import numpy as np
#返回样本数据集
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]
return postingList,classVec
#提取样本数据中的单词,构成词汇表
def createVocabList(dataSet):
vocabSet = set([])
for document in dataSet:
vocabSet = vocabSet | set(document)
return list(vocabSet)
#传入单词表和待分析的数据,讲数据转为向量,这里记录每行样本的单词是否出现
def setOfWords2Vec(vocabList, inputSet):
retVocabList = [0] * len(vocabList)
for word in inputSet:
if word in vocabList:
retVocabList[vocabList.index(word)] = 1
else:
print 'word ',word ,'not in dict'
return retVocabList
#这里是每个样本的出现次数
def bagOfWords2VecMN(vocabList, inputSet):
returnVec = [0]*len(vocabList)
for word in inputSet:
if word in vocabList:
returnVec[vocabList.index(word)] += 1
return returnVec
#带入样本数据和结果,计算样本对于某一类别的出现次数
#这个求出不同组中,每个词出现的概率
def trainNB0(trainMatrix,trainCatergory):
numTrainDoc = len(trainMatrix)
numWords = len(trainMatrix[0])
pAbusive = sum(trainCatergory)/float(numTrainDoc)
#防止多个概率的成绩当中的一个为0
p0Num = np.ones(numWords)
p1Num = np.ones(numWords)
p0Denom = 2.0
p1Denom = 2.0
for i in range(numTrainDoc):
if trainCatergory[i] == 1:
p1Num +=trainMatrix[i]
p1Denom += sum(trainMatrix[i])
else:
p0Num +=trainMatrix[i]
p0Denom += sum(trainMatrix[i])
#处于精度的考虑,否则很可能到限归零,因为可能有太多项都为0
#避免下溢出和浮点数舍入导致的错误
p1Vect = np.log(p1Num/p1Denom)
p0Vect = np.log(p0Num/p0Denom)
return p0Vect,p1Vect,pAbusive
#这里也就相当于log了一下
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
#测试方法
def testingNB():
listOPosts,listClasses = loadDataSet()
myVocabList = createVocabList(listOPosts)
trainMat=[]
for postinDoc in listOPosts:
trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
p0V,p1V,pAb = trainNB0(np.array(trainMat),np.array(listClasses))
testEntry = ['love', 'my', 'dalmation']
thisDoc = np.array(setOfWords2Vec(myVocabList, testEntry))
print testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb)
testEntry = ['stupid', 'garbage']
thisDoc = np.array(setOfWords2Vec(myVocabList, testEntry))
print testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb)
def main():
testingNB()
if __name__ == '__main__':
main()