《统计学习方法》学习笔记（6）-- 决策树-附代码（sklearn）

决策树，特征选择的三个准则：信息增益（ID3），信息增益比（C4.5），基尼系数（CART）。决策树的生成，决策树的剪枝。

代码：
数据：decision tree.csv

RID,age,income,student,credit_rating,class_buys_computer1,youth,high,no,fair,no2,youth,high,no,excellent,no3,middle_aged,high,no,fair,yes4,senior,medium,no,fair,yes5,senior,low,yes,fair,yes6,senior,low,yes,excellent,no7,middle_aged,low,yes,excellent,yes8,youth,medium,no,fair,no9,youth,low,yes,fair,yes10,senior,medium,yes,fair,yes11,youth,medium,yes,excellent,yes12,middle_aged,medium,no,excellent,yes13,middle_aged,high,yes,fair,yes14,senior,medium,no,excellent,no

代码：

# coding=utf-8from sklearn.feature_extraction import DictVectorizerimport csvfrom sklearn import treefrom sklearn import preprocessingfrom sklearn.externals.six import StringIO# Read in the csv file and put features into list of dict and list of class labelallElectronicsData = open(r'decision_tree.csv', 'rb')reader = csv.reader(allElectronicsData) # 按行读取内容headers = reader.next() # 内容的第一行## print(headers)featureList = []labelList = []for row in reader:    labelList.append(row[len(row)-1]) # 取每一行的最后一个值    rowDict = {}    for i in range(1, len(row)-1):        rowDict[headers[i]] = row[i]    featureList.append(rowDict)# print(featureList) # 如下面每一个字典是数据文件中的一行# # [{'credit_rating': 'fair', 'age': 'youth', 'student': 'no', 'income': 'high'},# # {'credit_rating': 'excellent', 'age': 'youth', 'student': 'no', 'income': 'high'},。。。。# Vetorize featuresvec = DictVectorizer() # sklearn 中提供了一个工具，可以将包含字典类型的list直接转化为数值型的数据。dummyX = vec.fit_transform(featureList) .toarray()# print("dummyX: " + str(dummyX))# print(vec.get_feature_names())# print("labelList: " + str(labelList))# vectorize class labelslb = 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 modelwith open("decision_tree.dot", 'w') as f:    f = tree.export_graphviz(clf, feature_names=vec.get_feature_names(), out_file=f)# graphviz 打印出这个tree来看看，打印的时候将转化前的feature_names找回来。# 上面生成dot文件，可以将其转化为pdf文件可视化出来。# 转化命令：dot -Tpdf decision_tree.dot -o decision_tree.pdfoneRowX = dummyX[0, :]print("oneRowX: " + str(oneRowX))newRowX = oneRowXnewRowX[0] = 1newRowX[2] = 0print("newRowX: " + str(newRowX))predictedY = clf.predict(newRowX)print("predictedY: " + str(predictedY))