按照惯例，先把代码粘到这里
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] # 1 is abusive, 0 not
return postingList, classVec
def CreateVocabList(dataSet):
vocabSet = set([]) # create empty set
for document in dataSet:
vocabSet = vocabSet | set(document) # union of the two sets
return list(vocabSet)
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
def BagOfWords2VecMN(vocabList, inputSet):
returnVec = [0] * len(vocabList)
for word in inputSet:
if word in vocabList:
returnVec[vocabList.index(word)] += 1
return returnVec
def trainNB0(trainMatrix, trainCategory):
numTrainDocs = len(trainMatrix)
numWords = len(trainMatrix[0])
pAbusive = sum(trainCategory) / float(numTrainDocs)
p0Num = ones(numWords)
p1Num = ones(numWords) #change to ones() to avoid product to be zero
p0Denom = 2.0; p1Denom = 2.0 #change to 2.0
for i in range(numTrainDocs):
if trainCategory[i] == 1:
p1Num += trainMatrix[i]
p1Denom += sum(trainMatrix[i])
else:
p0Num += trainMatrix[i]
p0Denom += sum(trainMatrix[i])
p1Vect = log(p1Num/p1Denom) #change to log() to avoid down-overflow
p0Vect = log(p0Num/p0Denom) #change to log()
return p0Vect, p1Vect, pAbusive
def ClassifyNB(vec2classify, p0Vec, p1Vec, pClass1):
p1 = sum(vec2classify * p1Vec) + log(pClass1)
p0 = sum(vec2classify * p0Vec) + log(1.0 - pClass1)
if p1 > p0:
return 1
else:
return 0
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('machinelearninginaction\Ch04\email\spam\%d.txt' % i).read())
docList.append(wordList)
fullText.extend(wordList)
classList.append(1)
wordList = TextParse(open('machinelearninginaction\Ch04\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(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(array(trainMat), array(trainClasses))
errorCount = 0
for docIndex in testSet: # classify the remaining items
wordVector = BagOfWords2VecMN(vocabList, docList[docIndex])
if ClassifyNB(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
# 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
# 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(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(array(trainMat), array(trainClasses))
# errorCount = 0
# for docIndex in testSet: # classify the remaining items
# wordVector = bagOfWords2VecMN(vocabList, docList[docIndex])
# if classifyNB(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]
编译过程中遇到的错误
错误1：
UnicodeDecodeError: 'gbk' codec can't decode byte 0xae in position 199: illegal multibyte sequence这个错误意思是python无法读取某个txt文件，实为编码问题，解决方法是按照错误跳转到相应程序行，在spam或者ham中查找有问题的txt，看看是否编码错误。如果编码错误，可以手动修改编码，或者你的编译器可以自动选择编码模式，修改一下就可以了。
错误2：
TypeError: 'range' object doesn't support item deletion将
trainingSet = range(50) 改为
trainingSet = list(range(50))即可
关于机器学习的源代码以及数据集在这里：
http://blog.csdn.net/iamoldpan/article/details/78010329
