使用朴素贝叶斯过滤垃圾邮件

#!/usr/bin/python
# -*- coding: utf-8 -*-
#__author__ : stray_camel
#pip_source : https://mirrors.aliyun.com/pypi/simple
import sys,os

class Bayes():
    def __init__(self, 
    absPath:"Directory of the current file"== os.path.dirname(os.path.abspath(__file__)),
    ):
        self.absPath = absPathCopy

 #contain all documents and list without duplicate words
    def createVocabList(self, 
    dataSet:dict(type="", help = "the source data"),
    )->dict(type=list, help = "Deduplicated list"):
        vocabSet=set([])#creat an empty set,'set' is a list without duplicate words
        for document in dataSet:
            vocabSet=vocabSet|set(document) #create an union of two sets
        return list(vocabSet)Copy

    #determine if a term appears in the documents
    def setOfWords2Vec(self, 
    vocabList = dict(type="", help="a glossary "), 
    inputSet = dict(type="", help="The word you want to detect"), 
    )-> = dict(type="", help="Word vector"):
        returnVec = [0]*len(vocabList)
        for word in inputSet:
            if word in vocabList:
                returnVec[vocabList.index(word)] = 1
            else:
                print("单词: %s 不在我的词汇里面!" % word)#Returns a document vector indicating whether a word has appeared 1/0 in the input document
        return returnVecCopy

    #naive bayes classfication training function
    def trainNB0(self,trainMatrix,trainCategory):
        numTrainDocs=len(trainMatrix)
        numWords=len(trainMatrix[0])
        pAbusive=sum(trainCategory)/float(numTrainDocs)
        p0Num = ones(numWords)
        p1Num = ones(numWords)
        p0Denom = 2.0
        p1Denom = 2.0
        for i in range(numTrainDocs):#Iterate through all documents
            if trainCategory[i]==1:
                p1Num+=trainMatrix[i]
                p1Denom+=sum(trainMatrix[i])
            else:
                p0Num+=trainMatrix[i]
                p0Denom+=sum(trainMatrix[i])

        p1Vect = log(p1Num / p1Denom)
        p0Vect = log(p0Num / p0Denom)
        return p0Vect, p1Vect, pAbusiveCopy

 #filtering email, training+testing
    def spamTest(self):
        docList=[]; classList=[]; fullText=[]
        # iterate through all the test files, A total of 26
        for i in range(1,26):
            wordList = self.textParse(open(self.absPath+'/email/spam/%d.txt' % i, "rb").read().decode('GBK', 'ignore'))
            docList.append(wordList)
            fullText.extend(wordList)
            classList.append(1)
            wordList = self.textParse(open(self.absPath+'/email/ham/%d.txt' % i, "rb").read().decode('GBK', 'ignore'))
            docList.append(wordList)
            fullText.extend(wordList)
            classList.append(0)
        vocabList=self.createVocabList(docList)

        trainingSet = list(range(50))
        testSet=[]

        for i in range(10):
            # random.uniform(x,y)  Returns a float random number from x to y
            randIndex=int(random.uniform(0,len(trainingSet)))
            testSet.append(trainingSet[randIndex])
            del(trainingSet[randIndex])
        trainMat=[]; trainClasses=[]
        for docIndex in trainingSet:
            trainMat.append(self.setOfWords2Vec(vocabList,docList[docIndex]))
            trainClasses.append(classList[docIndex])
        p0V,p1V,pSpam=self.trainNB0(np.array(trainMat),np.array(trainClasses))
        errorCount=0
        for docIndex in testSet:
            wordVector=self.setOfWords2Vec(vocabList,docList[docIndex])
            if self.classifyNB(np.array(wordVector),p0V,p1V,pSpam)!=classList[docIndex]:
                errorCount+=1
                print("分类错误的是： %s" %vocabList[docIndex])
        print('错误率是:',float(errorCount)/len(testSet))
Copy

if __name__ == "__main__":
    test = Bayes()
    test.spamTest()Copy

分类错误的是：
scifinance now automatically generates gpu-enabled pricing & risk model source code that runs up to 50-300
分类错误的是： tended in the latest release. this includes:

错误率是: 0.2Copy