def similarity(self, term1, term2):
# stem and remove stop words in two terms first to make them compatible with those stored
parser = Parser()
term1 = parser.tokenise(term1) # after tokenization, it is a list
if term1 == []:
return 0
else:
term1 = parser.tokenise(term1[0])
term2 = parser.tokenise(term2)
if term2 == []:
return 0
else:
term2 = parser.tokenise(term2[0])
try:
index1 = self.keyword_index_mapping[term1[0]]
except:
print term1, ": indexing error 1"
return 0
try:
index2 = self.keyword_index_mapping[term2[0]]
except:
print term2, "indexing error 2"
return 0
return float(
np.dot(self.lsa_matrix[index1], self.lsa_matrix[index2])
/ (np.linalg.norm(self.lsa_matrix[index1]) * np.linalg.norm(self.lsa_matrix[index2]))
)