app.py

import streamlit as st
from textwrap3 import wrap
from flashtext import KeywordProcessor
import torch, random, nltk, string, traceback, sys, requests, datetime, os
import numpy as np
import pandas as pd
from transformers import T5ForConditionalGeneration,T5Tokenizer
import pke
from helper import postprocesstext, summarizer, get_nouns_multipartite, get_keywords,\
    get_question, get_related_word, get_final_option_list, load_raw_text


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)

@st.cache(allow_output_mutation = True)
def load_model():
    nltk.download('punkt')
    nltk.download('brown')
    nltk.download('wordnet')
    nltk.download('stopwords')
    nltk.download('wordnet')
    nltk.download('omw-1.4')
    summary_mod_name = os.environ["summary_mod_name"]
    question_mod_name = os.environ["question_mod_name"]
    summary_model = T5ForConditionalGeneration.from_pretrained(summary_mod_name)
    summary_tokenizer = T5Tokenizer.from_pretrained(summary_mod_name)
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    summary_model = summary_model.to(device)
    question_model = T5ForConditionalGeneration.from_pretrained(question_mod_name)
    question_tokenizer = T5Tokenizer.from_pretrained(question_mod_name)
    question_model = question_model.to(device)
    return summary_model, summary_tokenizer, question_tokenizer, question_model 

from nltk.corpus import wordnet as wn
from nltk.tokenize import sent_tokenize
from nltk.corpus import stopwords

def csv_downloader(df):
    res = df.to_csv(index=False,sep="\t").encode('utf-8')
    st.download_button(
    label="Download logs data as CSV separated by tab",
    data=res,
    file_name='df_quiz_log_file_v1.csv',
    mime='text/csv')

def load_file():
    """Load text from file"""
    uploaded_file = st.file_uploader("Upload Files",type=['txt'])
    if uploaded_file is not None:
        if uploaded_file.type == "text/plain":
            raw_text = str(uploaded_file.read(),"utf-8")
        return raw_text


# Loading Model
summary_model, summary_tokenizer, question_tokenizer, question_model = load_model()

# App title and description
st.title("MCQ generator")
st.write("Insert any long text, and then you will got some MCQ with answers")

# Load file

default_text = load_raw_text()
raw_text = st.text_area("Enter text here", default_text, height=250, max_chars=1000000, )

# raw_text = load_file()
start_time = str(datetime.datetime.now())
if raw_text != None and raw_text != '':
    summary_text = summarizer(raw_text,summary_model,summary_tokenizer)
    ans_list =  get_keywords(raw_text,summary_text)
    #print("Ans list: {}".format(ans_list))
    questions = []
    option1=[]
    option2=[]
    option3=[]
    option4=[]
    for idx,ans in enumerate(ans_list):
        #print("IDX: {}, ANS: {}".format(idx, ans))
        ques = get_question(summary_text,ans,question_model,question_tokenizer)
        other_options = get_related_word(ans)
        final_options, ans_index = get_final_option_list(ans,other_options)
        option1.append(final_options[0])
        option2.append(final_options[1])
        option3.append(final_options[2])
        option4.append(final_options[3])                   
        if ques not in questions:
            html_str = f"""
            <div>
            <p>
            {idx+1}: <b> {ques} </b>
            </p>
            </div>
            """
            html_str += f' <p style="color:Green;"><b> {final_options[0]} </b></p> ' if ans_index == 0 else f' <p><b> {final_options[0]} </b></p> '
            html_str += f' <p style="color:Green;"><b> {final_options[1]} </b></p> ' if ans_index == 1 else f' <p><b> {final_options[1]} </b></p> '
            html_str += f' <p style="color:Green;"><b> {final_options[2]} </b></p> ' if ans_index == 2 else f' <p><b> {final_options[2]} </b></p> '
            html_str += f' <p style="color:Green;"><b> {final_options[3]} </b></p> ' if ans_index == 3 else f' <p><b> {final_options[3]} </b></p> '
            html_str += f"""
            """
            st.markdown(html_str , unsafe_allow_html=True)
            st.markdown("-----")
        questions.append(ques)
    output_path = "results/df_quiz_log_file_v1.csv"
    res_df = pd.DataFrame({"TimeStamp":[start_time]*len(ans_list),\
        "Input":[str(raw_text)]*len(ans_list),\
        "Question":questions,"Option1":option1,\
        "Option2":option2,\
        "Option3":option3,\
        "Option4":option4,\
        "Correct Answer":ans_list})
    res_df.to_csv(output_path, mode='a', index=False, sep="\t", header= not os.path.exists(output_path))
    # st.dataframe(pd.read_csv(output_path,sep="\t").tail(5))
    csv_downloader(pd.read_csv(output_path,sep="\t"))