Spaces:
Sleeping
Sleeping
File size: 1,565 Bytes
8ba15ea 1f22e94 8ba15ea 1f22e94 8ba15ea 36a20b5 8ba15ea 36a20b5 8ba15ea 36a20b5 8ba15ea |
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 |
from preprocess.preprocess import Preprocessor
from processor.matching import prepare_groups_with_ids,new_find_matches_with_ids
class Processor():
def __init__(self, long_types_list, short_types_list, sour_list,
type_wine, gbs, colors_for_trim, grapes, other_words,
sour_merge_dict, type_merge_dict, color_merge_dict,
country_list, normalized_names_dict):
self.preprocessor=Preprocessor(long_types_list, short_types_list, sour_list,
type_wine, gbs, colors_for_trim, grapes, other_words,
sour_merge_dict, type_merge_dict, color_merge_dict,
country_list, normalized_names_dict)
def process(self, products, items, is_items_first=False, th=65, include_alternatives=True):
items, products=self.preprocessor.process(products, items)
print('-----*-----Matching-----*-----')
if is_items_first:
products['new_brand']=products['brand']
items['brand']=items['new_brand']
products_groups = prepare_groups_with_ids(products)
res=new_find_matches_with_ids(items, products_groups, products, name_threshold=th, include_alternatives=include_alternatives)
else:
items_groups = prepare_groups_with_ids(items)
res=new_find_matches_with_ids(products, items_groups, items, name_threshold=th, include_alternatives=include_alternatives)
return res.drop(['type','type_wine','alco','gb'], axis=1), items, products
|