spacy fix

Home.py

@@ -160,6 +160,7 @@ def application():
     ###Models
     @st.cache_resource
     def setup_models():
+        spacy.cli.download("en_core_web_md")
         return Title_Generator('./t5_model', slim_df), input_manager(vector_df, slim_df, search_tokens),  model_control(apikey=st.secrets.key,model_id=st.secrets.model)
 
     Tgen, iman, mctrl = setup_models()

description_generator.py

@@ -7,13 +7,12 @@ from operator import itemgetter
 #user input manager class
 class input_manager:
   
-  #initialize key dictionary from vector data frame and set community top N
-  def __init__(self,key_df, slim_df, search_tokens, top_n=10):
+  #initialize key dictionary from vector data frame
+  def __init__(self,key_df, slim_df, search_tokens):
         self.key_df = key_df
         self.slim_df = slim_df
         self.search_tokens = search_tokens
         self.key = dict(zip(list(key_df.columns),np.zeros(len(key_df.columns))))
-        self.top_n = top_n
         self.nlp = spacy.load("en_core_web_md")
 
   #translate input text to vector

requirements.txt

@@ -8,6 +8,4 @@ sentencepiece==0.1.97
 spacy==3.5.1
 streamlit==1.20.0
 torch==2.0.0
-transformers==4.27.3
-en_core_web_sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.4.0/en_core_web_sm-3.4.0-py3-none-any.whl
-en_core_web_md @ https://github.com/explosion/spacy-models/releases/download/en_core_web_md-3.4.0/en_core_web_md-3.4.0-py3-none-any.whl
+transformers==4.27.3

title_generator.py

@@ -5,10 +5,12 @@ from gensim.parsing import preprocess_string, strip_tags, strip_numeric, strip_m
 import spacy
 import torch
 from transformers import T5ForConditionalGeneration,T5Tokenizer
+import random
+import itemgetter
 
 #Custom text tokenizer from https://github.com/canunj/deconstructing_games by N Canu & K Chen
 def doc_text_preprocessing(ser):
-    nlp=spacy.load("en_core_web_sm", exclude=['parser','ner','textcat'])
+    nlp=spacy.load("en_core_web_md", exclude=['parser','ner','textcat'])
 
     """text processing steps"""
     import re
@@ -68,8 +70,6 @@ class Title_Generator:
         return candidates, description
     
     def candidate_score(self,candidates,ex_check=None):
-        import random
-        from operator import itemgetter
         
         if ex_check != None:
             pat = re.compile("((?:" + "|".join(map(re.escape, candidates[0]+[cand.upper() for cand in candidates[0]])) + "|" + "|".join(ex_check) +"))")