#!/usr/bin/env python
# -*- coding: utf-8 -*-
from sklearn.feature_extraction import DictVectorizer
import csv
from sklearn import tree
from sklearn import preprocessing
from sklearn.externals.six import StringIO

# Read in the csv file and put features into list of dict and list of class label
allElectronicsData = open(r‘AllElectronics.csv‘, ‘rb‘)
reader = csv.reader(allElectronicsData)
headers = reader.next()

print(headers)

featureList = []
labelList = []

for row in reader:
    labelList.append(row[len(row)-1]) # 取得每一行最後一個值 標簽
    rowDict = {} #取得每一行的值 包含有字典的list
    for i in range(1, len(row)-1):
        rowDict[headers[i]] = row[i]
    featureList.append(rowDict)

print(featureList)

# Vetorize features
vec = DictVectorizer()#將字典轉換成00100的形式（1000）
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()#將標簽轉換成0,1
dummyY = lb.fit_transform(labelList)
print("dummyY: " + str(dummyY))

# Using decision tree for classification
# clf = tree.DecisionTreeClassifier()
clf = tree.DecisionTreeClassifier(criterion=‘entropy‘)#信息熵
clf = clf.fit(dummyX, dummyY)
print("clf: " + str(clf))


# Visualize model
with open("allElectronicInformationGainOri.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)
print("predictedY: " + str(predictedY))

決策樹（Decision Tree）SkLearn