class EudexTestCases(unittest.TestCase):
"""Test Eudex distance functions.
abydos.distance.Eudex
"""
cmp = Eudex()
def test_eudex_dist_abs(self):
"""Test abydos.distance.Eudex.dist_abs."""
# Base cases
self.assertEqual(self.cmp.dist_abs('', ''), 0)
self.assertEqual(Eudex(None).dist_abs('', ''), 0)
self.assertEqual(Eudex('fibonacci').dist_abs('', ''), 0)
self.assertEqual(Eudex([10, 1, 1, 1]).dist_abs('', ''), 0)
self.assertEqual(Eudex(_yield_1).dist_abs('', ''), 0)
self.assertEqual(self.cmp.dist_abs('', '', normalized=True), 0)
self.assertEqual(self.cmp.dist_abs('Niall', 'Niall'), 0)
self.assertEqual(Eudex(None).dist_abs('Niall', 'Niall'), 0)
self.assertEqual(Eudex('fibonacci').dist_abs('Niall', 'Niall'), 0)
self.assertEqual(Eudex([10, 1, 1, 1]).dist_abs('Niall', 'Niall'), 0)
self.assertEqual(Eudex(_yield_1).dist_abs('Niall', 'Niall'), 0)
self.assertEqual(self.cmp.dist_abs('Niall', 'Niall', normalized=True),
0)
self.assertEqual(self.cmp.dist_abs('Niall', 'Neil'), 2)
self.assertEqual(Eudex(None).dist_abs('Niall', 'Neil'), 1)
self.assertEqual(Eudex('fibonacci').dist_abs('Niall', 'Neil'), 2)
self.assertEqual(Eudex([10, 1, 1, 1]).dist_abs('Niall', 'Neil'), 1)
self.assertEqual(Eudex(_yield_1).dist_abs('Niall', 'Neil'), 1)
self.assertAlmostEqual(
self.cmp.dist_abs('Niall', 'Neil', normalized=True), 0.00098039)
self.assertEqual(self.cmp.dist_abs('Niall', 'Colin'), 524)
self.assertEqual(Eudex(None).dist_abs('Niall', 'Colin'), 10)
self.assertEqual(Eudex('fibonacci').dist_abs('Niall', 'Colin'), 146)
self.assertEqual(Eudex([10, 1, 1, 1]).dist_abs('Niall', 'Colin'), 42)
self.assertEqual(Eudex(_yield_1).dist_abs('Niall', 'Colin'), 10)
self.assertAlmostEqual(
self.cmp.dist_abs('Niall', 'Colin', normalized=True), 0.25686274)
# Test wrapper
self.assertEqual(eudex_hamming('Niall', 'Neil', 'fibonacci'), 2)
def test_eudex_dist(self):
"""Test abydos.distance.Eudex.dist."""
# Base cases
self.assertEqual(self.cmp.dist('', ''), 0)
self.assertEqual(Eudex(None).dist('', ''), 0)
self.assertEqual(Eudex('fibonacci').dist('', ''), 0)
self.assertEqual(self.cmp.dist('Niall', 'Niall'), 0)
self.assertEqual(Eudex(None).dist('Niall', 'Niall'), 0)
self.assertEqual(Eudex('fibonacci').dist('Niall', 'Niall'), 0)
self.assertAlmostEqual(self.cmp.dist('Niall', 'Neil'), 0.00098039)
self.assertAlmostEqual(Eudex(None).dist('Niall', 'Neil'), 0.11111111)
self.assertAlmostEqual(
Eudex('fibonacci').dist('Niall', 'Neil'), 0.00287356)
self.assertAlmostEqual(self.cmp.dist('Niall', 'Colin'), 0.25686275)
self.assertAlmostEqual(Eudex(None).dist('Niall', 'Colin'), 0.16666667)
self.assertAlmostEqual(
Eudex('fibonacci').dist('Niall', 'Colin'), 0.20977011)
with self.assertRaises(ValueError):
Eudex('veryLarge').dist_abs('Niall', 'Colin')
# Test wrapper
self.assertAlmostEqual(dist_eudex('Niall', 'Neil', 'fibonacci'),
0.00287356)
def test_eudex_sim(self):
"""Test abydos.distance.Eudex.sim."""
