1 #载入数据
  2 from sklearn.datasets import load_breast_cancer
  3 from sklearn.linear_model import LogisticRegression
  4 from sklearn.model_selection import train_test_split
  5 from sklearn.model_selection import cross_val_predict
  6 from sklearn.model_selection import ShuffleSplit
  7 from sklearn.preprocessing import PolynomialFeatures
  8 from sklearn.model_selection import learning_curve
  9 from sklearn.model_selection import ShuffleSplit
 10 from sklearn.pipeline import Pipeline
 11 import numpy as np
 12 import matplotlib.pyplot as plt
 13 import time
 14 from common.utils import plot_learning_curve
 15 
 16 %pylab
 17 # np.random.seed(6)
 18 
 19 #增加多项式做预处理
 20 def polynomial_model(degree=1,**kwarg):
 21     polynomial_features = PolynomialFeatures(degree=degree,
 22                                         include_bias=False)
 23     logistic_regression = LogisticRegression(**kwarg)
 24     pipeline = Pipeline([("polynomial_features",polynomial_features),
 25                         ("logistic_regression",logistic_regression)])
 26     return pipeline
 27 
 28 # 学习曲线的绘制
 29 def plot_learning_curve(plt,estimator,title,X,y,ylim=None,cv=None,
 30                        n_jobs=1,train_sizes=np.linspace(.1,1.0,5)):
 31     """
 32     estimator:实现‘fit‘和‘predict‘方法的对象类型
 33     title:字符串：图标抬头
 34     X,y:图标x,y
 35     ylim:元祖，(ymin,ymax)，可选择定义图像的最小和最大y值
 36     cv:int,交叉验证生成器，可选择和决定交叉验证的生成策略，cv的可能输入有：
 37         - None,使用默认的3-fold交叉验证
 38         - Integer,指定折叠的数量
 39             --如实上述两种情况，如果‘y‘是个二元的或者多元分类，使用StratifiedKFold
 40             --如果‘y‘不是分类问题，使用KFold
 41         - 一个对象，可被用来作为cv生成器
 42         - 一个迭代器
 43     n_jobs:整数，同时运行的工作数量
 44     train_sizes:表示把训练样本数量从0.1~1分成5等分，生成[0.1,0.325,0.55,0.775,1]的
 45             序列，从序列中取出训练样本数量百分比，逐个计算在当前训练样本数量情况下训练出来的
 46             模型准确性。
 47     """
 48     plt.title(title)
 49     if ylim is not None:
 50         plt.ylim(*ylim)
 51     plt.xlabel("Training examples")
 52     plt.ylabel("Score")
 53     train_sizes,train_scores,test_scores=learning_curve(estimator,
 54                     X,y,cv=cv,n_jobs=n_jobs,train_sizes=train_sizes)
 55     train_scores_mean = np.mean(train_scores,axis = 1)
 56     train_scores_std = np.std(train_scores,axis = 1)
 57     test_scores_mean = np.mean(test_scores,axis = 1)
 58     test_scores_std = np.std(test_scores,axis = 1)
 59     plt.grid(True)
 60     plt.fill_between(train_sizes, train_scores_mean - train_scores_std,
 61                      train_scores_mean + train_scores_std, alpha=0.1,
 62                      color="r")
 63     plt.fill_between(train_sizes,test_scores_mean-test_scores_std,
 64                     test_scores_mean+test_scores_std,alpha=0.1,color=‘g‘)
 65     plt.plot(train_sizes,train_scores_mean,‘o--‘,color="r",
 66                 label = "Training score")
 67     plt.plot(train_sizes,test_scores_mean,‘o-‘,color="g",
 68                 label = "Cross_Validation score")
 69     plt.legend(loc="best")
 70     return plt
 71 
 72 cancer = load_breast_cancer()
 73 X = cancer.data
 74 y = cancer.target
 75 print(‘data shape:{0}‘.format(X.shape))
 76 print(‘no.features:{0}‘.format(X.shape[1]))
 77 print(‘features name:{0}‘.format(cancer.feature_names))
 78 print(‘no.postive:{0}‘.format(y[y==1].shape[0]))
 79 print(‘no.negative:{0}‘.format(y[y==0].shape[0]))
 80 # print(cancer.data[0])
 81 
 82 #模型训练 训练集和测试集
 83 X_train,X_test,y_train,y_test = train_test_split(X,y,test_size = 0.2)
 84 
 85 #模型训练
 86 model = LogisticRegression()
 87 model.fit(X_train,y_train)
 88 train_score = model.score(X_train,y_train)
 89 test_score = model.score(X_test,y_test)
 90 print(‘\ntrain score:{}‘.format(train_score))
 91 print(‘test score:{}‘.format(test_score))
 92 
 93 #样本预测
 94 y_pred = model.predict(X_test)
 95 print(‘\nmatchs:{0}/{1}‘.format(np.equal(y_pred,y_test).shape[0],y_test.shape[0]))
 96 
 97 #预测概率 找出预测“自信度”低于90%的样本 阳性，阴性均大于0.1
 98 y_pred_proba = model.predict_proba(X_test)
 99     #找出第一列预测为阴性的概率大于0.1的样本，保存在result中
100 y_pred_proba_0 = y_pred_proba[:,0]>0.1
101 result = y_pred_proba[y_pred_proba_0]
102     #找出第二列预测为阳性的概率大于0.1的样本
103 y_pred_prob_1 = result[:,1]>0.1
104 print(result[y_pred_prob_1])
105 
106 # np.random.seed(3)
107 #模型优化
108 X_train1,X_test1,y_train1,y_test1 = train_test_split(X,y,test_size = 0.2)
109 model_adjust = polynomial_model(degree=2,penalty = ‘l1‘)
110 start = time.clock()
111 model_adjust.fit(X_train1,y_train1)
112 train_score1 = model.score(X_train1,y_train1)
113 cv_score = model.score(X_test1,y_test1)
114 print(‘\ntrain score:{0:.6f}‘.format(train_score1))
115 print(‘test score:{0:.6f}‘.format(cv_score))
116 logistic_regression = model_adjust.named_steps[‘logistic_regression‘]
117 #coef_里面保存的是模型参数，增加二阶多项式后，特征由30-->495个，其实有用的只有94个
118 print(‘\nmodel parameters shape:{0}‘.format(logistic_regression.coef_.shape))
119 print(‘count of non-zero element:{0}‘.format(np.count_nonzero(logistic_regression.coef_)))
120 
121 #首先画出L1作为正则项的一二三阶多项式学习曲线
122 cv = ShuffleSplit(n_splits=10,test_size=0.2,random_state=0)
123 title = ‘Learning_Curves(degree={0},penalty={1})‘
124 degrees = [1,2,3]
125 penalty = [‘l1‘,‘l2‘]
126 index_penalty = 0
127 index_degrees = 0
128 count = 0
129 plt.figure(figsize=(15,4),dpi=100)
130 for i in range(6):
131     plt.subplot(2,len(degrees),i+1)
132     plot_learning_curve(plt,polynomial_model(degree=degrees[index_degrees],133          penalty=penalty[index_penalty]),134          title.format(degrees[index_degrees],penalty[index_penalty]),135          X,y,ylim=(0.8,1.01),cv=cv)
136     if i==len(degrees)-1:
137         index_penalty+=1
138         index_degrees=-1
139     index_degrees+=1
140 
141     
142 
143 
144