机器学习--逻辑回归及乳腺癌预测

 # 加载自带乳腺癌数据集

    
 from sklearn.datasets import load_breast_cancer
    
  
    
 cancer=load_breast_cancer()
    
 X=cancer.data
    
 y=cancer.target
    
 print('data.shape:{0};no. positive:{1};no. negative:{2}'.format(X.shape,y[y==1].shape[0],y[y==0].shape[0]))
    
 print(cancer.data[0])

 from sklearn.model_selection import train_test_split

    
 X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2)
    
  
    
 from sklearn.linear_model import LogisticRegression
    
 model = LogisticRegression()
    
 model.fit(X_train,y_train)
    
  
    
 train_score = model.score(X_train,y_train)
    
 test_score = model.score(X_test,y_test)
    
 print('train score:{train_score: .6f}; test score:{test_score:.6f}'.format(train_score=train_score,test_score=test_score))
    
  
    
 # 查看预测样本中有几个正确
    
 y_pred = model.predict(X_test)
    
 # sum()只返回True的个数
    
 print('matchs:{0}/{1}'.format(np.equal(y_pred,y_test).sum(),y_test.shape[0]))

 # 找出预测概率低于90%的样本

    
 y_pred_proba = model.predict_proba(X_test)   #每个测试样本的测试概率
    
 print('sample of predict probability:{0}'.format(y_pred_proba[0]))  #打印第一个样本数据
    
  
    
 # 找出第一列，即预测为阴性的概率大于0.1的样本
    
 result = y_pred_proba[y_pred_proba[:,0]>0.1]
    
  
    
 # 在result里找出第二列，即预测为阳性概率大于0.1的样本
    
 result_1 = result[result[:,1]>0.1]
    
 print(result_1)

 from sklearn.preprocessing import PolynomialFeatures

    
 from sklearn.linear_model import LogisticRegression
    
 from sklearn.pipeline import Pipeline
    
  
    
 def polynomial_model(degree=1,**kwarg):
    
     polynomial_features = PolynomialFeatures(degree=degree, include_bias=False)
    
     logistic_regression = LogisticRegression(**kwarg)
    
     pipeline = Pipeline([('polynomial_features',polynomial_features),('logistic_regression',logistic_regression)])
    
     return pipeline
    
  
    
 # 二阶多项式
    
 import time
    
 # 使用L1范数为正则项，实现参数稀疏化
    
 model = polynomial_model(degree=2,penalty='l1')
    
  
    
 start = time.clock()
    
 model.fit(X_train,y_train)
    
  
    
 train_score = model.score(X_train,y_train)
    
 test_score = model.score(X_test,y_test)
    
  
    
 print('elaspe:{0:.6f}; train score:{1:.6f}; test score:{2:.6f}'.format(time.clock()-start,train_score,test_score))

 logistic_regression = model.named_steps['logistic_regression']

    
 print('model parameters shape:{0};count of non-zero element:{1}'.format(logistic_regression.coef_.shape,np.count_nonzero(logistic_regression.coef_)))

 # L1范数的一阶和二阶多项式

    
 cv = ShuffleSplit(n_splits=10,test_size=0.2,random_state=0)
    
 title = 'Learning Curve(degree ={0},penalty={1})'
    
 degrees=[1,2]
    
 penalty='l1'
    
  
    
 start=time.clock()
    
 plt.figure(figsize=(12,4),dpi=144)
    
 for i in range(len(degrees)):
    
     plt.subplot(1,2,i+1)
    
     plot_learning_curve(polynomial_model(degree=degrees[i],penalty=penalty),title.format(degrees[i],penalty),X,y,ylim=(0.8,1.01),cv=cv)
    
 print('elaspe:{0:.6f}'.format(time.clock()-start))
    
  
    
 # L2范数的一阶和二阶多项式
    
 penalty='l2'
    
  
    
 start=time.clock()
    
 plt.figure(figsize=(12,4),dpi=144)
    
 for i in range(len(degrees)):
    
     plt.subplot(1,2,i+1)
    
     plot_learning_curve(polynomial_model(degree=degrees[i],penalty=penalty),title.format(degrees[i],penalty),X,y,ylim=(0.8,1.01),cv=cv)
    
 print('elaspe:{0:.6f}'.format(time.clock()-start))