朴素贝叶斯-Machine Learining In Action学习笔记

    p0Num, p1Num = zeros(numWords), zeros(numWords)
    p0Denom, p1Denom = 0.0, 0.0

    p0Num, p1Num = ones(numWords), ones(numWords)
    p0Denom, p1Denom = 2.0, 2.0

    p1Vect = p1Num / p1Denom
    p0Vect = p0Num / p0Denom

    p1Vect = log(p1Num / p1Denom)
    p0Vect = log(p0Num / p0Denom)

# -*- coding:utf-8 -*-
from numpy import *
def loadDataSet():
    postingList = [[‘my‘, ‘dog‘, ‘has‘, ‘flea‘, ‘problems‘, ‘help‘, ‘please‘],
                   [‘maybe‘, ‘not‘, ‘take‘, ‘him‘, ‘to‘, ‘dog‘, ‘park‘, ‘stupid‘],
                   [‘my‘, ‘dalmation‘, ‘is‘, ‘so‘, ‘cute‘, ‘I‘, ‘love‘, ‘him‘],
                   [‘stop‘, ‘posting‘, ‘stupid‘, ‘worthless‘, ‘garbage‘],
                   [‘mr‘, ‘licks‘, ‘ate‘, ‘my‘, ‘steak‘, ‘how‘, ‘to‘, ‘stop‘, ‘him‘],
                   [‘quit‘, ‘buying‘, ‘worthless‘, ‘dog‘, ‘food‘, ‘stupid‘]]
    classVec = [0, 1, 0, 1, 0, 1]  # 1 is abusive, 0 not
    return postingList, classVec
# 创建一个在所有文档中出现的不重复词的列表
def createVocabList(dataSet):
    vocabSet = set([])
    for document in dataSet:
        vocabSet = vocabSet | set(document)
    return list(vocabSet)
# 输入词汇列表和某个文档，输出文档向量，向量的每一元素为1或0，分别表示词汇表中的单词在输入文档中是否出现。
def setOfWords2Vec(vocabList, inputSet):
    returnVec = [0] * len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] = 1
        else:
            print "the word: %s is not in my Vocabulary!" % word
    return returnVec
# 基于文档词袋模型改进后的模型
def bagOfWords2VecMN(vocabList, inputSet):
    returnVec = [0] * len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] += 1
    return returnVec
# 输入参数为文档矩阵trainMatrix，以及由每篇文档类别标签所构成的向量trainCategory
def trainNB0(trainMatrix, trainCategory):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory) / float(numTrainDocs)  # 2分类问题，仅0,1构成向量，此处计算1
    p0Num, p1Num = ones(numWords), 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 = log(p1Num / p1Denom)
    p0Vect = log(p0Num / p0Denom)
    return p0Vect, p1Vect, pAbusive
# 要分类的向量vec2Classify
def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    p1 = sum(vec2Classify * p1Vec) + log(pClass1)
    p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
    if p1 > p0:
        return 1
    else:
        return 0
def testingNB():
    listOPosts, listClasses = loadDataSet()
    myVocabList = createVocabList(listOPosts)
    trainMat = []
    for postinDoc in listOPosts:
        trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
    p0V, p1V, pAb = trainNB0(array(trainMat), array(listClasses))
    testEntry = [‘love‘, ‘my‘, ‘dalmation‘]
    thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
    print testEntry, ‘classified as: ‘, classifyNB(thisDoc, p0V, p1V, pAb)
    testEntry = [‘stupid‘, ‘garbage‘]
    thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
    print testEntry, ‘classified as: ‘, classifyNB(thisDoc, p0V, p1V, pAb)
# 文件解析及完整的垃圾邮件测试函数
def textParse(bigString):
    import re
    listOfTokens = re.split(r‘\W*‘, bigString)
    return [tok.lower() for tok in listOfTokens if len(tok) > 2]
def spamTest():
    import random
    # 导入并解析文本文件
    docList, classList, fullText = [], [], []
    for i in range(1, 26):
        wordList = textParse(open(‘email/spam/%d.txt‘ % i, ‘r‘).read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1)
        wordList = textParse(open(‘email/ham/%d.txt‘ % i, ‘r‘).read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    vocabList = createVocabList(docList)
    trainingSet = range(50)
    testSet = []
    # 随机构建训练集(训练集40个，测试集10个)
    for i in range(10):
        randIndex = int(random.uniform(0, len(trainingSet)))
        testSet.append(trainingSet[randIndex])
        del(trainingSet[randIndex])
    trainMat, trainClasses = [], []
    for docIndex in trainingSet:
        trainMat.append(setOfWords2Vec(vocabList, docList[docIndex]))
        trainClasses.append(classList[docIndex])
    p0V, p1V, pSpam = trainNB0(array(trainMat), array(trainClasses))
    # 对测试集分类
    errorCount = 0
    for docIndex in testSet:
        wordVector = setOfWords2Vec(vocabList, docList[docIndex])
        if classifyNB(array(wordVector), p0V, p1V, pSpam) != classList[docIndex]:
            errorCount += 1
    print ‘the error rate is: ‘, float(errorCount) / len(testSet)