(机器学习实战)第四章
作者：互联网
都是在python3下面的:
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
postingList,classVec = loadDataSet()
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
vocabList = createVocabList(postingList)
vocabList.sort()
vocabList
#setOfWords2Vec(vocabList, postingList[0])
from numpy import *
def trainNB0(trainMatrix,trainCategory):
numTrainDocs = len(trainMatrix)
numWords = len(trainMatrix[0])
pAbusive = sum(trainCategory)/float(numTrainDocs)
# print("pAbusive :")
# print(pAbusive)
p0Num = ones(numWords);
# print("p0Num :")
# print(p0Num)
# print(type(p0Num))
p1Num = ones(numWords) #change to ones()
p0Denom = 2.0;
p1Denom = 2.0 #change to 2.0
for i in range(numTrainDocs):
if trainCategory[i] == 1:
# print("trainMatrix[i] :")
# print(trainMatrix[i])
# print(type(trainMatrix[i]))
p1Num += trainMatrix[i]
# print("p1Num :")
# print(p1Num)
# print(type(p1Num))
p1Denom += sum(trainMatrix[i])
else:
p0Num += trainMatrix[i]
p0Denom += sum(trainMatrix[i])
# print("p1Num/p1Denom :")
# print(p1Num/p1Denom)
# print(type(p1Num/p1Denom))
p1Vect = log(p1Num/p1Denom) #change to log()
p0Vect = log(p0Num/p0Denom) #change to log()
return p0Vect,p1Vect,pAbusive
traimMat = []
for postinDoc in postingList:
traimMat.append(setOfWords2Vec(vocabList, postinDoc))
#traimMat
p0V, p1V, pAb = trainNB0(traimMat, classVec)
pAb
p0V
p1V
def classifyNB(vec2Classify, p0Vec, p1Vec, pClass1):
p1 = sum(vec2Classify * p1Vec) + log(pClass1) #element-wise mult
p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1)
if p1 > p0:
return 1
else:
return 0
def testingNB():
listOPosts,listClasses = loadDataSet()
myVocabList = createVocabList(listOPosts)
trainMat=[]
for postinDoc in listOPosts:
trainMat.append(setOfWords2Vec(myVocabList, postinDoc))
p0V,p1V,pAb = trainNB0(array(trainMat),array(listClasses))
testEntry = ['love', 'my', 'dalmation']
thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
print("thisDoc :")
print(thisDoc)
print(testEntry, "classified as: ", classifyNB(thisDoc,p0V,p1V,pAb))
testEntry = ['stupid', 'garbage']
thisDoc = array(setOfWords2Vec(myVocabList, testEntry))
#print testEntry,'classified as: ',classifyNB(thisDoc,p0V,p1V,pAb)
print(testEntry, "classified as: ", classifyNB(thisDoc,p0V,p1V,pAb))
testingNB()
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
regEx = re.compile("\\W")
listOfTokens = regEx.split(bigString)
#print(listOfTokens)
return [tok.lower() for tok in listOfTokens if len(tok) > 2]
#textParse('ngaib faibga i aig baibgaigag abi baigba i')
def spamTest():
docList=[]; classList = []; fullText =[]
for i in range(1,26):
wordList = textParse(open('email/spam/%d.txt' % i).read())
# if i == 1:
# print(wordList)
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 = range(50);
#print(vocabList)
trainingSet = list(range(50))
#print(trainingSet)
testSet=[] #create test set
#随机的找10个 0-49的数字
for i in range(10):
randIndex = int(random.uniform(0,len(trainingSet)))
testSet.append(trainingSet[randIndex])
del(trainingSet[randIndex])
#print(testSet)
trainMat=[]; trainClasses = []
for docIndex in trainingSet:#train the classifier (get probs) trainNB0
trainMat.append(bagOfWords2VecMN(vocabList, docList[docIndex]))
trainClasses.append(classList[docIndex])
# print("trainMat :")
# print(trainMat)
# print("trainClasses :")
# print(trainClasses)
p0V,p1V,pSpam = trainNB0(array(trainMat),array(trainClasses))
print(pSpam)
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
spamTest()
import feedparser
ny = feedparser.parse("http://newyork.craigslist.org/stp/index.rss")
len(ny['entries'])
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 stopWords():
import re
wordList = open('stopword.txt').read() # see http://www.ranks.nl/stopwords
return textParse(wordList)
def localWords(feed1,feed0):
import feedparser
docList=[]; classList = []; fullText =[]
minLen = min(len(feed1['entries']),len(feed0['entries']))
#print(minLen) #4
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
print(len(vocabList))
#两种方法对词汇表进行剪枝
# top30Words = calcMostFreq(vocabList,fullText) #remove top 30 words
# for pairW in top30Words:
# if pairW[0] in vocabList:
# vocabList.remove(pairW[0])
# print(len(vocabList))
stopWordList = stopWords()
for stopWord in stopWordList:
if stopWord in vocabList:
vocabList.remove(stopWord)
print(len(vocabList))
trainingSet = list(range(2*minLen));
testSet=[] #create test set
for i in range(5):
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])
classifiedClass = classifyNB(array(wordVector),p0V,p1V,pSpam)
originalClass = classList[docIndex]
result = classifiedClass != originalClass
if result:
errorCount += 1
print ('\n',docList[docIndex],'\nis classified as: ',classifiedClass,', while the original class is: ',originalClass,'. --',not result)
print ('\nthe error rate is: ',float(errorCount)/len(testSet))
return vocabList,p0V,p1V
ny = feedparser.parse("http://www.nasa.gov/rss/dyn/image_of_the_day.rss")
sf = feedparser.parse("http://sports.yahoo.com/nba/teams/hou/rss.xml")
#print((ny['entries'][0]["summary"]))
#print(len(sf['entries']))
#ny
#vocabList, psF, pNY = localWords(ny, sf)
#stopWords()
vocabList, psF, pNY = localWords(ny, sf)
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])
getTopWords(ny,sf)
标签：实战,vocabList,len,NY,第四章,print,机器,SF,append 来源： https://blog.csdn.net/weixin_41791402/article/details/100822953