def compare(self, text_a, text_b):
texta = self.split(self.lower(self.remove_punctuation(self.remove_spec_chars(text_a))))
textb = self.split(self.lower(self.remove_punctuation(self.remove_spec_chars(text_b))))
stemmer = Stemmer()
texta = stemmer.stem_words(texta)
textb = stemmer.stem_words(textb)
set_a = set(texta)
set_b = set(textb)
jaccard_similarity_result = len(set_a & set_b) / len(set_a | set_b)
return jaccard_similarity_result
def compare(self, text_a, text_b):
texta = self.split(
self.lower(self.remove_punctuation(
self.remove_spec_chars(text_a))))
textb = self.split(
self.lower(self.remove_punctuation(
self.remove_spec_chars(text_b))))
texta = self.remove_stopwords(texta)
textb = self.remove_stopwords(textb)
var_1 = text_a
var_2 = text_b
stemmer = Stemmer()
texta = stemmer.stem_words(texta)
textb = stemmer.stem_words(textb)
general_set = set()
for i in texta:
general_set.add(i)
for i in textb:
general_set.add(i)
map_a = {}
map_b = {}
for i in general_set:
map_a[i] = 0
map_b[i] = 0
for i in texta:
map_a[i] = map_a[i] + 1
for i in textb:
map_b[i] = map_b[i] + 1
ab = 0
a = 0
b = 0
for i in general_set:
ab += map_a[i] * map_b[i]
for i in general_set:
a += map_a[i]**2
for i in general_set:
b += map_b[i]**2
cosine_similarity_coefficient = ab / (math.sqrt(a) * math.sqrt(b))
return cosine_similarity_coefficient
def compare(self, text_a, text_b):
texta = self.split(
self.lower(self.remove_punctuation(
self.remove_spec_chars(text_a))))
textb = self.split(
self.lower(self.remove_punctuation(
self.remove_spec_chars(text_b))))
texta = self.remove_stopwords(texta)
textb = self.remove_stopwords(textb)
stemmer = Stemmer()
texta = stemmer.stem_words(texta)
textb = stemmer.stem_words(textb)
general_set = set()
for i in texta:
general_set.add(i)
for i in textb:
general_set.add(i)
map_a = {}
map_b = {}
for i in general_set:
map_a[i] = 0
map_b[i] = 0
for i in texta:
map_a[i] = map_a[i] + 1
for i in textb:
map_b[i] = map_b[i] + 1
ab = 0
a = 0
b = 0
for i in general_set:
if map_a[i] > 0 and map_b[i] > 0:
ab += 1
if map_a[i] > 0:
a += 1
if map_b[i] > 0:
b += 1
dice_similarity_coefficient = (2 * ab) / (a + b)
return dice_similarity_coefficient
def compare(self, text_a, text_b):
texta = self.split(
self.lower(self.remove_punctuation(
self.remove_spec_chars(text_a))))
textb = self.split(
self.lower(self.remove_punctuation(
self.remove_spec_chars(text_b))))
stemmer = Stemmer()
texta = stemmer.stem_words(texta)
textb = stemmer.stem_words(textb)
set_a = set(texta)
set_b = set(textb)
matching_coefficient = len(set_a & set_b) / (min(
len(set_a), len(set_b)))
return matching_coefficient