决策树 实现

决策树实现 
通过预处理基础数据 
然后通过tree里的决策树方法实现二分类问题

其中
AllElectronics.csv 是一个excel表格字段对应数据



#encoding=utf-8
from sklearn.feature_extraction import DictVectorizer
import csv
from sklearn import tree
from sklearn import preprocessing
from sklearn.externals.six import StringIO
allElectronicsData = open(r'AllElectronics.csv','rb')
reader = csv.reader(allElectronicsData)
headers = reader.next()


featureList = []
labelList=[]
for row in reader:
    labelList.append(row[len(row)-1])
    rowDict={}
    for i in range(1, len(row)-1):
        rowDict[headers[i]] = row[i]
    featureList.append(rowDict)



vec = DictVectorizer()
dummyX = vec.fit_transform(featureList).toarray()


lb = preprocessing.LabelBinarizer()
dummyY = lb.fit_transform(labelList)


clf = tree.DecisionTreeClassifier(criterion='entropy')
clf = clf.fit(dummyX, dummyY)
print(str(clf))