import pickle
import pandas as pd
from sentence_transformers import SentenceTransformer, util
from preprocess_function import preprocess_text
from topics_extraction import classify

model_sent = SentenceTransformer("all-mpnet-base-v2")

sector_model = pickle.load(open('sector_knn.sav', 'rb'))
indus_model = pickle.load(open('indus_knn.sav', 'rb'))

def get_mapping(prep_text):
    
  tags_list = classify(prep_text)
  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_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()

      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]
    
    
      return topic_name, distance_name, topic_name_indus, distance_name_indus,tags_list

  else:
      return 'no tags identified', None, None, None,tags_list