使用scikit-learn实现决策树的算法模板

给出AllElectronics.csv文件，其原始训练数据如下：

RID	age	income	student	credit_rating	class_buy_computer
1	youth	high	no	fair	no
2	youth	high	no	excellent	no
3	middle_aged	high	no	fair	yes
4	senior	medium	no	fair	yes
5	senior	low	yes	fair	yes
6	senior	low	yes	excellent	no
7	middle_aged	low	yes	excellent	yes
8	youth	medium	no	fair	no
9	youth	low	yes	fair	yes
10	senior	medium	yes	fair	yes
11	youth	medium	yes	excellent	yes
12	middle_aged	medium	no	excellent	yes
13	middle_aged	high	yes	fair	yes
14	senior	medium	no	excellent	no

通过scikit-learn实现决策树，对上述数据进行训练，并进行预测。

模板如下：

from sklearn.feature_extraction import DictVectorizer
import csv
from sklearn import preprocessing
from sklearn import tree
from sklearn.externals.six import StringIO
from __builtin__ import str
from _csv import reader
from docutils.nodes import header
#open the csv file
allElectronicsData=open(r'E:\eclipse-jee-neon-3-win32\workspace\DeepLearningBasicsMachineLearning\DecisionTree\data\AllElectronics.csv','rb')
reader=csv.reader(allElectronicsData)
headers=reader.next()
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(featureList)

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

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

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

with open("AllElectronics.dot",'w')as f:
    f=tree.export_graphviz(clf, feature_names=vec.get_feature_names(), out_file=f)

#predict
oneRowX=dummyX[0,:]
print("oneRowX:"+str(oneRowX))

newRowX=oneRowX
newRowX[0]=1
newRowX[2]=0
print("newRowX:"+str(newRowX))
predictedY=clf.predict([newRowX])
print("predictedY:"+str(predictedY))