score_fincat.py

import gradio as gr
import nltk
from fincat_utils import extract_context_words
from fincat_utils import bert_embedding_extract
import pickle
lr_clf = pickle.load(open("lr_clf_FiNCAT.pickle",'rb'))
nltk.download('punkt')

def score_fincat(txt):
  li = []
  highlight = []
  txt = " " + txt + " "
  k = ''
  for word in txt.split():
    if any(char.isdigit() for char in word):
      if word[-1] in ['.', ',', ';', ":", "-", "!", "?", ")", '"', "'"]:
        k = word[-1]
        word = word[:-1]
      st = txt.find(" " + word + k + " ")+1
      k = ''
      ed = st + len(word)
      x = {'paragraph' : txt, 'offset_start':st, 'offset_end':ed}
      context_text = extract_context_words(x)
      features = bert_embedding_extract(context_text, word)
      if(features[0]=='None'):
          highlight.append((txt, '    '))
          return highlight
      prediction = lr_clf.predict(features.reshape(1, 768))
      prediction_probability = '{:.4f}'.format(round(lr_clf.predict_proba(features.reshape(1, 768))[:,1][0], 4))
      highlight.append((word, '    In-claim' if prediction==1 else 'Out-of-Claim'))
    else:
      highlight.append((word, '    '))
  return highlight