# Base cases
self.assertEqual(self.cmp.sim('', ''), 1)
self.assertEqual(Eudex(None).sim('', ''), 1)
self.assertEqual(Eudex('fibonacci').sim('', ''), 1)
self.assertEqual(self.cmp.sim('Niall', 'Niall'), 1)
self.assertEqual(Eudex(None).sim('Niall', 'Niall'), 1)
self.assertEqual(Eudex('fibonacci').sim('Niall', 'Niall'), 1)
self.assertAlmostEqual(self.cmp.sim('Niall', 'Neil'), 0.99901961)
self.assertAlmostEqual(Eudex(None).sim('Niall', 'Neil'), 0.88888889)
self.assertAlmostEqual(
Eudex('fibonacci').sim('Niall', 'Neil'), 0.99712644)
self.assertAlmostEqual(self.cmp.sim('Niall', 'Colin'), 0.74313725)
self.assertAlmostEqual(Eudex(None).sim('Niall', 'Colin'), 0.83333333)
self.assertAlmostEqual(
Eudex('fibonacci').sim('Niall', 'Colin'), 0.79022989)
# Test wrapper
self.assertAlmostEqual(sim_eudex('Niall', 'Neil', 'fibonacci'),
0.99712644)
def __init__(self,
model='latin',
prefilter=True,
allow_alt_surname=True,
allow_initials=True,
allow_missing_components=True):
# user-provided parameters
self.model = model
self.allow_alt_surname = allow_alt_surname
self.allow_initials = allow_initials
self.allow_missing_components = allow_missing_components
self.prefilter = prefilter
if self.prefilter:
self.refined_soundex = {
'b': 1,
'p': 1,
'f': 2,
'v': 2,
'c': 3,
'k': 3,
's': 3,
'g': 4,
'j': 4,
'q': 5,
'x': 5,
'z': 5,
'd': 6,
't': 6,
'l': 7,
'm': 8,
'n': 8,
'r': 9
}
# verify user-supplied class arguments
model_dir = self.validate_parameters()
self.impH = input_helpers.InputHelper()
# Phonetic Encoder
self.pe = Ainsworth()
# Soundex Firstname Algorithm
self.pshp_soundex_first = PSHPSoundexFirst()
# Soundex Lastname Algorithm
self.pshp_soundex_last = PSHPSoundexLast()
# String Distance algorithms
self.algos = [
IterativeSubString(),
BISIM(),
DiscountedLevenshtein(),
Prefix(),
LCSstr(),
MLIPNS(),
Strcmp95(),
MRA(),
Editex(),
SAPS(),
FlexMetric(),
JaroWinkler(mode='Jaro'),
HigueraMico(),
Sift4(),
Eudex(),
ALINE(),
CovingtonGuard(),
PhoneticEditDistance()
]
self.algo_names = [
'iterativesubstring', 'bisim', 'discountedlevenshtein', 'prefix',
'lcsstr', 'mlipns', 'strcmp95', 'mra', 'editex', 'saps',
'flexmetric', 'jaro', 'higueramico', 'sift4', 'eudex', 'aline',
'covington', 'phoneticeditdistance'
]
# String Distance Pipeline (Level 0/Base Model)
self.baseModel = joblib.load(os.path.join(model_dir, 'base.pkl'))
# Character Embedding Network (Level 0/Base Model)
self.vocab = preprocess.VocabularyProcessor(
max_document_length=15,
min_frequency=0).restore(os.path.join(model_dir, 'vocab'))
siamese_model = os.path.join(model_dir, 'siamese')
# start tensorflow session
graph = tf.Graph()
with graph.as_default() as graph:
self.sess = tf.Session(
) if tf.__version__[0] == '1' else tf.compat.v1.Session()
with self.sess.as_default():
# Load the saved meta graph and restore variables
if tf.__version__[0] == '1':
saver = tf.train.import_meta_graph(
'{}.meta'.format(siamese_model))
self.sess.run(tf.global_variables_initializer())
else:
saver = tf.compat.v1.train.import_meta_graph(
'{}.meta'.format(siamese_model))
self.sess.run(tf.compat.v1.global_variables_initializer())
saver.restore(self.sess, siamese_model)
# Get the placeholders from the graph by name
self.input_x1 = graph.get_operation_by_name('input_x1').outputs[0]
self.input_x2 = graph.get_operation_by_name('input_x2').outputs[0]
self.dropout_keep_prob = graph.get_operation_by_name(
'dropout_keep_prob').outputs[0]
self.prediction = graph.get_operation_by_name(
'output/distance').outputs[0]
self.sim = graph.get_operation_by_name(
'accuracy/temp_sim').outputs[0]
# Logreg (Level 1/Meta Model)
self.metaModel = joblib.load(os.path.join(model_dir, 'meta.pkl'))
# seen names (mapping dict from raw name to processed name)
self.seen_names = {}
# seen pairs (mapping dict from name pair tuple to similarity)
self.seen_pairs = {}
# user scores (mapping dict from name pair tuple to similarity)
self.user_scores = {}