朴素贝叶斯的简单应用

利用已有的简单词表材料判断所给的测试记录的分类，词条非常的简单，作为笔记
主要步骤：

1. 加载数据 loadDataSet()
2. 得到词向量 createVocabList(listOPosts)
3. 生成训练数据集的矩阵
4. 得到训练数据的参数矩阵 trainNB0(trainMat, listClasses)
5. 生成测试数据并且得到测试数据的矩阵 array(setOfWords2Vec(myVocabList, testEntry))
6. 分类

#!/usr/bin/python
# coding:utf-8
from numpy import *
from math 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]  # 1代表侮辱性文字 0代表正常的言论
return postingList, classVec


def createVocabList(dataSet):    # 给定一个数据集，创建一个不含重复单词的词向量
    vocabList = set([])
for document in dataSet:
        vocabList = vocabList | set(document)
return list(vocabList)


def setOfWords2Vec(vocabList, inputSet):   #给定一个词向量和一条单词构成的记录，生成次条记录的向量
    returnVec = [0] * len(vocabList)
for word in inputSet:
if word in vocabList:
            returnVec[vocabList.index(word)] = 1
return returnVec


def trainNB0(trainMatrix, trainCategory):  # 训练参数,得到一个参数矩阵，对应着各个单词对应分类的出现频率
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory) / float(numTrainDocs)
    p0Num = ones(numWords)
    p1Num = ones(numWords)
    p0Denom = 2
    p1Denom = 2
for i in range(numTrainDocs):
if trainCategory[i] == 1:
            p1Num += trainMatrix[i]
            p1Denom += sum(trainMatrix[i])
else:
            p0Num += trainMatrix[i]
            p0Denom += sum(trainMatrix[i])
    p1Vec = p1Num / p1Denom
    p0Vec = p0Num / p0Denom
return p0Vec, p1Vec, pAbusive


def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):   # 计算分类
    p1 = sum(vec2Classify * p1Vec) + log(pClass1)  # array相乘并且加上类别个数的对数上
    p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
if p1 > p0:
return 1
else:
return 0


def testNB():    # 测试贝叶斯
    listOPosts, listClasses = loadDataSet()   #加载数据集
    myVocabList = createVocabList(listOPosts)  # 得到词向量
    trainMat = []
for postinDoc in listOPosts:  # 生成训练数据集的向量
        vecOfWord = setOfWords2Vec(myVocabList, postinDoc)
        trainMat.append(vecOfWord)
    p0v, p1v, pAb = trainNB0(trainMat, listClasses)  # 根据已有的数据训练出的参数p0 p1为矩阵
    testEntry = ['stupid']  # 测试数据
    testMatrix = array(setOfWords2Vec(myVocabList, testEntry)) # 得到测试数据的array
return classifyNB(testMatrix, p0v, p1v, pAb)  # 分类


print testNB() #测试主函数