def get_similarities(string,
strings,
method='jaro_winkler',
similarity_function=None,
case_sensitivity=1.0,
first_char_weight=0.0,
first_word_weight=0.0,
echo=0):
"""
:type string: str
:type strings: list[str]
:type treat_as_sentence: bool
:param str method: can be one of 'jaro_winkler', 'levenshtein', 'sentence_jaro_winkler', 'sentence_levenshtein'
:type case_sensitivity: float
:type first_char_weight: float
:type first_word_weight: float
:rtype:
"""
echo = max(0, echo)
string = str(string)
text = string + ' ? '
return list(
ProgressBar.map(function=lambda x: get_similarity(
s1=string,
s2=x,
method=method,
similarity_function=similarity_function,
first_char_weight=first_char_weight,
case_sensitivity=case_sensitivity,
first_word_weight=first_word_weight),
iterable=strings,
iterable_text=strings,
text=text,
echo=echo))
def find_most_similar(strings,
candidates,
candidate_ids=None,
string_ids=None,
method='jaro_winkler',
similarity_function=None,
case_sensitivity=1.0,
first_char_weight=0.0,
first_word_weight=0.0,
num_results=1,
echo=0):
"""
:type strings: str or list[str]
:type candidates: list[str]
:type candidate_ids: list or NoneType
:type string_ids: list or NoneType
:param str method: can be one of 'jaro_winkler', 'levenshtein', 'sentence_jaro_winkler', 'sentence_levenshtein'
:type treat_as_sentence: bool
:type first_char_weight: float
:type first_word_weight: float
:type case_sensitivity: float
:rtype: pd.DataFrame
"""
echo = max(0, echo)
if string_ids is None:
string_ids = range(len(strings))
return pd.concat(
list(
ProgressBar.map(
function=lambda x: find_most_similar_for_one_string(
string=x[0],
string_id=x[1],
candidates=candidates,
candidate_ids=candidate_ids,
method=method,
similarity_function=similarity_function,
case_sensitivity=case_sensitivity,
first_char_weight=first_char_weight,
first_word_weight=first_word_weight,
num_results=num_results,
echo=echo - 1),
iterable=list(zip(strings, string_ids)),
iterable_text=strings,
echo=echo))).reset_index(drop=True)[[
'string_id', 'string', 'candidate_id', 'candidate',
'similarity_rank', 'similarity'
]]