image.png
    image.png

    1. def loadDataSet():
    2.     postingList = [['my', 'dog', 'has', 'flea', \
    3.                     'problems', 'help', 'please'],
    4.                    ['maybe', 'not', 'take', 'him', \
    5.                     'to', 'dog', 'park', 'stupid'],
    6.                    ['my', 'dalmation', 'is', 'so', 'cute', \
    7.                     'I', 'love', 'him'],
    8.                    ['stop', 'posting', 'stupid', 'worthless', 'garbage'],
    9.                    ['mr', 'licks', 'ate', 'my', 'steak', 'how', \
    10.                     'to', 'stop', 'him'],
    11.                    ['quit', 'buying', 'worthless', 'dog', 'food', 'stupid']]
    12.     classVec = [0,1,0,1,0,1] #1 代表侮辱性文字，0代表正常言论
    13.     return postingList,classVec
    14. def createVocabList(dataSet):
    15.     vocabSet = set([])
    16.     for document in dataSet:
    17.         vocabSet = vacabSet | set(document)
    18.     return list(vocabSet)
    19. def setOfWords2Vec(vocabList, inputSet):
    20.     returnVec = [0]*len(vocabList)
    21.     for word in inputSet:
    22.         if word in vocabList:
    23.             returnVec[vocabList.index(word)] = 1
    24.         else: print('the word: {}is not in my Vocabulary!' .format(word))
    25.     return returnVec
    26. def trainNB0(trainMatrix, trainCategory):
    27.     numTrainDocs = len(trainMatrix)
    28.     numWords = len(trainMatrix[0])
    29.     pAbusive = sum(trainCategory)/float(numTrainDocs)
    30.     p0Num = zeros(numWords); p1Num = zeros(numWords)
    31.     p0Denom = 0.0; p1Denom = 0.0
    32.     for i in range(numTrainDocs):
    33.         if trainCategory[i] ==1:
    34.             p1Num += trainMatrix[i]
    35.             p1Denom += sum(trainMatrix[i])
    36.         else:
    37.             p0Num += trainMatrix[i]
    38.             p0Denom += sum(trainMatrix[i])
    39.     p1Vect = p1Num/p1Denom
    40.     p0Vect = p0Num/p0Denom
    41.     return p0Vect, p1Vect, pAbusive
    42. def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    43.     p1 = sum(vec2Classify * p1Vec) + log(pClass1)
    44.     p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
    45.     if p1 > p0:
    46.         return 1
    47.     else:
    48.         return 0
    50. def testingNB():    
    51.     listOPosts, listClasses = loadDataSet()
    52.     myVocabList = createVocabList(listOPosts)
    53.     trainMat = []
    54.     for postinDoc in listOPosts:
    55.         trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
    56.     p0V, p1V, pAb = trainNB0(trainMat, listClasses)
    57.     testEntry = ['love', 'my', 'dalmation']
    58.     thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
    59.     print(testEntry,'classified as: ', classifyNB(thisDoc, p0V, p1V, pAb))
    60.     testEntry = ['stupid', 'garbage']
    61.     thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
    62.     print(testEntry,'classified as: ', classifyNB(thisDoc, p0V, p1V, pAb))
    63. def bagOfWords2VecMN(vocabList, inputSet):
    64.     returnVec = [0]*len(vocabList)
    65.     for word in inputSet:
    66.         if word in vocabList:
    67.             returnVec[vocabList.index(word)] += 1
    68.     return returnVec