ID3决策树python代码

【核心代码】

# -*- coding: utf-8 -*-
"""
Created on Sun Dec 31 20:53:34 2017

@author: Administrator
"""

# -*- coding: utf-8 -*-
"""
Created on Sun Dec 31 14:30:17 2017

@author: Administrator
"""



from sklearn.feature_extraction import DictVectorizer
##涉及到对csv文件的读取，故导入csv接口
import csv
from sklearn import preprocessing
from sklearn import tree
from sklearn.externals.six import StringIO
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
##将csv文件中的数据读取到变量allElectronicsData中
traindata=open(r'D:\Spyderworkspcce\data\atrain.csv')


##csv自带的reader可以按行读取allElectronicsData中的数据
reader=csv.reader(traindata)

##读取第一行数据即title
headers=reader.next()

#headers2=readertest.next()


#print headers

featureList = []
labelList = []


for row in reader:
    labelList.append(row[len(row)-1])
    rowDict = {}
    for i in range(0,len(row)-1):
        # print row[i]
        rowDict[headers[i]] = row[i]
        # print "rowDict:",rowDict
    featureList.append(rowDict)
    
 

###  list中的每一个字典对应原始数据中的一行数据 <featureList[0]对应第1行原始数据>

vec= DictVectorizer()
train_x = vec.fit_transform(featureList).toarray()
#定义样本训练属性集和测试属性集
train_xx=train_x[0:30164]
test_xx=train_x[30164:]

lb = preprocessing.LabelBinarizer()
train_y=lb.fit_transform(labelList)
#定义样本训练标签集和测试标签集
train_yy=train_y[0:30164]
test_yy=train_y[30164:]


model = DecisionTreeClassifier(criterion='entropy',min_samples_leaf=3)
model = model.fit(train_xx, train_yy)
##
##
y_train_pred = model.predict(train_xx)
y_test_pred = model.predict(test_xx)
##print y_train_pred
print '测试集预测类标 ' str(y_test_pred)
###
acc_train = accuracy_score(train_yy, y_train_pred)
acc_test = accuracy_score(test_yy, y_test_pred)
###
print '\t训练集准确率: %.4f%%' % (100*acc_train)
print '\t测试集准确率: %.4f%%\n' % (100*acc_test)

predict