机器学习决策树的算法实现

#coding=gbk# DictVectorizer:数据类型转换from sklearn.feature_extraction import DictVectorizer# csv:原始数据放在csv文件中，该package为python自带，不需要安装import csv#引入数据预处理包、决策树包、读写字符串包from sklearn import preprocessingfrom sklearn import treefrom sklearn.externals.six import StringIO#从csv文件中读取数据，并保存到allElectronicsData变量中allElectronicsData = open(r'D:\eclipse\mars\project\DeepLearningBasicsMachineLearning\Datasets\AllElectronics.csv','r')# csv的reader方法按行读取数据reader = csv.reader(allElectronicsData)#next方法读取到csv文件的第一行数据headers = next(reader)#打印第一行数据print(headers)#建两个list，featureList装特征值，labelList装类别标签featureList = []labelList = []#遍历csv文件的每一行for row in reader:    #将类别标签加入到labelList中    labelList.append(row[len(row)-1])    #下面这几步的目的是为了让特征值转化成一种字典的形式，就可以调用sk-learn里面的DictVectorizer，直接将特征的类别值转化成0,1值    rowDict = {}    for i in range(1,len(row)-1):        rowDict[headers[i]] = row[i]    featureList.append(rowDict)print(featureList)#实例化    vec = DictVectorizer()dummyX = vec.fit_transform(featureList).toarray()print("dummyX:"+str(dummyX))print(vec.get_feature_names())# label的转化，直接用preprocessing的LabelBinarizer方法lb = preprocessing.LabelBinarizer()dummyY = lb.fit_transform(labelList)print("dummyY:"+str(dummyY))print("labelList:"+str(labelList))#criterion是选择决策树节点的标准，这里是按照“熵”为标准，即ID3算法；默认标准是gini index，即CART算法。clf = tree.DecisionTreeClassifier(criterion = 'entropy')clf = clf.fit(dummyX,dummyY)print("clf:"+str(clf))#生成dot文件with open("allElectronicInformationGainOri.dot",'w') as f:    f = tree.export_graphviz(clf,feature_names = vec.get_feature_names(),out_file = f)#测试代码，取第1个实例数据，将001->100，即age：youth->middle_aged    oneRowX = dummyX[0,:]print("oneRowX:"+str(oneRowX))newRowX = oneRowXnewRowX[0] = 1newRowX[2] = 0print("newRowX:"+str(newRowX))#预测代码predictedY = clf.predict(newRowX)print("predictedY:"+str(predictedY))
5.9、sk-learn的决策树文档
地址：scikit-learn.org/stable/modules/tree.html
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73