2a2b3aa7ef4ac140c8d55f7f68705225b2349955,Word2Vec.py,,cleanDataset,#,19

Before Change

	for line in allLines:
	    tempStr = line.replace("\n"," ").lower()
	    myStr += re.sub("[.!?]","", tempStr)
	return myStr, Counter(myStr.split())

def createTrainingMatrices(dictionary, corpus):
	allUniqueWords = dictionary.keys()	
	allWords = corpus.split()

After Change

	for line in allLines:
	    tempStr = line.replace("\n"," ").lower()
	    myStr += re.sub("[.!?]","", tempStr)
	intermediateDict = Counter(myStr.split())
	for word in intermediateDict:
		numOccurences = intermediateDict[word]
		if numOccurences <= unknownCutoff:
			intermediateDict["<unk>"] += numOccurences
			myStr.replace(word, "<unk>")
			del intermediateDict[word]
	return myStr, intermediateDict

def createTrainingMatrices(dictionary, corpus):
	allUniqueWords = dictionary.keys()	

Instances