朴素贝叶斯的python代码实例

下面是一个朴素贝叶斯的Python代码实例，代码中包含了对样本数据的处理、训练和预测等步骤：

# -*- coding: utf-8 -*-
from numpy import *

# 过滤网站的恶意留言
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,,1]    # 1代表侮辱性文字，0代表正常言论
    return postingList,classVec
# 创建词汇表
def createVocabList(dataSet):
    vocabSet = set([])  # 创建一个空的不重复列表
    for document in dataSet:
        vocabSet = vocabSet | set(document) # 取并集
    return list(vocabSet)

# 将文本转换为词向量
def setOfWords2Vec(vocabList, inputSet):
    returnVec = [0]*len(vocabList) # 创建一个其中所含元素都为0的向量
    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

# 训练朴素贝叶斯分类器
def trainNB0(trainMatrix,trainCategory):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory)/float(numTrainDocs) # 计算侮辱性文档的概率
    p0Num = ones(numWords); p1Num = ones(numWords)      # 创建numpy.ones数组,词条出现数初始化为1，拉普拉斯平滑
    p0Denom = 2.0; p1Denom = 2.0                        # 分母初始化为2，拉普拉斯平滑
    for i in range(numTrainDocs):
        if trainCategory[i] == 1: # 统计属于侮辱类的条件概率所需的数据，即P(w0|1),P(w1|1),P(w2|1),...
            p1Num += trainMatrix[i]
            p1Denom += sum(trainMatrix[i])
        else:                     # 统计属于非侮辱类的条件概率所需的数据，即P(w0|0),P(w1|0),P(w2|0),...
            p0Num += trainMatrix[i]
            p0Denom += sum(trainMatrix[i]))
    p1Vect = log(p1Num/p1Denom)          # 取对数，防止下溢出
    p0Vect = log(p0Num/p0Denom)          
    return p0Vect,p1Vect,pAbusive

# 测试朴素贝叶斯分类器
def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
    p1 = sum(vec2Classify * p1Vec) + log(pClass1)    # 元素相乘
    p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
    if p1 > p0:
        return 1
    else:
        return 0

# 测试朴素贝叶斯分类器的效果
def testingNB():
    listOPosts,listClasses = loadDataSet() # 创建实验样本
    myVocabList = createVocabList(listOPosts) # 创建词汇表
    trainMat=[]
    for postinDoc in listOPosts:
        trainMat.append(setOfWords2Vec(myVocabList, postinDoc)) # 将实验样本向量化
    p0V,p1V,pAb = trainNB0(array(trainMat),array(listClasses)) # 训练朴素贝叶斯分类器
    testEntry = ['love', 'my', 'dalmation'] # 测试样本1
    thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
    print(testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb))
    testEntry = ['stupid', 'garbage'] # 测试样本2
    thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
    print(testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb))

testingNB()