2025Python-/2024朴素贝叶斯分类算法手写.py at main · wulixin/2025Python- · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
######################################################
#
#   python  朴素贝叶斯分类算法手写
#
#####################################################

##通过loadDataSet函数创建数据集和分类结果；
def loadDataSet():
  postingList= [['my','dog','has','problems','help','please'],
                ['my','dog','has','problems','help','please'],
                ['my','dog','has','problems','help','please'],
                ['my','dog','has','problems','help','please'],
                ['my','dog','has','problems','help','please'],
                ['my','dog','has','problems','help','please']]
  classVec = [0,1,0,1,0,1]
  return postingList,calssVec

##通过createVocabList函数统计所有文档中出现的词条列表。在函数中，新建一个存放词条，遍历文档中的每一篇文章，
###将文档列表转换为集合的形式，保证每个词条的唯一性，然后与vocabSet取并集，向vocabSet中添加没有出现的心得词条，
###再将集合转换为列表
def createVocabList(dataSet):
  vocabList=set([])
  for document in dataSet:
    vocabSet = vocabSet | set(document)
  return list(vocabSet)


## 通过setOfWords2Vec() 函数根据词条列表中的词条是否在文档中出现，将文档转换为词条向量，在函数中，新建一个长度为
### vocabSet的列表，并且各维度元素初始化为0，遍历文档中的每一个词条，如果词条在词条列表中出现，通过列表获取当前Word

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

## 通过trainNB0函数训练师案发，从词向量计算概率。

 def trainNB0(trainMatrix,trainCategory):
   numTrainDocs = len(trainMatrix)
   numWords = len(trainMatrix[0])
   pAbusive = sum(trainCategory)/float(numTrainDocs)
   p0Num = ones(numWords);p1Num = ones(numWords)
   p0Denom = 2.0;p1Denom = 2.0
   for i in range(numTrainDcos):
     if trainCategory[i] == 1:
       p1Num += rainMatrix[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

# 第五定义朴素贝叶斯分类函数，classifyNB()，其中vec2Classify表示待测试分类的词条向量，P0Vec表示类比为0所有文档
##中各词条出现的频数；
def calssfiyNB(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


# 通过testingNB函数，定义分类测试整体函数；在函数中由数据集获取文档矩阵和标签向量，统计所有文档中出现的词条，存入词条列表，然后创建
##新的列表，将每篇文档利用wordsVec函数转换为词条向量,存入文档矩阵中，将文档矩阵和类标签向量转换为Numpy的数组形式；
def testingNB():
  listOPosts,listClasses = loadDataSet()
  myVocabList = createVocabList(listOPosts)
  trainMat=[]
  for postinDoc in listOPosts:
    trainMat.append(setOfWords2Vec(myVocabList,postinDoc))
  p0V,p1V,pAb = trainNB(array(trainMat),array(listClasses))
  testEntry = ['love','my','dalmation']
  thisDoc = array(setOfWordsVec(myVocabList,testEntry))
  print(testEntry,'classified as:',classifyNB(thisDoc,p0V,p1V,pAb))
  testEntry = ['stupid','garbage']
  thisDoc = array(setOfWords2Vec(myVocabList,testEntry))
  print(testEntry,'calssified as:',classifyNB(thisDoc,p0V,p1V,pAb))

##第七 在实验中用textParse 函数处理数据长字符串，对称行字符串进行分割，分隔符为除单词和数字之外的任意符号串。
def textParse(bigString):
  import re
  listOfTokens = re.split(r'\W*',bigString)
  return [tok.lower() for tok in listOfTokens if len(tok) >2 ]


def testingNb()