【读书笔记】机器学习实战-4.5节 贝叶斯文本分类

机器学习

#!/usr/bin/python
# -*- coding: utf-8 -*-
from numpy import *

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]  # 标签
return postingList, classVec

def createVocabList(dataSet):  # 返回词汇列表
vocabSet = set([])  # 创建空集
for document in dataSet:
vocabSet = vocabSet|set(document)
return list(vocabSet)

def setOfWords2Vec(vocabList, inputSet):  # 输入：词汇表 输入文档
returnVec = [0]*len(vocabList)
for word in inputSet:
if word in vocabList:
returnVec[vocabList.index(word)] = 1  # index()函数
else:
print"the word %s is not in my Vocabulary!" %word
return returnVec

#训练函数：
def trainNB0(trainMatrix, trainCategory):  # naive bayes 输入：训练文档矩阵  训练文档类别
numTrainDocs = len(trainMatrix)
numWords = len(trainMatrix[0])
pAbusive = sum(trainCategory)/float(numTrainDocs)   # 计算p(Ci) pabusive:侮辱文档概率，   1-pabusive ：正常文档概率
p0Num = ones(numWords); p1Num = ones(numWords)      # 分别统计各类别单词出现的次数 change to ones()
p0Denom = 2.0; p1Denom = 2.0
for i in range(numTrainDocs):
if trainCategory[i] == 1:
p1Num += trainMatrix[i]                     # numpy.array的数组运算
p1Denom += sum(trainMatrix[i])
else:
p0Num += trainMatrix[i]
p0Denom += sum(trainMatrix[i])
p1Vect = log(p1Num/p1Denom)                         # 计算p(Wj | Ci) ; change to log(): 防止下溢出
p0Vect = log(p0Num/p0Denom)
return p0Vect,p1Vect,pAbusive

def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):   # 输入：需分类的向量；P(Wj | C0)向量；P(Wj | C1)向量；P(C1)
p1 = sum(vec2Classify* p1Vec)+log(pClass1)          # SUM(log(P(Wj|Ci))) + log(P(Ci))
p0 = sum(vec2Classify* p0Vec)+log(1.0 - pClass1)
if p1>p0:
return 1
else:
return 0

def testingNB():
listOPosts,listClasses = loadDataSet()
myVocabList = createVocabList(listOPosts)
trainMat=[]
for postinDoc in listOPosts:
trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
p0V,p1V,pAb = trainNB0(array(trainMat),array(listClasses)) # 训练
testEntry = ['love', 'my', 'dalmation'] # 测试文本
thisDoc = array(setOfWords2Vec(myVocabList, testEntry))  # 测试文本预处理
print testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb)# 测试
testEntry = ['stupid', 'garbage']  # 测试文本
thisDoc = array(setOfWords2Vec(myVocabList, testEntry))  # 测试文本预处理
print testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb)  # 测试

testingNB()
#listOPosts,listClasses = loadDataSet()
#myVocabList = createVocabList(listOPosts)
#trainMat = []
#for postinDoc in listOPosts:
#   trainMat.append(setOfWords2Vec(myVocabList,postinDoc))
#p0V,p1V,pAb = trainNB0(trainMat,listClasses)
pass