# -*- coding: utf-8 -*-"""Created on Mon Aug 21 10:57:29 2017@author: 飄的心"""#過(guò)濾式特征選擇#根據(jù)方差進(jìn)行選擇，方差越小，代表該屬性識(shí)別能力很差，可以剔除from sklearn.feature_selection import VarianceThresholdx=[[100,1,2,3],  [100,4,5,6],  [100,7,8,9],  [101,11,12,13]]selector=VarianceThreshold(1) #方差閾值值，selector.fit(x)selector.variances_ #展現(xiàn)屬性的方差selector.transform(x)#進(jìn)行特征選擇selector.get_support(True) #選擇結(jié)果后，特征之前的索引selector.inverse_transform(selector.transform(x)) #將特征選擇后的結(jié)果還原成原始數(shù)據(jù)                         #被剔除掉的數(shù)據(jù)，顯示為0#單變量特征選擇from sklearn.feature_selection import SelectKBest,f_classifx=[[1,2,3,4,5],  [5,4,3,2,1],  [3,3,3,3,3],  [1,1,1,1,1]]y=[0,1,0,1]selector=SelectKBest(score_func=f_classif,k=3)#選擇3個(gè)特征，指標(biāo)使用的是方差分析F值selector.fit(x,y)selector.scores_ #每一個(gè)特征的得分selector.pvalues_selector.get_support(True) #如果為true，則返回被選出的特征下標(biāo)，如果選擇False，則              #返回的是一個(gè)布爾值組成的數(shù)組，該數(shù)組只是那些特征被選擇selector.transform(x)#包裹時(shí)特征選擇from sklearn.feature_selection import RFEfrom sklearn.svm import LinearSVC #選擇svm作為評(píng)定算法from sklearn.datasets import load_iris #加載數(shù)據(jù)集iris=load_iris()x=iris.datay=iris.targetestimator=LinearSVC()selector=RFE(estimator=estimator,n_features_to_select=2) #選擇2個(gè)特征selector.fit(x,y)selector.n_features_  #給出被選出的特征的數(shù)量selector.support_   #給出了被選擇特征的maskselector.ranking_   #特征排名，被選出特征的排名為1#注意：特征提取對(duì)于預(yù)測(cè)性能的提升沒(méi)有必然的聯(lián)系，接下來(lái)進(jìn)行比較；from sklearn.feature_selection import RFEfrom sklearn.svm import LinearSVCfrom sklearn import cross_validationfrom sklearn.datasets import load_iris#加載數(shù)據(jù)iris=load_iris()X=iris.datay=iris.target#特征提取estimator=LinearSVC()selector=RFE(estimator=estimator,n_features_to_select=2)X_t=selector.fit_transform(X,y)#切分測(cè)試集與驗(yàn)證集x_train,x_test,y_train,y_test=cross_validation.train_test_split(X,y,                  test_size=0.25,random_state=0,stratify=y)x_train_t,x_test_t,y_train_t,y_test_t=cross_validation.train_test_split(X_t,y,                  test_size=0.25,random_state=0,stratify=y)clf=LinearSVC()clf_t=LinearSVC()clf.fit(x_train,y_train)clf_t.fit(x_train_t,y_train_t)print('origin dataset test score:',clf.score(x_test,y_test))#origin dataset test score: 0.973684210526print('selected Dataset:test score:',clf_t.score(x_test_t,y_test_t))#selected Dataset:test score: 0.947368421053import numpy as npfrom sklearn.feature_selection import RFECVfrom sklearn.svm import LinearSVCfrom sklearn.datasets import load_irisiris=load_iris()x=iris.datay=iris.targetestimator=LinearSVC()selector=RFECV(estimator=estimator,cv=3)selector.fit(x,y)selector.n_features_selector.support_selector.ranking_selector.grid_scores_#嵌入式特征選擇import numpy as npfrom sklearn.feature_selection import SelectFromModelfrom sklearn.svm import LinearSVCfrom sklearn.datasets import load_digitsdigits=load_digits()x=digits.datay=digits.targetestimator=LinearSVC(penalty='l1',dual=False)selector=SelectFromModel(estimator=estimator,threshold='mean')selector.fit(x,y)selector.transform(x)selector.threshold_selector.get_support(indices=True)#scikitlearn提供了Pipeline來(lái)講多個(gè)學(xué)習(xí)器組成流水線，通常流水線的形式為：將數(shù)據(jù)標(biāo)準(zhǔn)化，#--》特征提取的學(xué)習(xí)器————》執(zhí)行預(yù)測(cè)的學(xué)習(xí)器，除了最后一個(gè)學(xué)習(xí)器之后，#前面的所有學(xué)習(xí)器必須提供transform方法，該方法用于數(shù)據(jù)轉(zhuǎn)化（如歸一化、正則化、#以及特征提取#學(xué)習(xí)器流水線（pipeline）from sklearn.svm import LinearSVCfrom sklearn.datasets import load_digitsfrom sklearn import cross_validationfrom sklearn.linear_model import LogisticRegressionfrom sklearn.pipeline import Pipelinedef test_Pipeline(data):  x_train,x_test,y_train,y_test=data  steps=[('linear_svm',LinearSVC(C=1,penalty='l1',dual=False)),      ('logisticregression',LogisticRegression(C=1))]  pipeline=Pipeline(steps)  pipeline.fit(x_train,y_train)  print('named steps',pipeline.named_steps)  print('pipeline score',pipeline.score(x_test,y_test))if __name__=='__main__':  data=load_digits()  x=data.data  y=data.target  test_Pipeline(cross_validation.train_test_split(x,y,test_size=0.25,                  random_state=0,stratify=y))