def test_compare_implementations():
# Compare the implementations of python-Levenshtein to our
# pure-Python implementations
if Levenshtein is False:
raise unittest.SkipTest
# Test on strings with randomly placed common char
for string1, string2 in _random_common_char_pairs(n_pairs=50):
assert (string_distances._jaro_winkler(
string1, string2,
winkler=False) == Levenshtein.jaro(string1, string2))
assert (string_distances._jaro_winkler(
string1, string2,
winkler=True) == Levenshtein.jaro_winkler(string1, string2))
assert (string_distances.levenshtein_ratio(
string1, string2) == Levenshtein.ratio(string1, string2))
# Test on random strings
for string1, string2 in _random_string_pairs(n_pairs=50):
assert (string_distances._jaro_winkler(
string1, string2,
winkler=False) == Levenshtein.jaro(string1, string2))
assert (string_distances._jaro_winkler(
string1, string2,
winkler=True) == Levenshtein.jaro_winkler(string1, string2))
assert (string_distances.levenshtein_ratio(
string1, string2) == Levenshtein.ratio(string1, string2))
def test_compare_implementations():
# Compare the implementations of python-Levenshtein to our
# pure-Python implementations
if Levenshtein is False:
raise unittest.SkipTest
for string1, string2 in _random_string_pairs(n_pairs=10):
assert (string_distances._jaro_winkler(
string1, string2,
winkler=False) == Levenshtein.jaro(string1, string2))
assert (string_distances._jaro_winkler(
string1, string2) == Levenshtein.jaro_winkler(string1, string2))
assert (string_distances.levenshtein_ratio(
string1, string2) == Levenshtein.ratio(string1, string2))
def test_similarity_encoder():
X = np.array(['aa', 'aaa', 'aaab']).reshape(-1, 1)
X_test = np.array([['Aa', 'aAa', 'aaa', 'aaab', ' aaa c']]).reshape(-1, 1)
similarities = ['levenshtein-ratio', 'jaro-winkler', 'jaro', 'ngram']
for similarity in similarities:
model = similarity_encoder.SimilarityEncoder(similarity=similarity,
handle_unknown='ignore')
encoder = model.fit(X).transform(X_test)
if similarity == 'levenshtein-ratio':
ans = np.zeros((len(X_test), len(X)))
for i, x_t in enumerate(X_test.reshape(-1)):
for j, x in enumerate(X.reshape(-1)):
ans[i, j] = string_distances.levenshtein_ratio(x_t, x)
assert np.array_equal(encoder, ans)
if similarity == 'jaro-winkler':
ans = np.zeros((len(X_test), len(X)))
for i, x_t in enumerate(X_test.reshape(-1)):
for j, x in enumerate(X.reshape(-1)):
ans[i, j] = string_distances.jaro_winkler(x_t, x)
assert np.array_equal(encoder, ans)
if similarity == 'jaro':
ans = np.zeros((len(X_test), len(X)))
for i, x_t in enumerate(X_test.reshape(-1)):
for j, x in enumerate(X.reshape(-1)):
ans[i, j] = string_distances.jaro(x_t, x)
assert np.array_equal(encoder, ans)
if similarity == 'ngram':
ans = np.zeros((len(X_test), len(X)))
for i, x_t in enumerate(X_test.reshape(-1)):
for j, x in enumerate(X.reshape(-1)):
ans[i, j] = string_distances.ngram_similarity(x_t, x, 3)
assert np.array_equal(encoder, ans)
def test_identical_strings():
# Test that if 2 strings are the same, the similarity
for string1, _ in _random_string_pairs(n_pairs=10):
assert string_distances.jaro(string1, string1) == 1
assert string_distances.jaro_winkler(string1, string1) == 1
assert string_distances.levenshtein_ratio(string1, string1) == 1