决策树

# -*- coding: utf-8 -*-
"""
Created on Sun Oct 22 22:01:49 2017

@author: wilcohuang
"""

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 feature into list of dict and list of class label
#这里要注意Python读取windows文件的方式，可以用'D:/'或者r'D:/'，如果路径有中文必须转化为gbk编码，因为windows使用文件都是gbk编码
allElectronicsData = open(r'C:\Users\wilcohuang\Desktop\\机器学习笔记\AllElectronics.csv'.decode('utf8').encode('gbk'), '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)

#Vectorize 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()
dummyY = lb.fit_transform(labelList)
print("dummyY: " + str(dummyY))

#Using decision tree for classification
# clf = tree.DecisionTreeClassifier()
clf = tree.DecisionTreeClassifier(criterion='entropy')
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)

#cmd
#dot -Tpdf allElectronicInformationGainOri.dot -o allElectronicInformationGainOri.pdf 

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

newRowX = oneRowX
newRowX[0] = 1;
newRowX[2] = 0;
print("newRowX: " + str(newRowX))

paramRow = []
paramRow.append(newRowX)
print("paramRow: " + str(paramRow))

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