根据公式:
可以得出:
这里进行计算时,只需要计算分子,比较大小,因为分母只是对数值有影响,对两个数的比较不会产生影响
import numpy as np
"""创建数据集"""
def loadDataSet():
postingList = [['my', 'dog', 'has', 'flea', 'problems', 'help', 'please'],
['maybe', 'not', 'take', 'him', 'to', 'dog', 'park', 'stupid'], # stupid侮辱类
['my', 'dalmation', 'is', 'so', 'cute', 'I', 'love', 'him'],
['stop', 'posting', 'stupid', 'worthless', 'garbage'], # garbage,stupid侮辱类
['mr', 'licks', 'ate', 'my', 'steak', 'how', 'to', 'stop', 'him'],
['quit', 'buying', 'worthless', 'dog', 'food', 'stupid']] # stupid侮辱类
classVec = [0, 1, 0, 1, 0, 1] # 类别标签向量,1代表侮辱性词汇,0代表不是
return postingList, classVec
"""创建词汇表"""
def createVocabList(dataSet):
vocabSet = set([])
for document in dataSet: # 取出每一行文档(每行七个单词)
vocabSet = vocabSet | set(document) # 先将文档转换为set集合,无需不重复,再取并集
return list(vocabSet)
"""判断输入集中单词是否在词汇表中"""
def setOfWordsVec(vocabList, inputSet):
returnVec = [0] * len(vocabList) # 创建一个元素都为0的向量
for word in inputSet: # 取输入集的每一个单词
if word in vocabList: # 如果单词在词汇表中
returnVec[vocabList.index(word)] = 1 # 标志位置为一,表示所检测单词在词汇表中
else:
print("the word:$s is not in my Vocabulary!" % word)
return returnVec
"""计算概率"""
def trainNB0(trainMatrix, trainCategory):
numTrainDocs = len(trainMatrix) # 样本个数,6
numWords = len(trainMatrix[0]) # 每个样本长度,32
pAbusive = sum(trainCategory) / float(numTrainDocs) # 文档属于侮辱类的概率
p0Num = np.ones(numWords) # 非侮辱类情况下,某个单词出现的概率
p1Num = np.ones(numWords) # 侮辱类情况下,某个单词出现的概率
p0Denom = 2.0 # 分母,都设置为2(我们需要的是两个比较,所以都设置为共同的分母不影响大小)
p1Denom = 2.0
for i in range(numTrainDocs):
if trainCategory[i] == 1:
p1Num += trainMatrix[i] # 每个侮辱类样本都相加(记录侮辱类每个单词的个数)
p1Denom += sum(trainMatrix[i]) # 求和所有侮辱类样本的单词数
else:
p0Num += trainMatrix[i] # 每个非侮辱类样本都相加(记录侮辱类每个单词的个数)
p0Denom += sum(trainMatrix[i]) # 求和所有非侮辱类样本的单词数
p1Vect = np.log(p1Num / p1Denom) # 取对数,防止下溢出
p0Vect = np.log(p0Num / p0Denom)
return p0Vect, p1Vect, pAbusive
"""分类"""
def classifyNB(vecClassify, p0Vec, p1Vec, pClass1):
p1 = sum(vecClassify * p1Vec) + np.log(pClass1) # log(A*B)=logA+logB,前边没有log,是因为这需要两个数比较,同时log和都不log不会影响比较大小
p0 = sum(vecClassify * p0Vec) + np.log(1 - pClass1)
if p1 > p0:
return 1
else:
return 0
if __name__ == '__main__':
listOposts, listClasses = loadDataSet()
myVocabList = createVocabList(listOposts)
trainMat = []
for postinDoc in listOposts:
trainMat.append(setOfWordsVec(myVocabList, postinDoc)) # 生成6*32的矩阵,表示每条数据中单词在词汇表的存在情况
poV, p1V, pAb = trainNB0(np.array(trainMat), np.array(listClasses))
testEntry = ['love', 'my', 'dalmation']
thisDoc = np.array(setOfWordsVec(myVocabList, testEntry))
if classifyNB(thisDoc, poV, p1V, pAb):
print("%s属于侮辱类词汇。" % (testEntry,))
else:
print("%s属于非侮辱类词汇。" % (testEntry,))
testEntry = ['stupid', 'garbage']
thisDoc = np.array(setOfWordsVec(myVocabList, testEntry))
if classifyNB(thisDoc, poV, p1V, pAb):
print("%s属于侮辱类词汇。" % (testEntry,))
else:
print("%s属于非侮辱类词汇。" % (testEntry,))