【机器学习】实战笔记_朴素贝叶斯

因本人刚开始写博客，学识经验有限，如有不正之处望读者指正，不胜感激；也望借此平台留下学习笔记以温故而知新。这个系列是机器学习实战一书的学习笔记，主要是基本算法的代码实现。

机器学习实战 百度网盘链接：百度网盘-链接不存在

提取码：qcht

推荐指数：5颗星

朴素贝叶斯的特点
优点：在数据较少的情况下仍然有效，可以处理多类别问题。
缺点：对于输入数据的准备方式较为敏感。
适用数据类型：标称型数据。

朴素贝叶斯的一般流程
(1) 收集数据：可以使用任何方法。本章使用RSS源。
(2) 准备数据：需要数值型或者布尔型数据。
(3) 分析数据：有大量特征时，绘制特征作用不大，此时使用直方图效果更好。
(4) 训练算法：计算不同的独立特征的条件概率。
(5) 测试算法：计算错误率。
(6) 使用算法：一个常见的朴素贝叶斯应用是文档分类。可以在任意的分类场景中使用朴素贝叶斯分类器，不一定非要是文本。

朴素贝叶斯中朴素一词的含义：独立条件假设

问题描述
使用朴素贝叶斯进行文档分类(三个例子：过滤社区恶意词语；过滤垃圾邮件；从个人广告中获取区域倾向)

# -*- coding: utf-8 -*-
"""
Created on Thu Mar 28 21:48:39 2019

@author: yuxi
"""

import numpy as np

## 处理过滤网站中的恶意留言
# 创建文档数据集
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 is abusive, 0 not
    return postingList,classVec

# 创建单词数据集
def createVocabList(dataSet):
    vocabSet = set([])  # 创建空集合
    for document in dataSet:
        vocabSet = vocabSet | set(document) # 求并集操作
    return list(vocabSet)

# 单词向量化操作
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

# 计算相关概率取值
def trainNB0(trainMatrix,trainCategory):
    numTrainDocs = len(trainMatrix)
    numWords = len(trainMatrix[0])
    pAbusive = sum(trainCategory)/float(numTrainDocs)
    p0Num = np.ones(numWords)    # 为了解决概率值未出现为0的情况
    p1Num = np.ones(numWords)
    p0Denom = 2
    p1Denom = 2
    for i in range(numTrainDocs):
        if trainCategory[i] == 1:
            p1Num += trainMatrix[i]    # 向量相加
            p1Denom += sum(trainMatrix[i])   # 数值求和
        else:
            p0Num += trainMatrix[i]
            p0Denom += sum(trainMatrix[i])
    p1Vect = np.log(p1Num/p1Denom)
    p0Vect = np.log(p0Num/p0Denom)
    return p0Vect,p1Vect,pAbusive
    
# 朴素贝叶斯分类器函数
def classifyNB(vec2Classify,p0Vec,p1Vec,pClass1):
    p1 = sum(vec2Classify * p1Vec) + np.log(pClass1)    
    p0 = sum(vec2Classify * p0Vec) + np.log(1.0 - pClass1)
    if p1 > p0:
        return 1
    else: 
        return 0

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

##  处理过滤垃圾邮件
def bagOfWords2VecMN(vocabList, inputSet):
    returnVec = [0]*len(vocabList)
    for word in inputSet:
        if word in vocabList:
            returnVec[vocabList.index(word)] += 1
    return returnVec

def textParse(bigString):    #input is big string, #output is word list
    import re
    listOfTokens = re.split(r'\W*', bigString)
    return [tok.lower() for tok in listOfTokens if len(tok) > 2] 

def spamTest():
    docList=[]; classList = []; fullText =[]
    for i in range(1,26):
        wordList = textParse(open('email/spam/%d.txt' % i).read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1)
        wordList = textParse(open('email/ham/%d.txt' % i).read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    vocabList = createVocabList(docList)            # create vocabulary
    trainingSet = list(range(50)); testSet=[]       # create test set
    for i in range(10):
        randIndex = int(np.random.uniform(0,len(trainingSet)))
        testSet.append(trainingSet[randIndex])
        del(trainingSet[randIndex])  
    trainMat=[]; trainClasses = []
    for docIndex in trainingSet:       # train the classifier (get probs) trainNB0
        trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))
        trainClasses.append(classList[docIndex])
    p0V,p1V,pSpam = trainNB0(np.array(trainMat),np.array(trainClasses))
    errorCount = 0
    for docIndex in testSet:           # classify the remaining items
        wordVector = bagOfWords2VecMN(vocabList, docList[docIndex])
        if classifyNB(np.array(wordVector),p0V,p1V,pSpam) != classList[docIndex]:
            errorCount += 1
            print ("classification error",docList[docIndex])
    print ('the error rate is: ',float(errorCount)/len(testSet))
    #return vocabList,fullText


## 从个人广告中获取区域倾向
#import feedparser
#ny = feedparser.parse('http://newyork.craigslist.org/stp/index.rss')
def calcMostFreq(vocabList,fullText):
    import operator
    freqDict = {}
    for token in vocabList:
        freqDict[token]=fullText.count(token)
    sortedFreq = sorted(freqDict.items(), key=operator.itemgetter(1), reverse=True) 
    return sortedFreq[:30]       

def localWords(feed1,feed0):
#    import feedparser
    docList=[]; classList = []; fullText =[]
    minLen = min(len(feed1['entries']),len(feed0['entries']))
    for i in range(minLen):
        wordList = textParse(feed1['entries'][i]['summary'])
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1) #NY is class 1
        wordList = textParse(feed0['entries'][i]['summary'])
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    vocabList = createVocabList(docList)#create vocabulary
    top30Words = calcMostFreq(vocabList,fullText)   #remove top 30 words
    # 去掉出现次数最高的词语
    for pairW in top30Words:
        if pairW[0] in vocabList: vocabList.remove(pairW[0])
    trainingSet = range(2*minLen); 
    testSet=[]           #create test set
    for i in range(20):
        randIndex = int(np.random.uniform(0,len(trainingSet)))
        testSet.append(trainingSet[randIndex])
        del(trainingSet[randIndex])  
    trainMat=[]; trainClasses = []
    for docIndex in trainingSet:#train the classifier (get probs) trainNB0
        trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))
        trainClasses.append(classList[docIndex])
    p0V,p1V,pSpam = trainNB0(np.array(trainMat),np.array(trainClasses))
    errorCount = 0
    for docIndex in testSet:        #classify the remaining items
        wordVector = bagOfWords2VecMN(vocabList, docList[docIndex])
        if classifyNB(np.array(wordVector),p0V,p1V,pSpam) != classList[docIndex]:
            errorCount += 1
    print ('the error rate is: ',float(errorCount)/len(testSet))
    return vocabList,p0V,p1V

def getTopWords(ny,sf):
#    import operator
    vocabList,p0V,p1V=localWords(ny,sf)
    topNY=[]; topSF=[]
    for i in range(len(p0V)):
        if p0V[i] > -6.0 : topSF.append((vocabList[i],p0V[i]))
        if p1V[i] > -6.0 : topNY.append((vocabList[i],p1V[i]))
    sortedSF = sorted(topSF, key=lambda pair: pair[1], reverse=True)
#    print ("SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**SF**")
    for item in sortedSF:
        print (item[0])
    sortedNY = sorted(topNY, key=lambda pair: pair[1], reverse=True)
#    print ("NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**NY**")
    for item in sortedNY:
        print (item[0])

主要步骤小结：

创建文档单词列表
单词向量化操作
计算各概率值
创建贝叶斯分类器函数
测试数据
计算错误率
用于预测判断