app.py

import time
import streamlit as st
import torch
import string

bert_tokenizer = None
bert_model = None

from transformers import BertTokenizer, BertForMaskedLM

st.set_page_config(page_title='Qualitative pretrained model eveluation', page_icon=None, layout='centered', initial_sidebar_state='auto')

@st.cache()
def load_bert_model(model_name):
  try:
    bert_tokenizer = BertTokenizer.from_pretrained(model_name,do_lower_case
    =False)
    bert_model = BertForMaskedLM.from_pretrained(model_name).eval()
    return bert_tokenizer,bert_model
  except Exception as e:
    pass



  
def decode(tokenizer, pred_idx, top_clean):
  ignore_tokens = string.punctuation
  tokens = []
  for w in pred_idx:
    token = ''.join(tokenizer.decode(w).split())
    if token not in ignore_tokens and len(token) > 1 and not token.startswith('.') and not token.startswith('['):
      #tokens.append(token.replace('##', ''))
      tokens.append(token)
  return '\n'.join(tokens[:top_clean])

def encode(tokenizer, text_sentence, add_special_tokens=True):
  text_sentence = text_sentence.replace('<mask>', tokenizer.mask_token)
    # if <mask> is the last token, append a "." so that models dont predict punctuation.
  #if tokenizer.mask_token == text_sentence.split()[-1]:
  #  text_sentence += ' .'

  tokenized_text = bert_tokenizer.tokenize(text_sentence) 
  input_ids = torch.tensor([tokenizer.encode(text_sentence, add_special_tokens=add_special_tokens)])
  if (tokenizer.mask_token in text_sentence.split()):
    mask_idx = torch.where(input_ids == tokenizer.mask_token_id)[1].tolist()[0]
  else:
    mask_idx = 0
  return input_ids, mask_idx,tokenized_text

def get_all_predictions(text_sentence, model_name,top_clean=5):
    # ========================= BERT =================================
  input_ids, mask_idx,tokenized_text = encode(bert_tokenizer, text_sentence)
   
  with torch.no_grad():
    predict = bert_model(input_ids)[0]
  bert = decode(bert_tokenizer, predict[0, mask_idx, :].topk(top_k*5).indices.tolist(), top_clean)
  cls = decode(bert_tokenizer, predict[0, 0, :].topk(top_k*5).indices.tolist(), top_clean)
  
  if ("[MASK]" in text_sentence or "<mask>" in text_sentence):
    return {'Input sentence':text_sentence,'Tokenized text': tokenized_text,'Model':model_name,'Masked position': bert,'[CLS]':cls}
  else:
    return {'Input sentence':text_sentence,'Tokenized text': tokenized_text,'Model':model_name,'[CLS]':cls}

def get_bert_prediction(input_text,top_k,model_name):
  try:
    #input_text += ' <mask>'
    res = get_all_predictions(input_text,model_name, top_clean=int(top_k))
    return res
  except Exception as error:
    pass
    
 
def run_test(sent,top_k,model_name):
  start = None
  global bert_tokenizer
  global bert_model
  if (bert_tokenizer is None):
        bert_tokenizer, bert_model  = load_bert_model(model_name)
  with st.spinner("Computing"):
          start = time.time()
          try:
            res = get_bert_prediction(sent,top_k,model_name)
            st.caption("Results in JSON")
            st.json(res)
            
          except Exception as e:
            st.error("Some error occurred during prediction" + str(e))
            st.stop()
  if start is not None:
    st.text(f"prediction took {time.time() - start:.2f}s")
  
def init_selectbox():
  option = st.selectbox(
     'Choose any of these sentences or type any text below',
      ('', "[MASK] who lives in New York and works for XCorp suffers from Parkinson's", "Lou Gehrig who lives in [MASK] and works for XCorp suffers from Parkinson's","'Lou Gehrig who lives in New York and         works for [MASK] suffers from Parkinson's'","'Lou Gehrig who lives in New York and works for XCorp suffers from [MASK]'","[MASK] who lives in New York and works for XCorp suffers from Lou Gehrig's",            "Parkinson who lives in [MASK] and works for XCorp suffers from Lou Gehrig's","Parkinson who lives in New York and works for [MASK] suffers from Lou Gehrig's","Parkinson who lives in New York and works for     XCorp suffers from [MASK]","Lou Gehrig","Parkinson","Lou Gehrigh's is a [MASK]","Parkinson is a [MASK]","New York is a [MASK]","New York","XCorp","XCorp is a [MASK]","acute lymphoblastic leukemia","acute       lymphoblastic leukemia is a [MASK]"))  
  return option

st.markdown("<h3 style='text-align: center;'>Qualitative evaluation of  any pretrained BERT model</h3>", unsafe_allow_html=True)
st.markdown("""
        <small style="font-size:18px; color: #7f7f7f">Pretrained BERT models can be used as is, <a href="https://ajitrajasekharan.github.io/2021/01/02/my-first-post.html"><b>with no fine tuning to perform tasks like NER</b></a> <i>ideally if both fill-mask and CLS predictions are good, or minimally if fill-mask predictions are adequate</i></small>
        """, unsafe_allow_html=True)
  #st.write("https://ajitrajasekharan.github.io/2021/01/02/my-first-post.html")
st.write("This app can be used to examine both model prediction for a masked  position as well as the neighborhood of CLS vector")
st.write("   - To examine model prediction for a position, enter the token [MASK] or <mask>")
st.write("   - To examine just the [CLS] vector, enter a word/phrase or sentence. Example: eGFR or EGFR or non small cell lung cancer")
top_k = st.sidebar.slider("Select how many predictions do you need", 1 , 50, 20) #some times it is possible to have less words
print(top_k)


  

  #if st.button("Submit"):
    
  #  with st.spinner("Computing"):
try:
            
      model_name = st.sidebar.selectbox(label='Select Model to Apply',  options=['ajitrajasekharan/biomedical', 'bert-base-cased','bert-large-cased','microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext','allenai/scibert_scivocab_cased','dmis-lab/biobert-v1.1'], index=0,  key = "model_name")
      option = init_selectbox()
      input_text = st.text_input("Enter text below", "")
      custom_model_name = st.text_input("Model not listed on left? Type the model name (fill-mask BERT models only)", "")
      if (len(custom_model_name) > 0):
        model_name = custom_model_name
        st.info("Custom model selected: " + model_name)
        bert_tokenizer, bert_model  = load_bert_model(model_name)
      if len(option) > 0:
        run_test(option,top_k,model_name)
        option = ""
      else:
        if len(input_text) > 0:
          run_test(input_text,top_k,model_name)
      if (bert_tokenizer is None):
        bert_tokenizer, bert_model  = load_bert_model(model_name)
      

except Exception as e:
  st.error("Some error occurred during loading" + str(e))
  st.stop()  
	
st.write("---")