Update mapping.py

mapping.py

@@ -13,49 +13,54 @@ def get_mapping(prep_text):
     
   tags_list = classify(event_info)
   tags_list = tags_list['tags']
+
+  if tags_list!=[]:
     
-  event_discr_embeddings = model_sent.encode([' '.join(tags_list)],
-                                      batch_size=250,
-                                      show_progress_bar=True)
+      event_discr_embeddings = model_sent.encode([' '.join(tags_list)],
+                                          batch_size=250,
+                                          show_progress_bar=True)
+        
+      event_embedd = event_discr_embeddings[0]
+      sectors = pd.read_excel('sect_other.xlsx', sheet_name = 'sectors')
+      sectors['name_clean'] = sectors['name'].str.replace('&','').str.strip()
+      sectors['name_clean'] = sectors['name_clean'].str.replace('IT','information technology').str.replace(',','').str.lower()
     
-  event_embedd = event_discr_embeddings[0]
-  sectors = pd.read_excel('sect_other.xlsx', sheet_name = 'sectors')
-  sectors['name_clean'] = sectors['name'].str.replace('&','').str.strip()
-  sectors['name_clean'] = sectors['name_clean'].str.replace('IT','information technology').str.replace(',','').str.lower()
-
-  industries = pd.read_excel('sect_other.xlsx', sheet_name = 'other_indus')
-  industries['industries_name_clean'] = industries['name'].str.replace('&','').str.strip()
-  industries['industries_name_clean'] = industries['industries_name_clean'].str.replace('IT','information technology').str.replace(',','').str.lower()
-
-  other_industries = pd.read_csv('other_industries.csv')
-  other_industries['other_industries_name_clean'] = other_industries['Industry'].str.replace('-',' ').str.replace('/',' ').str.replace('(',' ').str.replace(')',' ').replace('&',' ').str.strip().str.lower()
-  
-  n_neighbors = 1
-  threshold = 0.40
-
-  #sectors
-  distances, indices = sector_model.kneighbors([event_embedd], n_neighbors=2)
-  name_index = indices[0]
-  distance_name = str(distances[0])
-  topic_name = []
-  for index_i in name_index:
-    topic_name.append(sectors['name_clean'].tolist()[index_i])
-  topic_name = str(topic_name)
-
-
-  #industries
-  distances_indus, indices_indus = indus_model.kneighbors([event_embedd], n_neighbors=n_neighbors)
-  name_index_indus = indices_indus[0][0]
-  distance_name_indus = distances_indus[0][0]
-  topic_name_indus = industries['industries_name_clean'].tolist()[name_index_indus]
-
-  #other_industries
-  distances_other, indices_other = other_indus_model.kneighbors([event_embedd], n_neighbors=3)
-  name_index_other = indices_other[0]
-  distance_name_other = str(distances_other[0])
-  topic_name_other = []
-  for index_o in name_index_other:
-    topic_name_other.append(other_industries['other_industries_name_clean'].tolist()[index_o])
-  topic_name_other = str(topic_name_other)
+      industries = pd.read_excel('sect_other.xlsx', sheet_name = 'other_indus')
+      industries['industries_name_clean'] = industries['name'].str.replace('&','').str.strip()
+      industries['industries_name_clean'] = industries['industries_name_clean'].str.replace('IT','information technology').str.replace(',','').str.lower()
+    
+      other_industries = pd.read_csv('other_industries.csv')
+      other_industries['other_industries_name_clean'] = other_industries['Industry'].str.replace('-',' ').str.replace('/',' ').str.replace('(',' ').str.replace(')',' ').replace('&',' ').str.strip().str.lower()
+      
+      n_neighbors = 1
+      threshold = 0.40
+    
+      #sectors
+      distances, indices = sector_model.kneighbors([event_embedd], n_neighbors=2)
+      name_index = indices[0]
+      distance_name = str(distances[0])
+      topic_name = []
+      for index_i in name_index:
+        topic_name.append(sectors['name_clean'].tolist()[index_i])
+      topic_name = str(topic_name)
+    
+    
+      #industries
+      distances_indus, indices_indus = indus_model.kneighbors([event_embedd], n_neighbors=n_neighbors)
+      name_index_indus = indices_indus[0][0]
+      distance_name_indus = distances_indus[0][0]
+      topic_name_indus = industries['industries_name_clean'].tolist()[name_index_indus]
+    
+      #other_industries
+      distances_other, indices_other = other_indus_model.kneighbors([event_embedd], n_neighbors=3)
+      name_index_other = indices_other[0]
+      distance_name_other = str(distances_other[0])
+      topic_name_other = []
+      for index_o in name_index_other:
+        topic_name_other.append(other_industries['other_industries_name_clean'].tolist()[index_o])
+      topic_name_other = str(topic_name_other)
+    
+      return topic_name, distance_name, topic_name_indus, distance_name_indus,topic_name_other,distance_name_other
 
-  return topic_name, distance_name, topic_name_indus, distance_name_indus,topic_name_other,distance_name_other
+  else:
+      return 'no tags identified', None, None, None,None,None