def test_iterable_input(self):
"""Function should function properly when called with an iterable"""
self.assertEqual(fuzzycomp.levenshtein_distance(["H", "e", "l", "l", "o"], ["H", "e", "l", "l", "o"]), 0)
self.assertEqual(
fuzzycomp.levenshtein_distance(["S", "a", "t", "u", "r", "d", "a", "y"], ["S", "u", "n", "d", "a", "y"]), 3
)
self.assertEqual(fuzzycomp.levenshtein_distance(("H", "e", "l", "l", "o"), ("H", "e", "l", "l", "o")), 0)
self.assertEqual(
fuzzycomp.levenshtein_distance(("S", "a", "t", "u", "r", "d", "a", "y"), ("S", "u", "n", "d", "a", "y")), 3
)
def extractVenueFeatures(A,B):
# remove pontuation
A = re.sub(r'[^\w\s]','',A)
# remove pontuation
B = re.sub(r'[^\w\s]','',B)
# remove multiple spaces
A = re.sub(' +',' ',A)
B = re.sub(' +',' ',B)
if A == '':
A = '-';
if B == '':
B = '-';
charactersA = numpy.zeros(26)
for char in A:
if char >= 'a' and char <= 'z':
charactersA[ord(char)-97]+=1
charactersB = numpy.zeros(26)
for char in B:
if char >= 'a' and char <= 'z':
charactersB[ord(char)-97]+=1
subtraction = numpy.absolute(charactersA-charactersB)
distance = numpy.sum(subtraction)
max_chars = max(numpy.sum(charactersA),numpy.sum(charactersB))
if (max_chars ==0):
measure =0
else:
measure = distance/float(max_chars)
return [measure, fuzzycomp.levenshtein_distance(A,B), fuzzycomp.jaccard_distance(A,B), fuzzycomp.jaro_distance(A,B)]
def test_iterable_input(self):
"""Function should function properly when called with an iterable"""
self.assertEqual(
fuzzycomp.levenshtein_distance(["H", "e", "l", "l", "o"],
["H", "e", "l", "l", "o"]), 0)
self.assertEqual(
fuzzycomp.levenshtein_distance(
["S", "a", "t", "u", "r", "d", "a", "y"],
["S", "u", "n", "d", "a", "y"]), 3)
self.assertEqual(
fuzzycomp.levenshtein_distance(("H", "e", "l", "l", "o"),
("H", "e", "l", "l", "o")), 0)
self.assertEqual(
fuzzycomp.levenshtein_distance(
("S", "a", "t", "u", "r", "d", "a", "y"),
("S", "u", "n", "d", "a", "y")), 3)
def extractCathegoryFeatures(A,B):
matches=re.findall(r"\'(.+?)\'",A)
a = " ".join(matches)
matches=re.findall(r"\'(.+?)\'",B)
b = " ".join(matches)
a = a.replace("&", "")
a = re.sub(r'[^\w\s]','',a)
a = re.sub(' +',' ',a)
b = b.replace("&", "")
b = re.sub(r'[^\w\s]','',b)
b = re.sub(' +',' ',b)
a = a.split()
b = b.split()
if not a:
a.append("-")
if not b:
b.append("-")
min_leven = 99999;
value_leven =0;
for elem1 in a:
for elem2 in b:
if elem1 == "":
elem1 = "-"
if elem2 == "":
elem2 = "-"
lev = fuzzycomp.levenshtein_distance(elem1,elem2)
if lev < min_leven:
value_leven = lev
min_leven = value_leven
return value_leven
def extractVenueFeatures(A, B):
# remove pontuation
A = re.sub(r'[^\w\s]', '', A)
# remove pontuation
B = re.sub(r'[^\w\s]', '', B)
# remove multiple spaces
A = re.sub(' +', ' ', A)
B = re.sub(' +', ' ', B)
if A == '':
A = '-'
if B == '':
B = '-'
charactersA = numpy.zeros(26)
for char in A:
if char >= 'a' and char <= 'z':
charactersA[ord(char) - 97] += 1
charactersB = numpy.zeros(26)
for char in B:
if char >= 'a' and char <= 'z':
charactersB[ord(char) - 97] += 1
subtraction = numpy.absolute(charactersA - charactersB)
distance = numpy.sum(subtraction)
max_chars = max(numpy.sum(charactersA), numpy.sum(charactersB))
if (max_chars == 0):
measure = 0
else:
measure = distance / float(max_chars)
return [
measure,
fuzzycomp.levenshtein_distance(A, B),
fuzzycomp.jaccard_distance(A, B),
fuzzycomp.jaro_distance(A, B)
]
def extractCathegoryFeatures(A, B):
matches = re.findall(r"\'(.+?)\'", A)
a = " ".join(matches)
matches = re.findall(r"\'(.+?)\'", B)
b = " ".join(matches)
a = a.replace("&", "")
a = re.sub(r'[^\w\s]', '', a)
a = re.sub(' +', ' ', a)
b = b.replace("&", "")
b = re.sub(r'[^\w\s]', '', b)
b = re.sub(' +', ' ', b)
a = a.split()
b = b.split()
if not a:
a.append("-")
if not b:
b.append("-")
min_leven = 99999
value_leven = 0
for elem1 in a:
for elem2 in b:
if elem1 == "":
elem1 = "-"
if elem2 == "":
elem2 = "-"
lev = fuzzycomp.levenshtein_distance(elem1, elem2)
if lev < min_leven:
value_leven = lev
min_leven = value_leven
return value_leven
def test_case_difference(self):
"""Algorithm should be case sensitive"""
self.assertNotEqual(fuzzycomp.levenshtein_distance("HELLO", "hello"), 0)
def test_valid_input(self):
"""Algorithm should return correct values under valid input"""
self.assertEqual(fuzzycomp.levenshtein_distance("Hello", "Hello"), 0)
self.assertEqual(fuzzycomp.levenshtein_distance("Saturday", "Sunday"), 3)
def test_case_difference(self):
"""Algorithm should be case sensitive"""
self.assertNotEqual(fuzzycomp.levenshtein_distance("HELLO", "hello"),
0)
def test_valid_input(self):
"""Algorithm should return correct values under valid input"""
self.assertEqual(fuzzycomp.levenshtein_distance("Hello", "Hello"), 0)
self.assertEqual(fuzzycomp.levenshtein_distance("Saturday", "Sunday"),
3)
