def Sim2(text1, text2) :
stop = stopwords.words('english')
text1=regexpProcessing(text1)
text2=regexpProcessing(text2)
# convert both texts into upper case
TEXT1=text1.strip()
TEXT2=text2.strip()
TEXT1=TEXT1.lower()
TEXT2=TEXT2.lower()
token1 = generateTokens(TEXT1)
token2 = generateTokens(TEXT2)
t1List=[]
for tok1 in token1:
word1 = Word(tok1)
w1=word1.spellcheck()
correctw=w1[0][0]
confidence = w1[0][1]
if (confidence > 0.8) and (correctw not in stop):
t1List.append(correctw)
t2List=[]
for tok2 in token2:
word2 = Word(tok2)
w2=word2.spellcheck()
correctw=w2[0][0]
confidence = w2[0][1]
if (confidence > 0.8) and (correctw not in stop):
t2List.append(correctw)
for i in range(len(TextItems)):
token = generateTokens(TextItems[i])
tokenList.append(token)
token = []
# spell correction
# POS Tagging
word1 = wn.synset('dog.n.01')
word2 = wn.synset('cat.n.01')
word1.path_similarity(word2)
return CosineSimilarity
