def checkStopWordGram(extractToken):
for wordExtract in extractToken:
checkWord = functionPython.findWordFromList(listOfStopWord, wordExtract)
if checkWord == "True":
extractToken.remove(wordExtract)
return extractToken
def checkStopWordGram(extractToken):
newExtractToken = []
for wordExtract in extractToken:
checkWord = functionPython.findWordFromList(listOfStopWord,
wordExtract)
if checkWord == "False":
newExtractToken.append(wordExtract)
return newExtractToken
else:
sentence = sentence + data[j]
#print(listOfSentence)
listOfTotalSentence.append(listOfSentence)
listOfSentence = []
print(listOfTotalSentence)
wordToCount = {}
checkWord = ""
for i in range(0, len(listOfTotalSentence)):
extractToken = t.bn_word_tokenizer(listOfTotalSentence[i][0])
#print(listOfTotalSentence[i])
for word in extractToken:
checkWord = functionPython.findWordFromList(listOfTotalWord, word)
if checkWord == "True":
checkWord = ""
if word not in wordToCount.keys():
wordToCount[word] = 1
else:
wordToCount[word] += 1
print(wordToCount)
#print(wordToCount.items())
wordToList = []
for key, value in wordToCount.items():
temp = [key,value]
break
else:
sentence = sentence + data[j]
#print(listOfSentence)
listOfTotalSentence.append(listOfSentence)
listOfSentence = []
print(listOfTotalSentence)
wordToCount = {}
checkWord = ""
for i in range(0, len(listOfTotalSentence)):
extractToken = t.bn_word_tokenizer(listOfTotalSentence[i][0])
#print(listOfTotalSentence[i])
for word in extractToken:
checkWord = functionPython.findWordFromList(listOfStopWord, word)
if checkWord == "False":
checkWord = ""
if word not in wordToCount.keys():
wordToCount[word] = 1
else:
wordToCount[word] += 1
print(wordToCount)
#print(wordToCount.items())
wordToList = []
for key, value in wordToCount.items():
temp = [key, value]
wordToList.append(temp)