决策树练习

'''
@author :Eric-chen
@contact:809512722@qq.com
@time   :2017/12/19 16:19
@desc   :
'''
from sklearn.feature_extraction import DictVectorizer
import csv
from sklearn import preprocessing
from sklearn import tree
from sklearn.externals.six import StringIO

#read in the csv file and put features in a list of dict and list of class label
allData=open(r'F:pythonday01AllElectronics.csv','rb')
reader=csv.reader(allData)
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):
        # print (row[i])
        # print ("==")
        rowDict[headers[i]]=row[i]
        # print (rowDict)
    featureList.append(rowDict)
print (featureList)

# Vetorize features
vec=DictVectorizer()
dummyX=vec.fit_transform(featureList).toarray()
print ("dummyX:"+str(dummyX))
print (vec.get_feature_names())
print ("labellist:"+str(labelList))
# Vectorize class labels
lb=preprocessing.LabelBinarizer()
dummY=lb.fit_transform(labelList)
print("dummY"+str(dummY))

# Using decision tree for classification
clf=tree.DecisionTreeClassifier(criterion='entropy')
clf=clf.fit(dummyX,dummY)
print("clf:"+str(clf))

# Visualize model
with open("allData.dot",'w') as f:
    f=tree.export_graphviz(clf,feature_names=vec.get_feature_names(),out_file=f)
oneRowX=dummyX[0,:]
print ("oneRowX:"+str(oneRowX))
newRowX=oneRowX
newRowX[0]=1
newRowX[2]=0

print("newRowx:"+str(newRowX))
predictedY=clf.predict(newRowX.reshape(1, -1))
print("predictedY"+str(predictedY))