UnicodeDecodeError: ‘utf-8‘ codec can‘t decode byte 0x92 in position 884: invalid start byte

---------------------------------------------------------------------------
UnicodeDecodeError                        Traceback (most recent call last)
<ipython-input-81-823d79549753> in <module>
----> 1 bayes.spamTest()

D:\maxwelllearning\maxwellhandon\machine learning in action\bayes.py in spamTest()
    144         fullText.extend(wordList)
    145         classList.append(1)
--> 146         wordList = textParse(open('email/ham/%d.txt' % i).read())
    147         docList.append(wordList)
    148         fullText.extend(wordList)

D:\Soft\Anaconda3\lib\codecs.py in decode(self, input, final)
    320         # decode input (taking the buffer into account)
    321         data = self.buffer + input
--> 322         (result, consumed) = self._buffer_decode(data, self.errors, final)
    323         # keep undecoded input until the next call
    324         self.buffer = data[consumed:]

UnicodeDecodeError: 'utf-8' codec can't decode byte 0x92 in position 884: invalid start byte

original code:

def spamTest():
    docList = []; classList = []; fullText = []
    for i in range(1, 26):
        wordList = textParse(open('email/spam/%d.txt' % i, encoding="ISO-8859-1").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 = range(50); testSet = []           #create test set
    for i in range(10):
        randIndex = int(np.random.uniform(0, len(trainingSet)))
        testSet.append(trainingSet[randIndex])
        del(list(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

Modify Code:

def spamTest():
    docList = []; classList = []; fullText = []
    for i in range(1, 26):
        wordList = textParse(open('email/spam/%d.txt' % i, encoding="ISO-8859-1").read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(1)
        wordList = textParse(open('email/ham/%d.txt' % i, encoding="ISO-8859-1").read())
        docList.append(wordList)
        fullText.extend(wordList)
        classList.append(0)
    vocabList = createVocabList(docList)#create vocabulary
    trainingSet = range(50); testSet = []           #create test set
    for i in range(10):
        randIndex = int(np.random.uniform(0, len(trainingSet)))
        testSet.append(trainingSet[randIndex])
        del(list(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

Adding code : encoding="ISO-8859-1"