机器学习----决策树ID3之Python实现（二）

from sklearn.feature_extraction import DictVectorizer
import csv
from sklearn import preprocessing
from sklearn import tree
from sklearn.externals.six import StringIO

allElectronicsData = open("F:\\tree.csv","r")
reader = csv.reader(allElectronicsData)
headers = next(reader)
#第一行数据内容
# print(headers)

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)    
# print(labelList)
# print(featureList)

vec = DictVectorizer()
dummyX = vec.fit_transform(featureList).toarray()
print("dummyX:\n"+str(dummyX))
# print(vec.get_feature_names())
# print("labelList:\n" + str(labelList))

lb = preprocessing.LabelBinarizer()
dummyY = lb.fit_transform(labelList)
print("dummyY:\n" + str(dummyY))

#训练分类器
clf = tree.DecisionTreeClassifier(criterion = 'entropy')
clf = clf.fit(dummyX,dummyY)
print("clf:\n" + str(clf))