File size: 1,469 Bytes
c837b79 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 |
import mojimoji
import pandas as pd
from rapidfuzz import fuzz, process
class EntityDictionary:
def __init__(self, path):
self.df = pd.read_csv(path)
def get_candidates_list(self):
return self.df.iloc[:, 0].to_list()
def get_normalization_list(self):
return self.df.iloc[:, 2].to_list()
def get_normalized_term(self, term):
return self.df[self.df.iloc[:, 0] == term].iloc[:, 2].item()
class DiseaseDict(EntityDictionary):
def __init__(self):
super().__init__('dictionaries/disease_dict.csv')
class DrugDict(EntityDictionary):
def __init__(self):
super().__init__('dictionaries/drug_dict.csv')
class EntityNormalizer:
def __init__(self, database: EntityDictionary, matching_method=fuzz.ratio, matching_threshold=0):
self.database = database
self.matching_method = matching_method
self.matching_threshold = matching_threshold
self.candidates = [mojimoji.han_to_zen(x) for x in self.database.get_candidates_list()]
def normalize(self, term):
term = mojimoji.han_to_zen(term)
preferred_candidate = process.extractOne(term, self.candidates, scorer=self.matching_method)
score = preferred_candidate[1]
if score > self.matching_threshold:
ret = self.database.get_normalized_term(preferred_candidate[0])
return ('' if pd.isna(ret) else ret), score
else:
return '', score
|