朴素贝叶斯算法处理垃圾邮件

代码实现

import numpy as np
import re
import jieba
import string


def createVocabList(dataSet):
    vocabSet = set([])
    for i in dataSet:
        vocabSet = vocabSet | set(i)
    return list(vocabSet)


def setOfWords2Vec(vocabList, inputSet):
    returnVec = [0] * len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] = 1
        else:
            print(f'the word: {word} is not in my Vocabulary!')
    return returnVec


def bagOfWords2VecMN(vocabList, inputSet):
    returnVec = [0] * len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] += 1
    return returnVec


def trainNB0(trainMatrix, trainCategory):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory) / float(numTrainDocs)
    p0Num, p1Num = np.ones(numWords), np.ones(numWords)
    p0Denom, p1Denom = 2.0, 2.0
    for i in range(numTrainDocs):
        if trainCategory[i] == 1:
            p1Num += trainMatrix[i]
            p1Denom += sum(trainMatrix[i])
        else:
            p0Num += trainMatrix[i]
            p0Denom += sum(trainMatrix[i])
    p1Vect, p0Vect = np.log(p1Num / p1Denom), np.log(p0Num / p1Denom)
    return p0Vect, p1Vect, pAbusive


def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    p1 = sum(vec2Classify * p1Vec) + np.log(pClass1)
    p0 = sum(vec2Classify * p0Vec) + np.log(1.0 - pClass1)
    if p1 > p0:
        return 1
    else:
        return 0


def textParse(bigString):
    line = re.sub(r'[a-zA-Z.【】0-9、。，/！…~*\n]', ' ', bigString)
    listOfTokens = jieba.cut(line, cut_all=False)
    return [tok.lower() for tok in listOfTokens if len(tok) > 1]


def spam():
    doc, classList, fullText = [], [], []
    for txt in range(1, 11):
        word = textParse(open('email/spam/%d.txt' % txt, 'r', encoding='gb2312', errors='ignore').read())
        doc.append(word)
        fullText.append(word)
        classList.append(1)
        word = textParse(open('email/ham/%d.txt' % txt, 'r', encoding='gb2312', errors='ignore').read())
        doc.append(word)
        fullText.append(word)
        classList.append(0)
    vocab = createVocabList(doc)

    trainingSet, testSet = list(range(20)), []
    for i in range(5):
        randIndex = int(np.random.uniform(0, len(trainingSet)))
        testSet.append(trainingSet[randIndex])
        del(trainingSet[randIndex])
    trainMat, trainClasses = [], []
    for docIndex in trainingSet:
        trainMat.append(setOfWords2Vec(vocab, doc[docIndex]))
        trainClasses.append(classList[docIndex])
    p0V, p1V, pSpam = trainNB0(np.array(trainMat), np.array(trainClasses))

    errorCount = 0
    for docIndex in testSet:
        wordVector = setOfWords2Vec(vocab, doc[docIndex])
        count = classifyNB(wordVector, p0V, p1V, pSpam)
        print(f'count: {count}')
        print(f'classList: {classList[docIndex]}')
        if classifyNB(np.array(wordVector), p0V, p1V, pSpam) != classList[docIndex]:
            errorCount += 1
            print(f'docIndex: {docIndex}')
            print(f'分类错误的测试集：{doc[docIndex]}')
    print(f'错误率：{float(errorCount) / len(testSet) * 100}%')


if __name__ == '__main__':
    spam()

运行结果

参考链接

贝叶斯垃圾分类

基于朴素贝叶斯的垃圾邮件分类Python实现