机器学习实战_初识朴素贝叶斯算法_理解其python代码（二）

python 基础:

中间还有pickle二进制读取文件部分的error这个可以参见：机器学习实战初识决策树（ID3）算法理解其python代码（二）的第四部分

append: Appends object at end.：

x = [1, 2, 3]
x.append([4, 5])
print (x)
[1, 2, 3, [4, 5]]

extend: Extends list by appending elements from the iterable.：

x = [1, 2, 3]
x.extend([4, 5])
print (x)
[1, 2, 3, 4, 5]

测试算法：

import random
import re
from numpy import array

import LoadData
import bayes

def textParse(bigString):#接收大字符串，解析处理后返回字符串列表（去掉少于两个字符的字符串，并将所有字符串转换为小写）

    listOfTokens = re.compile('\\W*')
    listOfTokens = listOfTokens.split(bigString)#compile()split(r'\W*',bigString)#正则表达式re模块，详见之前的文章
    return [tok.lower() for tok in listOfTokens if len(tok)>0]#列表解析
'''这里出现错误最多的也还是Py2.x和Py3.x的不同导致的问题'''
def spamTest():
    docList = []
    classList = []
    fullText = []
    #读取25*2个文本
    for i in range(1,26):
        wordList = textParse(open('email/spam/%d.txt' % i,'rb').read().decode('GBK','ignore') )#1，UnicodeDecodeError: 'gbk' codec can't decode byte 0xae in position 199: illegal multibyte sequence
        #加上后面的后綴，因为有可能文件中存在类似“�”非法字符。
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1)
        wordList = textParse(open('email/ham/%d.txt' % i,'rb').read().decode('GBK','ignore') )#UnicodeDecodeError: 'gbk' codec can't decode byte 0xae in position 199: illegal multibyte sequence
        #这里还是Pickle的二进制问题，所以要加上‘rb’，其他nicodeDecodeError同上
        #注意append和extend的区别
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    vocabList = LoadData.createVocabList(docList)#得到参考用的词典
    #随机构建训练集
    trainingSet = list(range(50))
    testSet = []
    for i in range(10):#得到随机测试集
        randIndex = int(random.uniform(0,len(trainingSet)))
        testSet.append(trainingSet[randIndex])
        del(trainingSet[randIndex])#TypeError: 'range' object doesn't support item deletion，因为是python3中range不返回数组对象，而是返回range对象，所以trainingSet = list(range(50))而不是range(50)
    trainMat = [];trainClasses = []
    for docIndex in trainingSet:
        trainMat.append(LoadData.setOfWords2Vec(vocabList,docList[docIndex]))
        trainClasses.append(classList[docIndex])
    p0V,p1V,pSpam = bayes.trainNB0(array(trainMat),array(trainClasses))#计算相应的概率
    errorCount = 0
    for docIndex in testSet:
        wordVector = LoadData.setOfWords2Vec(vocabList,docList[docIndex])
        if bayes.classifyNB(array(wordVector),p0V,p1V,pSpam) != classList[docIndex]:#判断文本的类别
            errorCount+=1
    print('the error rate is :',float(errorCount)/len(testSet))