机器学习算法的python实现之扫黄神器-朴素贝叶斯分类器的实现

机器学习算法的python实现之扫黄神器-朴素贝叶斯分类器的实现2015-10-081.背景

以前我在外面公司实习的时候，一个大神跟我说过，学计算机就是要一个一个贝叶斯公式的套用来套用去。嗯，现在终于用到了。朴素贝叶斯分类器据说是好多扫黄软件使用的算法，贝叶斯公式也比较简单，大学做概率题经常会用到。核心思想就是找出特征值对结果影响概率最大的项。公式如下：

什么是朴素贝叶斯，就是特征值相互独立互不影响的情况。贝叶斯可以有很多变形，这里先搞一个简单的，以后遇到复杂的再写。

2.数据集

摘自机器学习实战。

[["my","dog","has","flea","problems","help","please"], 0

["maybe","not","take","him","to","dog","park","stupid"], 1

["my","dalmation","is","so","cute","I","love","him"], 0

["stop","posting","stupid","worthless","garbage"], 1

["mr","licks","ate","my","steak","how","to","stop","him"], 0

["quit","buying","worthless","dog","food","stupid"]] 1

以上是六句话，标记是0句子的表示粗口句，标记是1句子的表示为粗口。我们通过分析每个句子中的每个词，在粗口句或是正常句出现的概率，可以找出那些词是粗口。

3.代码

#以矩阵形式创建数据集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

#将矩阵内容添加到列表，set获取list中不重复的元素def createVocabList（dataSet）:vocabSet = set（[]）#create empty setfor document in dataSet:vocabSet = vocabSet | set（document） #union of the two setsreturn list（vocabSet）

#判断list中每个词在总共词语list中的位置def setOfWords2Vec（vocabList, inputSet）:returnVec = [0]*len（vocabList）for word in inputSet:if word in vocabList:returnVec[vocabList.index（word）] = 1else: print "the word: %s is not in my Vocabulary！" % wordreturn returnVec

def trainNB0（trainMatrix,trainCategory）:numTrainDocs = len（trainMatrix）numWords = len（trainMatrix[0]）pAbusive = sum（trainCategory）/float（numTrainDocs）#脏句的比例 p0Num = zeros（numWords）; p1Num = zeros（numWords） #zero是numpy带的函数，zeros（i）长度为i的listp0Denom = 0.0; p1Denom = 0.0for i in range（numTrainDocs）:if trainCategory[i] == 1:#如果是粗口句，每个词在p1num加一p1Num += trainMatrix[i]p1Denom += sum（trainMatrix[i]）else:p0Num += trainMatrix[i]p0Denom += sum（trainMatrix[i]） p1Vect = p1Num/p1Denom#粗口字概率p0Vect = p0Num/p0Denom return p0Vect,p1Vect,pAbusive