_transform(x_train)
     
    
   

    

     

    
    

     

      x_test = std.transform(x_test)
     
    
  
 

逻辑回归预测

  

   

    

     

    
    

     

      lg = LogisticRegression(C=1.0)
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      lg.fit(x_train, y_train)
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      print(lg.coef_)
     
    
  
 

  

   

    

     

    
    

     

      LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
     
    
   

    

     

    
    

     

       intercept_scaling=1, max_iter=100, multi_class='warn',
     
    
   

    

     

    
    

     

       n_jobs=None, penalty='l2', random_state=None, solver='warn',
     
    
   

    

     

    
    

     

       tol=0.0001, verbose=0, warm_start=False)
     
    
  
 

  

   

    

     

    
    

     

      [[ 1.60392495 -0.11066665  0.93702846  1.01160157 -0.31111269  1.20876603
     
    
   

    

     

    
    

     

         1.20701977  1.04581779  0.81269039]]
     
    
  
 

  

   

    

     

    
    

     

      y_predict = lg.predict(x_test)
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      print("准确率：", lg.score(x_test, y_test))
     
    
   

    

     

    
    

     

      print("召回率：", classification_report(y_test, y_predict, labels=[2, 4], target_names=["良性", "恶性"]))
     
    
  
 

文章来源: drugai.blog.csdn.net，作者：DrugAI，版权归原作者所有，如需转载，请联系作者。

原文链接：drugai.blog.csdn.net/article/details/102001398