Update src/utils.py

src/utils.py

@@ -11,15 +11,16 @@ import numpy as np
 import spacy
 from spacy.tokens import DocBin
 from spacy.training import offsets_to_biluo_tags
-import en_fetch_ner_spacy_tsf
-nlp = en_fetch_ner_spacy_tsf.load()
+# import en_fetch_ner_spacy_tsf
+# nlp = en_fetch_ner_spacy_tsf.load()
 # clear_output()
 
-import nltk
+# import nltk
 # nltk.download('stopwords')
 
-from nltk.corpus import stopwords
+# from nltk.corpus import stopwords
 # stop_words = set(stopwords.words('english'))
+stop_words = ["at", "in", "get"]
 # additional_stop_words = {'pack'}
 # stop_words.update(additional_stop_words)
 # clear_output()
@@ -194,7 +195,7 @@ def offer_finder_by_category(search_input: str, search_category_tuple: Tuple, ca
             jaccard_sim_score = get_jaccard_sim(search_input, potential_offers)
             output = extract_similar_offers(jaccard_sim_score, threshold)
         elif score not in ['cosine', 'jaccard']:
-            raise ValueError(f'Please enter a valid score: cosine or jaccard; Not {score}')
+            raise ParamsInputError(f'Please enter a valid score: cosine or jaccard; Not {score}')
         else: # this means something else is worng
             raise UnknownError(f'Something must be broken. Please try again.')
         return output
@@ -251,7 +252,7 @@ def offer_finder_by_entity(search_input: str, entities: Tuple, offers_data: pd.D
         return None
 
 
-def search_offers(search_input: str, offers: pd.DataFrame, category_dict: Dict, brand_belong_category_dict: Dict, score: str, score_threshold: float = 0.0):
+def search_offers(search_input: str, offers: pd.DataFrame, category_dict: Dict, brand_belong_category_dict: Dict, score: str = "jaccard", score_threshold: float = 0.0):
     """Main function. Takes in a serach_input and decide whether it can find entities or not. Then excecute the appropriate functions
     Inputs:
     - search_input: a string that a user enters