app.py

import nltk
import ntlk_utils #nltk are download in different file
from nltk.corpus import wordnet as wn
from nltk.tokenize import sent_tokenize
from nltk.corpus import stopwords
from time import sleep

from flashtext import KeywordProcessor
from pprint import pprint
import random
import pke
import traceback

import json
import requests
import string
import re
import string
import itertools

import streamlit as st
from transformers import T5ForConditionalGeneration,T5Tokenizer

from transformers import pipeline

import torch
import random
import numpy as np

def set_seed(seed: int):
    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
    torch.cuda.manual_seed_all(seed)

set_seed(42)

summary_model = T5ForConditionalGeneration.from_pretrained('t5-base')
summary_tokenizer = T5Tokenizer.from_pretrained('t5-base')

question_model = T5ForConditionalGeneration.from_pretrained('ramsrigouthamg/t5_squad_v1')
question_tokenizer = T5Tokenizer.from_pretrained('ramsrigouthamg/t5_squad_v1')

#summarizer = pipeline("summarization", model="facebook/bart-large-cnn")



st.header(" Question Creation ")
st.subheader(" Enter the text and click on generate question. Questions will be created automatically.")
text = st.text_area("Input the text to get questions",placeholder="Enter the text", height=200)
button = st.button("Generate Question")

def postprocesstext (content):
  final=""
  for sent in sent_tokenize(content):
    sent = sent.capitalize()
    final = final +" "+sent
  return final


def summarizer(text,model,tokenizer):
  text = text.strip().replace("\n"," ")
  text = "summarize: "+text
  print (text)
  max_len = 512
  encoding = tokenizer.encode_plus(text,max_length=max_len, pad_to_max_length=False,truncation=True, return_tensors="pt").to(device)

  input_ids, attention_mask = encoding["input_ids"], encoding["attention_mask"]

  outs = model.generate(input_ids=input_ids,
                                  attention_mask=attention_mask,
                                  early_stopping=True,
                                  num_beams=3,
                                  num_return_sequences=1,
                                  no_repeat_ngram_size=2,
                                  min_length = 75,
                                  max_length=300)


  dec = [tokenizer.decode(ids,skip_special_tokens=True) for ids in outs]
  summary = dec[0]
  summary = postprocesstext(summary)
  summary= summary.strip()
  print( "done from summarizer")
  return summary


def get_nouns_multipartite(content):
    out=[]
    try:
        extractor = pke.unsupervised.MultipartiteRank()
        extractor.load_document(input=content,language='en')
        #    not contain punctuation marks or stopwords as candidates.
        pos = {'PROPN','NOUN'}
        #pos = {'PROPN','NOUN'}
        stoplist = list(string.punctuation)
        stoplist += ['-lrb-', '-rrb-', '-lcb-', '-rcb-', '-lsb-', '-rsb-']
        stoplist += stopwords.words('english')
        # extractor.candidate_selection(pos=pos, stoplist=stoplist)
        extractor.candidate_selection(pos=pos)
        # 4. build the Multipartite graph and rank candidates using random walk,
        #    alpha controls the weight adjustment mechanism, see TopicRank for
        #    threshold/method parameters.
        extractor.candidate_weighting(alpha=1.1,
                                      threshold=0.75,
                                      method='average')
        keyphrases = extractor.get_n_best(n=15)
        

        for val in keyphrases:
            out.append(val[0])
    except:
        out = []
        traceback.print_exc()

    return out

def get_keywords(originaltext,summarytext):
  keywords = get_nouns_multipartite(originaltext)
  print ("keywords unsummarized: ",keywords)
  keyword_processor = KeywordProcessor()
  for keyword in keywords:
    keyword_processor.add_keyword(keyword)

  keywords_found = keyword_processor.extract_keywords(summarytext)
  keywords_found = list(set(keywords_found))
  print ("keywords_found in summarized: ",keywords_found)

  important_keywords =[]
  for keyword in keywords:
    if keyword in keywords_found:
      important_keywords.append(keyword)

  return important_keywords[:4]

def get_question(context,answer,model,tokenizer):
  text = "context: {} answer: {}".format(context,answer)
  encoding = tokenizer.encode_plus(text,max_length=384, pad_to_max_length=False,truncation=True, return_tensors="pt").to(device)
  input_ids, attention_mask = encoding["input_ids"], encoding["attention_mask"]

  outs = model.generate(input_ids=input_ids,
                                  attention_mask=attention_mask,
                                  early_stopping=True,
                                  num_beams=5,
                                  num_return_sequences=1,
                                  no_repeat_ngram_size=2,
                                  max_length=72)


  dec = [tokenizer.decode(ids,skip_special_tokens=True) for ids in outs]


  Question = dec[0].replace("question:","")
  Question= Question.strip()
  return Question


if text and button:
    # summarized_text = summarizer(text,summary_model,summary_tokenizer)
    summarized_text = summarizer(text,summary_model,summary_tokenizer)
    puts ("stopping pankaj")
    sleep(0.5)
    puts("summry",summarized_text)
    #summarized_text = summarizer(text, max_length=130, min_length=30, do_sample=False)
    # summarized_text = "Musk tweeted that his electric vehicle-making company tesla will not accept payments in bitcoin because of environmental concerns. He also said that the company was working with developers of dogecoin to improve system transaction efficiency. The world's largest cryptocurrency hit a two-month low, while doge coin rallied by about 20 percent. Musk has in recent months often tweeted in support of crypto, but rarely for bitcoin."
    imp_keywords = get_keywords(text,summarized_text)
    for answer in imp_keywords:
        ques = get_question(summarized_text,answer,question_model,question_tokenizer)
        st.write(ques)
        st.write(answer.capitalize())
        st.write("\n")