python利用sklearn包编写决策树源代码

from sklearn.feature_extraction import DictVectorizerimport csvfrom sklearn import treefrom sklearn import preprocessingfrom sklearn.externals.six import StringIOfrom xml.sax.handler import feature_external_gesfrom numpy.distutils.fcompiler import dummy_fortran_file# Read in the csv file and put features into list of dict and list of class labelallElectronicsData = open(r'E:/DeepLearning/resources/AllElectronics.csv', 'rt')reader = csv.reader(allElectronicsData)headers = next(reader)featureList = []lableList = []for row in reader:lableList.append(row[len(row)-1])rowDict = {}#不包括len(row)-1for i in range(1,len(row)-1):rowDict[headers[i]] = row[i]featureList.append(rowDict)print(featureList)vec = DictVectorizer()dummX = vec.fit_transform(featureList).toarray()print(str(dummX))lb = preprocessing.LabelBinarizer()dummY = lb.fit_transform(lableList)print(str(dummY))#entropy=>ID3clf = tree.DecisionTreeClassifier(criterion='entropy')clf = clf.fit(dummX, dummY)print("clf:"+str(clf))#可视化treewith open("resultTree.dot",'w')as f:f = tree.export_graphviz(clf, feature_names=vec.get_feature_names(),out_file = f)#对于新的数据怎样来查看它的分类oneRowX = dummX[0,:]print("oneRowX: "+str(oneRowX))newRowX = oneRowXnewRowX[0] = 1newRowX[2] = 0predictedY = clf.predict(newRowX)print("predictedY: "+ str(predictedY))