自学教程：python

import numpy as npimport pandas as pdfrom sklearn import treeimport graphviz# x，y是sklearn中需要拟合的数据x = np.array(exam_train)y = np.array(classes_train)clf = tree.DecisionTreeClassifier(criterion='entropy', class_weight='balanced', max_depth=25)clf = clf.fit(x, y)dot_data = tree.export_graphviz(clf, out_file=None, feature_names=None, filled=True, rounded=True)  # 重要参数可定制graph = graphviz.Source(dot_data)graph.render(view=True, format="pdf", filename="decisiontree_pdf")

age look income orderly targetolder ugly low yes noyoung ugly high no noyoung handsome low no noyoung handsome high yes yesyoung handsome medium yes yesyoung handsome medium no no

# -*- coding:utf-8*-# 将字典 转化为 sklearn 用的数据形式 数据型 矩阵from sklearn.feature_extraction import DictVectorizerimport csvfrom sklearn import preprocessingfrom sklearn import treeallElectronicsData = open('c:/pic/data/tree.csv','rb')reader = csv.reader(allElectronicsData)header = reader.next()# print header## 数据预处理featureList = []labelList = []for row in reader:    # print row[-1]    labelList.append(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[header[i]] = row[i]    featureList.append(rowDict)for each in featureList:    print each# Vectorize featuresvec = 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()clf = clf.fit(dummyX,dummyY)print("clf:"+str(clf))# 导入相关函数，可视化决策树# 导出的结果是一个dot文件(在系统默认路劲)，需要安装Graphviz才能将它住哪华为PDF或png格式# 输出的dot文件可以使用graphvize软件转为PDF，graphvize安装目录中的bin目录放入到环境变量的Path中# 使用如下命令#cmd# dot -Tpdf  c:/tree.dot -o c:/tree.pdf#下载地址：http://www.graphviz.org/Download_windows.php#生成dot文件with open("c:/tree.dot",'w') as f:    f = tree.export_graphviz(clf, feature_names= vec.get_feature_names(),out_file= f)