【机器学习】决策树算法（二）— 代码实现

#coding=utf8
‘’’
Created on 2018年11月4日

@author: xiaofengyang
决策树算法：ID3算法
‘’’
from sklearn.feature_extraction import DictVectorizer
import csv
from sklearn import tree
from sklearn.externals.six import StringIO
from sklearn import preprocessing

## 1.读取csv 文件数据
allDate=open(‘AllElectronics.csv’)
reader=csv.reader(allDate)
##2.读取csv文件的头部
header=reader.next()
##3.对数据预处理
featureList=[]
laberList=[]

for item in reader:
## 将结果存入laberList中
laberList.append(item[len(item)-1])
## 创建字典存放属性名称与对应值
itemDit={}
for i in range(1,len(item)-1):
itemDit[header[i]]=item[i]
#将数据存入featureList
featureList.append(itemDit)
##4.数据的预处理问题
dic=DictVectorizer()
dummX=dic.fit_transform(featureList).toarray()

print str(dummX)

获取属性对应的值

print dic.get_feature_names()

##5.对于结果数据进行处理
lb=preprocessing.LabelBinarizer()
dummY=lb.fit_transform(laberList)

print dummY

##6.建立决策树
tcf=tree.DecisionTreeClassifier(criterion=‘entropy’)
clf=tcf.fit(dummX,dummY)

##7.预测
oneRox=dummX[0,:]
oneRox[4]=0
oneRox[9]=1
print oneRox

predict_data=clf.predict([oneRox])
print str(predict_data)

附件：数据集
RID,age,income,student,credit_rating,class_buys_computer
1,youth,high,no,fair,no
2,youth,high,no,excellent,no
3,middle_aged,high,no,fair,yes
4,senior,medium,no,fair,yes
5,senior,low,yes,fair,yes
6,senior,low,yes,excellent,no
7,middle_aged,low,yes,excellent,yes
8,youth,medium,no,fair,no
9,youth,low,yes,fair,yes
10,senior,medium,yes,fair,yes
11,youth,medium,yes,excellent,yes
12,middle_aged,medium,no,excellent,yes
13,middle_aged,high,yes,fair,yes
14,senior,medium,no,excellent,no