spacy fix

description_generator.py

@@ -1,7 +1,7 @@
 
 import numpy as np
 import re
-import spacy, en_core_web_md
+import spacy
 import openai
 from operator import itemgetter
 #user input manager class
@@ -15,10 +15,13 @@ class input_manager:
         self.key = dict(zip(list(key_df.columns),np.zeros(len(key_df.columns))))
         self.top_n = top_n
 
+        spacy.cli.download("en_core_web_md",'--no-deps')
+        self.nlp = spacy.load("en_core_web_md")
+
   #translate input text to vector
   def set_input(self,input_cats):
     #need setup to apply correct group tag to values
-    nlp=spacy.load("en_core_web_md")
+    
     #separate known/unknown features
     k_flags = [cat for cat in input_cats if cat in list(self.key.keys())]
     unk_flags = [cat for cat in input_cats if cat not in list(self.key.keys())]
@@ -29,23 +32,23 @@ class input_manager:
       outs = []
       for word in unk_flags:
         if re.match(r"game_type_",word):
-          tok = nlp(word.split("_")[-1])
+          tok = self.nlp(word.split("_")[-1])
           mtch = max([(key,key.similarity(tok)) for key in self.search_tokens[0]],key=itemgetter(1))
           #if no known match is found (model doesn't recognize input word), we're going to discard - other solutions performance prohibitive
           if mtch[1]>0:
             outs.append("game_type_"+mtch[0])
         elif re.match(r"mechanic_",word):
-          tok = nlp(word.split("_")[-1])
+          tok = self.nlp(word.split("_")[-1])
           mtch = max([(key,key.similarity(tok)) for key in self.search_tokens[1]],key=itemgetter(1))
           if mtch[1]>0:
             outs.append("mechanic_"+mtch[0])
         elif re.match(r"category_",word):
-          tok = nlp(word.split("_")[-1])
+          tok = self.nlp(word.split("_")[-1])
           mtch=max([(key,key.similarity(tok)) for key in self.search_tokens[2]],key=itemgetter(1))
           if mtch[1]>0:
             outs.append("category_"+mtch[0])
         elif re.match(r"family_",word):
-          tok = nlp(word.split("_")[-1])
+          tok = self.nlp(word.split("_")[-1])
           mtch=max([(key,key.similarity(tok)) for key in self.search_tokens[3]],key=itemgetter(1))
           if mtch[1]>0:
             outs.append("family_"+str(mtch[0]))

requirements.txt

@@ -9,4 +9,3 @@ spacy==3.5.1
 streamlit==1.20.0
 torch==2.0.0
 transformers==4.27.3
-en_core_web_md==3.5.0