1 import numpy as np
2 import re
3
4 #词表到向量的转换函数
5 def loadDataSet():
6 postingList = [[‘my‘, ‘dog‘, ‘has‘, ‘flea‘, ‘problems‘, ‘help‘, ‘please‘],
7 [‘maybe‘, ‘not‘, ‘take‘, ‘him‘, ‘to‘, ‘dog‘, ‘park‘, ‘stupid‘],
8 [‘my‘, ‘dalmation‘, ‘is‘, ‘so‘, ‘cute‘, ‘I‘, ‘love‘, ‘him‘],
9 [‘stop‘, ‘posting‘, ‘stupid‘, ‘worthless‘, ‘garbage‘],
10 [‘mr‘, ‘licks‘, ‘ate‘, ‘my‘, ‘steak‘, ‘how‘, ‘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
15 #创建一个包含在所有文档中出现的不重复词的列表
16 def createVocabList(dataSet):
17 vocabSet = set([]) #创建一个空集
18 for document in dataSet:
19 vocabSet = vocabSet | set(document) #创建两个集合的并集
20 return list(vocabSet)
21
22 #词集模型：文档中的每个词在词集中只出现一次
23 def setOfWords2Vec(vocabList, inputSet):
24 returnVec = [0] * len(vocabList) #创建长度与词汇表相同，元素都为0的向量
25 for word in inputSet:
26 if word in vocabList: #将出现在文档中的词汇在词汇表中对应词汇位置置1
27 returnVec[vocabList.index(word)] = 1
28 else:
29 print ("the word: %s isn‘t in my Vocabulary" % (word))
30 return returnVec
31
32 #词袋模型: 文档中的每个词在词袋中可以出现多次
33 def bagOfWords2VecMN(vocabList, inputSet):
34 returnVec = [0] * len(vocabList)
35 for word in inputSet:
36 if word in vocabList:
37 returnVec[vocabList.index(word)] += 1
38 return returnVec
39
40 #朴素贝叶斯分类器训练函数
41 def trainNB0(trainMatrix, trainCategory):
42 numTrainDocs = len(trainMatrix)
43 numWords = len(trainMatrix[0])
44 pAbusive = sum(trainCategory)/float(numTrainDocs)
45 #p0Num = np.zeros(numWords)
46 #p1Num = np.zeros(numWords)
47 #p0Denom = 0.0
48 #p1Denom = 0.0
49 p0Num = np.ones(numWords) #|利用贝叶斯分类器对文档进行分类时，要计算多个概率的乘积以获得文档属于某个类别的概率，
50 p1Num = np.ones(numWords) #|如果其中一个概率值为0，那么最后的乘积也为0.
51 p0Denom = 2.0 #|为降低这种影响，可以将所有词的出现数初始化为1，并将分母初始化为2
52 p1Denom = 2.0 #|(拉普拉斯平滑)
53 for i in range(numTrainDocs):
54 if trainCategory[i] == 1:
55 p1Num += trainMatrix[i]
56 p1Denom += sum(trainMatrix[i])
57 else:
58 p0Num += trainMatrix[i]
59 p0Denom += sum(trainMatrix[i])
60 #p1Vect = p1Num/p1Denom
61 #p0Vect = p0Num/p0Denom
62 p1Vect = np.log(p1Num/p1Denom) #|当太多很小的数相乘时，程序会下溢出，对乘积取自然对数可以避免下溢出或浮点数舍入导致的错误
63 p0Vect = np.log(p0Num/p0Denom) #|同时，采用自然对数进行处理不会有任何损失。ln(a*b)=ln(a)+ln(b)
64 return p0Vect, p1Vect, pAbusive
65
66 #朴素贝叶斯分类函数
67 def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
68 p1 = sum(vec2Classify * p1Vec) + np.log(pClass1) #元素相乘得到概率值
69 p0 = sum(vec2Classify * p0Vec) + np.log(1.0 - pClass1)
70 if p1 > p0:
71 return 1
72 else:
73 return 0
74
75 #便利函数，封装所有操作
76 def testingNB():
77 listOposts, listClasses = loadDataSet()
78 myVocabList = createVocabList(listOposts)
79 trainMat = []
80 for postinDoc in listOposts:
81 trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
82 p0V, p1V, pAb = trainNB0(np.array(trainMat), np.array(listClasses)) #获取训练文档返回的概率值
83 testEntry = [‘love‘, ‘my‘, ‘dalmation‘] #正面测试文档
84 thisDoc = np.array(setOfWords2Vec(myVocabList, testEntry)) #词汇表
85 print (testEntry, ‘classified as:‘, classifyNB(thisDoc, p0V, p1V, pAb)) #分类结果
86 testEntry = [‘stupid‘, ‘garbage‘] #侮辱性测试文档
87 thisDoc = np.array(setOfWords2Vec(myVocabList, testEntry)) #词汇表
88 print (testEntry, ‘classified as:‘, classifyNB(thisDoc, p0V, p1V, pAb)) #分类结果
89
90 #文件解析
91 def textParse(bigString):
92 listOfTokens = re.split(r‘\W+‘, bigString) #原书中的模式为\W*,匹配0个或多个
93 return [tok.lower() for tok in listOfTokens if len(tok) > 2]
94
95 #完整的垃圾邮件测试函数
96 def spamTest():
97 docList=[]; classList=[]; fullText=[]
98 for i in range(1, 26): #导入并解析文件
99 wordList = textParse(open(‘email/spam/%d.txt‘ % i).read())
100 docList.append(wordList)
101 fullText.extend(wordList)
102 classList.append(1)
103 wordList = textParse(open(‘email/ham/%d.txt‘ % i).read())
104 docList.append(wordList)
105 fullText.extend(wordList)
106 classList.append(0)
107 vocabList = createVocabList(docList)
108 trainingSet = list(range(50)); testSet=[]
109 for i in range(10): #随机构建训练集与测试集
110 randIndex = int(np.random.uniform(0, len(trainingSet)))
111 testSet.append(trainingSet[randIndex])
112 del(trainingSet[randIndex])
113 trainMat=[]; trainClasses=[]
114 for docIndex in trainingSet:
115 trainMat.append(setOfWords2Vec(vocabList, docList[docIndex]))
116 trainClasses.append(classList[docIndex])
117 p0V, p1V, pSpam = trainNB0(np.array(trainMat), np.array(trainClasses))
118 errorCount = 0
119 for docIndex in testSet: #对测试集分类并计算错误率
120 wordVector = setOfWords2Vec(vocabList, docList[docIndex])
121 if classifyNB(np.array(wordVector), p0V, p1V, pSpam) != classList[docIndex]:
122 errorCount += 1
123 print (‘The error rate is: ‘, float(errorCount/len(testSet)))
124
125 #Simple unit test of func: loadDataSet(), createVocabList(), setOfWords2Vec
126 #listOPosts, listClassed = loadDataSet()
127 #myVocabList =createVocabList(listOPosts)
128 #print (myVocabList)
129 #res = setOfWords2Vec(myVocabList, listOPosts[0])
130 #print (res)
131
132 #Simple unit test of func: trainNB0()
133 #listOposts, listClasses = loadDataSet()
134 #myVocabList = createVocabList(listOposts)
135 #trainMat = []
136 #for postinDoc in listOposts:
137 # trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
138 #p0V, p1V, pAb = trainNB0(trainMat, listClasses)
139 #print (p0V); print (p1V); print (pAb)
140
141 #Simple unit test of func: testingNB()
142 #testingNB()
143
144 spamTest()
京公网安备 11010802041100号