hamza50 commited on
Commit
a1c7ed3
1 Parent(s): 0bda70d

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +7 -8
app.py CHANGED
@@ -6,17 +6,16 @@
6
  @author: Hamza Farooq
7
  """
8
 
9
- import spacy
10
- from spacy.lang.en.stop_words import STOP_WORDS
11
  from string import punctuation
12
  from collections import Counter
13
  from heapq import nlargest
14
  import os
15
- nlp = spacy.load("en_core_web_sm")
16
  from sentence_transformers import SentenceTransformer, CrossEncoder, util
17
  import datetime
18
 
19
- from spacy import displacy
20
  import streamlit as st
21
  import matplotlib.pyplot as plt
22
  from wordcloud import WordCloud
@@ -180,18 +179,18 @@ def main():
180
  for token in text.lower().split():
181
  token = token.strip(string.punctuation)
182
 
183
- if len(token) > 0 and token not in _stop_words.ENGLISH_STOP_WORDS:
184
  tokenized_doc.append(token)
185
  return tokenized_doc
186
 
187
 
188
  def search(query):
189
  # q = [str(userinput)]
190
- doc = nlp(str(userinput))
191
 
192
- ent_html = displacy.render(doc, style="ent", jupyter=False)
193
  # Display the entity visualization in the browser:
194
- st.markdown(ent_html, unsafe_allow_html=True)
195
  ##### BM25 search (lexical search) #####
196
  bm25_scores = bm25.get_scores(bm25_tokenizer(query))
197
  top_n = np.argpartition(bm25_scores, -5)[-5:]
 
6
  @author: Hamza Farooq
7
  """
8
 
9
+
 
10
  from string import punctuation
11
  from collections import Counter
12
  from heapq import nlargest
13
  import os
14
+
15
  from sentence_transformers import SentenceTransformer, CrossEncoder, util
16
  import datetime
17
 
18
+
19
  import streamlit as st
20
  import matplotlib.pyplot as plt
21
  from wordcloud import WordCloud
 
179
  for token in text.lower().split():
180
  token = token.strip(string.punctuation)
181
 
182
+ if len(token) > 0:
183
  tokenized_doc.append(token)
184
  return tokenized_doc
185
 
186
 
187
  def search(query):
188
  # q = [str(userinput)]
189
+ # doc = nlp(str(userinput))
190
 
191
+ # ent_html = displacy.render(doc, style="ent", jupyter=False)
192
  # Display the entity visualization in the browser:
193
+ st.markdown(query, unsafe_allow_html=True)
194
  ##### BM25 search (lexical search) #####
195
  bm25_scores = bm25.get_scores(bm25_tokenizer(query))
196
  top_n = np.argpartition(bm25_scores, -5)[-5:]