def search(query):
tokenized_corpus = [doc.split(" ") for doc in corpus]
bm25 = BM25Okapi(tokenized_corpus)
query = query.split(" ")
subquery = []
subquery += query
for item in subquery:
query.append(item.replace('\n', ''))
scores = (bm25.get_scores(query=query))
for score in scores:
if score > 0:
print(score)
if score > 5:
return True
for item in query:
for word in corpus:
if item in exceptions:
return False
if len(item) < 2:
continue
if item.lower().find(word) != -1:
return True
if similarity(item, word) > 0.85:
return True
return False
def suggest_identifier(id, names):
sorted_names = sorted(names,
key=lambda other: jaro_winkler(id, other),
reverse=True)
if len(sorted_names) > 0:
if jaro_winkler(id, sorted_names[0]) > 0.0 and similarity(
id, sorted_names[0]) > 0.5:
return sorted_names[0]
def suggest_identifier(id, names):
sorted_names = sorted(names, key=lambda other: jaro_winkler(id, other), reverse=True)
if len(sorted_names) > 0:
if jaro_winkler(id, sorted_names[0]) > 0.0 and similarity(id, sorted_names[0]) > 0.5:
return sorted_names[0]