from sklearn.feature_extraction import DictVectorizer
import csv
from sklearn import tree
from sklearn import preprocessing
from sklearn.externals.six import StringIO
from xml.sax.handler import feature_external_ges
from numpy.distutils.fcompiler import dummy_fortran_file

# Read in the csv file and put features into list of dict and list of class label
allElectronicsData = 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)-1
for 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=>ID3
clf = tree.DecisionTreeClassifier(criterion='entropy')
clf = clf.fit(dummX, dummY)
print("clf:"+str(clf))


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


#對于新的數(shù)據(jù)怎樣來查看它的分類
oneRowX = dummX[0,:]
print("oneRowX: "+str(oneRowX))
newRowX = oneRowX
newRowX[0] = 1
newRowX[2] = 0

predictedY = clf.predict(newRowX)
print("predictedY: "+ str(predictedY))