def main(filepath):
linkset = defaultdict(set)
df = pd.read_csv(filepath)
for r in df.to_dict(orient='records'):
dataset = r['dataset']
a = r['owner_a']
b = r['owner_b']
p = token_sort_ratio(a, b)
if p > .8:
print(round(p, 2), a, b, sep='\t')
if r['actType'] not in [
"Boedelinventaris", "Boedelscheiding", "Testament",
"Overig", "Huwelijkse voorwaarden", "Kwitantie"
]:
continue
linkset[r['inventory']].add(
(r['dataset'], r['record'], r['actType']))
return linkset
def are_nouns_similar(noun1, noun2):
# jaccard, jaro_winkler, hamming, token_sort_ratio
jaccardD = jaccard(noun1, noun2)
jaro = jaro_winkler(noun1, noun2)
lev = levenshtein(noun1, noun2)
hammingD = hamming(noun1, noun2)
tsr = token_sort_ratio(noun1, noun2)
dice = dice_coefficient(noun1, noun2)
if lev > 0.42:
return True
def aggregate_term_variants(terms,
acro_defs=None,
fuzzy_dedupe=True):
"""
Take a set of unique terms and aggregate terms that are symbolic, lexical,
and ordering variants of each other, as well as acronyms and fuzzy string matches.
Args:
terms (Set[str]): set of unique terms with potential duplicates
acro_defs (dict): if not None, terms that are acronyms will be
aggregated with their definitions and terms that are definitions will
be aggregated with their acronyms
fuzzy_dedupe (bool): if True, fuzzy string matching will be used
to aggregate similar terms of a sufficient length
Returns:
List[Set[str]]: each item is a set of aggregated terms
Notes:
Partly inspired by aggregation of variants discussed in
Park, Youngja, Roy J. Byrd, and Branimir K. Boguraev.
"Automatic glossary extraction: beyond terminology identification."
Proceedings of the 19th international conference on Computational linguistics-Volume 1.
Association for Computational Linguistics, 2002.
"""
agg_terms = []
seen_terms = set()
for term in sorted(terms, key=len, reverse=True):
if term in seen_terms:
continue
variants = set([term])
seen_terms.add(term)
# symbolic variations
if '-' in term:
variant = term.replace('-', ' ').strip()
if variant in terms.difference(seen_terms):
variants.add(variant)
seen_terms.add(variant)
if '/' in term:
variant = term.replace('/', ' ').strip()
if variant in terms.difference(seen_terms):
variants.add(variant)
seen_terms.add(variant)
# lexical variations
term_words = term.split()
# last_word = term_words[-1]
# # assume last word is a noun
# last_word_lemmatized = lemmatizer.lemmatize(last_word, 'n')
# # if the same, either already a lemmatized noun OR a verb; try verb
# if last_word_lemmatized == last_word:
# last_word_lemmatized = lemmatizer.lemmatize(last_word, 'v')
# # if at least we have a new term... add it
# if last_word_lemmatized != last_word:
# term_lemmatized = ' '.join(term_words[:-1] + [last_word_lemmatized])
# if term_lemmatized in terms.difference(seen_terms):
# variants.add(term_lemmatized)
# seen_terms.add(term_lemmatized)
# if term is an acronym, add its definition
# if term is a definition, add its acronym
if acro_defs:
for acro, def_ in acro_defs.items():
if acro.lower() == term.lower():
variants.add(def_.lower())
seen_terms.add(def_.lower())
break
elif def_.lower() == term.lower():
variants.add(acro.lower())
seen_terms.add(acro.lower())
break
# if 3+ -word term differs by one word at the start or the end
# of a longer phrase, aggregate
if len(term_words) > 2:
term_minus_first_word = ' '.join(term_words[1:])
term_minus_last_word = ' '.join(term_words[:-1])
if term_minus_first_word in terms.difference(seen_terms):
variants.add(term_minus_first_word)
seen_terms.add(term_minus_first_word)
if term_minus_last_word in terms.difference(seen_terms):
variants.add(term_minus_last_word)
seen_terms.add(term_minus_last_word)
# check for "X of Y" <=> "Y X" term variants
if ' of ' in term:
split_term = term.split(' of ')
variant = split_term[1] + ' ' + split_term[0]
if variant in terms.difference(seen_terms):
variants.add(variant)
seen_terms.add(variant)
# intense de-duping for sufficiently long terms
if fuzzy_dedupe is True and len(term) >= 13:
for other_term in sorted(terms.difference(seen_terms), key=len, reverse=True):
if len(other_term) < 13:
break
tsr = token_sort_ratio(term, other_term)
if tsr > 0.93:
variants.add(other_term)
seen_terms.add(other_term)
break
agg_terms.append(variants)
return agg_terms
def test_empty(self, text_pairs):
for text1, text2 in text_pairs:
assert similarity.token_sort_ratio(text1, "") == 0.0
def test_identity(self, text_pairs):
for text1, text2 in text_pairs:
assert similarity.token_sort_ratio(text1, text1) == pytest.approx(1.0, rel=1e-3)
assert similarity.token_sort_ratio(text2, text2) == pytest.approx(1.0, rel=1e-3)
def test_default(self, text_pairs):
for text1, text2 in text_pairs:
assert 0.0 <= similarity.token_sort_ratio(text1, text2) <= 1.0
