Machine learning practice -- naive Bayes method (code explanation)

Machine learning practice -- naive Bayes method

First, I will talk about the problems encountered in the next code. For the code, please refer to the book of machine learning practice.

Question 1:
When running program listing 4-5 in machine learning practice P66, it always reports an error:
UnicodeDecodeError: 'gbk' codec can't decode byte 0xae in position 199: illegal multib
terms of settlement:
Open the 23.txt file and found that it contains a "? Character. "SciFinance?is", delete the "?" Yes.
Question two:
del(trainingSet[randIndex]) this code reports an error
Error 'range' object doesn't support item deletion
Main reason: different versions. In python2 version of the book, range returns range object instead of list in python3
Solution: change trainingSet = range(50) to trainingSet = list(range(50))

Question three:
When parsing text

strings = 'Hello python,the best language!' print(strings) import re listOfTokens = re.split(r'\W*',strings) print(listOfTokens)

Output result

Hello python,the best language! ['', 'H', 'e', 'l', 'l', 'o', '', 'p', 'y', 't', 'h', 'o', 'n', '', 't', 'h', 'e', '', 'b', 'e', 's', 't', '', 'l', 'a', 'n', 'g', 'u', 'a', 'g', 'e', '', '']

Visible file parsing is not correct.
terms of settlement:
Change listOfTokens = re.split(r '\ w *', strings) to listOfTokens = re.split(r '\ W', strings) and remove *

The code gives its own understanding in the following comments

from numpy import * """Constructing word vector from text""" def loadDataSet(): """Create an experiment sample""" postingList=[ ['my','dog','has','flea','probiems','help','please'], ['maybe','not','take','him','to','dog','park','stupid'], ['my','dalmation','is','so','cute','I','love','him'], ['stop','posting','stupid','worthless','garbage'], ['mr','licke','ate','my','steak','how','to','stop','him'], ['quit','buying','worthless','dog','food','atupid'] ] classVec = [0,1,0,1,0,1] #1 for insulting words, 0 for normal speech return postingList,classVec def creatVocabList(dataSet): """Create a list of all documents without duplicate words""" vocabSet = set([]) for document in dataSet: vocabSet = vocabSet | set(document) #set() removes duplicate words from the list return list(vocabSet) def setOfWords2Vec(vocabList,inputSet): #Word set model """Enter as glossary and document, check if the words in the document are in the glossary""" returnVet = [0]*len(vocabList) #Create a 0 vector with a length of vocabList for word in inputSet: if word in vocabList: returnVet[vocabList.index(word)] = 1 else: print("the word: " + word + " is not in my Vocabulary!") return returnVet def bagOfWords2Vec(vocabList,inputSet): #Word bag model """Enter as glossary and document and check the number of times words in the document appear in the glossary""" returnVet = [0]*len(vocabList) #Create a 0 vector with a length of vocabList for word in inputSet: if word in vocabList: returnVet[vocabList.index(word)] += 1 else: print("the word: " + word + " is not in my Vocabulary!") return returnVet """Calculating probability from word vector""" def trainNB0(trainMatrix,trainCategory): """Input: document matrix, document category label vector""" numTrainDocs = len(trainMatrix) #Number of documents numWords = len(trainMatrix[0]) #Number of words in the document pAbusive = sum(trainCategory)/float(numTrainDocs) # P(1) #Initialization probability p0Nnm = ones(numWords) #Vector of the number of times each word appears in the vocabulary in the document with category 0 p1Num = ones(numWords) #Files of category 1 p0Denom = 2.0 #Total number of words in the vocabulary for documents with category 0 p1Denom = 2.0 #The total number of words in the glossary for documents with category 1 for i in range(numTrainDocs): if trainCategory[i] == 1: p1Num += trainMatrix[i] p1Denom += sum(trainMatrix[i]) else: p0Nnm += trainMatrix[i] p0Denom += sum(trainMatrix[i]) p1Vect = log(p1Num/p1Denom) #p(w|c1) where W is the word vector of each document p0Vect = log(p0Nnm/p0Denom) #p(w|c0) return p0Vect,p1Vect,pAbusive def classfyNB(vec2Classify,p0Vec,p1Vec,pClass1): p1 = sum(vec2Classify * p1Vec) + log(pClass1) #p(w1|c1)*p(w2|c1)*...*p(wn|c1)*p(1) p0 = sum(vec2Classify * p0Vec) + log(1.0 - pClass1) #p(w1|c1)*p(w2|c1)*...*p(wn|c1)*p(0) if p1 > p0: return 1 else: return 0 def testingNB(): listOPosts,listClasses = loadDataSet() myVocabList = creatVocabList(listOPosts) trainMat = [] for postinDoc in listOPosts: trainMat.append(setOfWords2Vec(myVocabList,postinDoc)) p0V,p1V,pAb = trainNB0(array(trainMat),array(listClasses)) testEntry = ['him','to','dog'] thisDoc = array(setOfWords2Vec(myVocabList,testEntry)) print(testEntry,'classfied as:',classfyNB(thisDoc,p0V,p1V,pAb)) testEntry = ['stupid','garbage'] thisDoc = array(setOfWords2Vec(myVocabList,testEntry)) print(testEntry,'classfied as:',classfyNB(thisDoc,p0V,p1V,pAb)) def textParse(bigString): """Text parsing""" 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): #Parsed text wordList = textParse(open(r'E:\machine learning\machinelearninginaction\Ch04\email\spam\%d.txt' % i).read()) docList.append(wordList) fullText.extend(wordList) classList.append(1) # Classified labels wordList = textParse(open(r'E:\machine learning\machinelearninginaction\Ch04\email\ham\%d.txt' % i).read()) docList.append(wordList) fullText.extend(wordList) classList.append(0) vocabList = creatVocabList(docList) #Glossary trainingSet = list(range(50)) #Training dataset coordinates testSet = [] #Test data set coordinates for i in range(10): #Randomly select 10 texts as the test set randIndex = int(random.uniform(0,len(trainingSet))) #Randomly select text testSet.append(trainingSet[randIndex]) #Join test set del(trainingSet[randIndex]) #Remove test data from training set trainMat = []; trainClasses = [] for docIndex in trainingSet: trainMat.append(setOfWords2Vec(vocabList,docList[docIndex])) #Training set trainClasses.append(classList[docIndex]) #Training set category p0V,p1V,pSpam = trainNB0(array(trainMat),array(trainClasses)) #Computing probability errorCount = 0 for docIndex in testSet: #test wordVector = setOfWords2Vec(vocabList,docList[docIndex]) if classfyNB(array(wordVector),p0V,p1V,pSpam) != classList[docIndex]: errorCount += 1 print('classcation error:',docList[docIndex]) print('the error rate is:',float(errorCount)/len(testSet)) if __name__ == "__main__": spamTest()

Operation result

classcation error: ['home', 'based', 'business', 'opportunity', 'knocking', 'your', 'door', 'don A kind of', 'rude', 'and', 'let', 'this', 'chance', 'you', 'can', 'earn', 'great', 'income', 'and', 'find', 'your', 'financial', 'life', 'transformed', 'learn', 'more', 'here', 'your', 'success', 'work', 'from', 'home', 'finder', 'experts'] the error rate is: 0.1

• Give the thumbs-up
• Collection
• share
• • Article report