def test_damerau_levenshtein_distance(self):
"""Test for Damerau-Levenshtein Distance between two words"""
l = Levenshtein()
dist = l.Damerau_Levenshtein_Distance(
"all haile whose solempne glorious concepcioun",
"fresche floure in quhom the hevinlie dewe doun fell")
self.assertEqual(dist, 35)
def test_levenshtein_distance(self):
"""Test for Levenshtein Distance between two words"""
l = Levenshtein()
dist = l.Levenshtein_Distance(
"now grete glorious god through grace of himselven",
"and the precious prayer of his pris moder")
self.assertEqual(dist, 36)
def _calculate_ratios(self, list_a, list_b):
"""
Calulate a matrix of string comparisons given two input lists
:param list_a: list [object]
:param list_b: list [object]
:return: list [[Comparison]]
"""
comparisons = []
l = Levenshtein()
# For all strings in list a
for i, str_a in enumerate(list_a):
# Add a new list to our list of lists of comparisons
comparisons.append([])
# Compare str_a to every string in list_b
for str_b in list_b:
# If the sanitize, input flag is set, make the ratio with the sanitized values
if self.sanitize_input:
new_comparison = Comparison(
str_a['text'],
str_b['text'],
l.ratio(str_a['sanitized'], str_b['sanitized'])
)
# Otherwise, make the ratio with the original, unsanitize text strings
else:
new_comparison = Comparison(
str_a['text'],
str_b['text'],
l.ratio(str_a['text'], str_b['text'])
)
# If text metadata is set on this class for text a or b, save that data with the
# comparison
if self.text_ref_a:
new_comparison.set_ref_a(self.text_ref_a)
if self.text_ref_b:
new_comparison.set_ref_b(self.text_ref_b)
# Finally, append the new comparison to the list of comparisons
comparisons[i].append(new_comparison)
return comparisons
def compute_distance_matrix(proper_nouns: List[str]):
"""
Distance matrix with Levenshtein distance.
:param proper_nouns: Items of proper_nouns must be unique
:return:
"""
levenshtein = Levenshtein()
# We try to keep regroup different forms of a lemma
distance_matrix = np.zeros((len(proper_nouns), len(proper_nouns)))
for i in range(len(proper_nouns)):
for j in range(len(proper_nouns)):
distance_matrix[i, j] = levenshtein.Levenshtein_Distance(proper_nouns[i], proper_nouns[j])
return distance_matrix
def test_distance_ratio(self):
"""Test returning simple Levenshtein distance calculation ratio between two strings"""
l = Levenshtein()
ratio = l.ratio("dique deaeque omnes, studium quibus arua tueri,",
"dique deaeque omnes, quibus est tutela per agros,")
self.assertEqual(ratio, 0.71)
def compare_levenshtein(self, other_text):
return Levenshtein().ratio(self.data, other_text)