python朴素贝叶斯电子邮件分类实例

一、步骤

（1）收集数据：提供文本文件。
（2）准备数据：将文本文件解析成词条向量。
（3）分析数据：检查词条确保解析的正确性。
（4）训练算法：使用我们之前建立的trainNB0()函数。
（5）测试算法：使用classifyNB()，并且构建一个新的测试函数来计算文档集的错误率。
（6）使用算法：构建一个完整的程序对一组文档进行分类，将错分的文档输出到屏幕上。

二、实例+注释

# coding: utf-8

from numpy import *
import sys

def loadDataSet():
	''' 收集数据：提供文本文件。 '''

	postingList = [[ 'my', 'dog', 'has', 'flea', 'problems', 'help', 'please'], 
					['maybe', 'not', 'take', 'him', 'to', 'dog', 'park', 'stupid'], 
					['my', 'dalmation', 'is', 'so', 'cute', 'T', '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代表正常言论
	return postingList, classVec	
	
def createVocabList( dataSet ): 
	vocabSet = set([])		
	for document in dataSet:
		vocabSet = vocabSet | set(document)
	
	return list(vocabSet)
	
def setOfWordsVec( vocabList, inputSet ):
	''' 准备数据：将文本文件解析成词条向量。 '''
	# 创建一个其中所含元素都为0的向量
	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
	
def bagOfWords2VecMN( vocabList, inputSet ):
	''' 准备数据： 文档词袋模型 '''
	returnVec = [0] * len( vocabList )
	for word in inputSet:
		if word in inputSet:
			returnVec[ vocabList.index(word) ] += 1
			
	return returnVec
	
def trainNB0( trainMatrix, trainCategory ):
	''' 训练算法 分类器训练函数 '''
	''' 得到vec类型的 侮辱性词汇概率  训练矩阵，训练类型标签 '''
	numTrainDocs = len( trainMatrix ) # 多少行训练文档 6
	numWords = len( trainMatrix[0] ) # 一行文档有多少词条数量 32
	
	# 有多少个文档里面包含了侮辱性词汇
	pAbusive = sum( trainCategory ) / float( numTrainDocs )
	
	p0Num = ones( numWords ) # 初始化为1 防止相乘后为0
	p1Num = ones( numWords )
	p0Denom = 2.0
	p1Denom = 2.0 # 分母
	
	for i in range( numTrainDocs ):
		if trainCategory[i] == 1:  	# 该行有侮辱性词汇
			p1Num += trainMatrix[i] # 两个 narray 相加
			p1Denom += sum( trainMatrix[i] )
		else:
			p0Num += trainMatrix[i]
			p0Denom += sum( trainMatrix[i] )
			
	p1Vect = log(p1Num / p1Denom)		# 得到vec类型的 侮辱性词汇概率
	p0Vect = log(p0Num / p0Denom)		# 得到vec类型的 正常性词汇概率
	
	return p0Vect, p1Vect, pAbusive
	
def classifyNB( vec2Classify, p0Vec, p1Vec, pClass1 ):
	''' 测试算法：分类函数 '''
	p1 = sum( vec2Classify * p1Vec ) + log( pClass1 ) # 加法即乘法，log(ab) = log(a) + log(b)
	p0 = sum( vec2Classify * p0Vec ) + log( 1.0 - pClass1 )
	
	if p1 > p0:
		return 1
	else:
		return 0
		
def textParse( bigString ):
	''' 数据准备 '''
	import re
	listOfTokens = re.split(r'\W*', bigString)
	return [ tok.lower() for tok in listOfTokens if len(tok) > 0 ]
		
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 ) # 词集
	
	trainingSet = range(50) # 初始化一个长度为50 的训练列表
	
	testSet = []
	# 随机构建训练集
	for i in range(10):
		randIndex = int( random.uniform(0, len(trainingSet)) ) # 随机10个下标
		testSet.append( trainingSet[randIndex] ) # 将随机的下标的数据加入到测试集合
		del( trainingSet[randIndex] ) # 将这些下标数据从训练列表中删除

	trainMat = []; trainClasses = []
	for docIndex in trainingSet:
		trainMat.append( setOfWordsVec(vocabList, docList[docIndex]) )
		trainClasses.append( classList[docIndex] )
		
	p0V, p1V, pSpam = trainNB0( array(trainMat), array(trainClasses) )

	errorCount = 0
	for docIndex in testSet:
		wordVector = setOfWordsVec( vocabList, docList[docIndex] )
		
		if classifyNB( array(wordVector), p0V, p1V, pSpam ) != classList[docIndex]:
			errorCount += 1
			
	print 'the error rate is: ', float(errorCount) / len(testSet)
		
def testingNB():
	listOPosts, listClasses = loadDataSet()
	myVocabList = createVocabList( listOPosts ) # 所有不重复词条列表
	trainMat = []

	for postingDoc in listOPosts:
		trainMat.append( setOfWordsVec( myVocabList, postingDoc) )
		
	# 先需要得到 侮辱性词汇概率等数据 p0V, p1V, pAb
	p0V, p1V, pAb = trainNB0( array(trainMat), array(listClasses) )
	
	# 要考虑到对应位置的概率
	testEntry = [ 'love', 'my', 'dalmation' ]
	thisDoc = array( setOfWordsVec( myVocabList, testEntry ) )
	print testEntry, 'classified as : ', classifyNB( thisDoc, p0V, p1V, pAb )
	
	testEntry = [ 'stupid', 'garbage' ]
	thisDoc = array( setOfWordsVec(myVocabList, testEntry) )
	print testEntry, 'classified as : ', classifyNB( thisDoc, p0V, p1V, pAb )
	
if __name__=="__main__":
	spamTest()