app.py

import streamlit as st
import torch
import spacy
# from spacy.lang.en import English
# from utils import spacy_function, make_predictions, example_input

from Dataset import CustomDataSetManager
from Embeddings import get_embeddings
from Model import MachineModel
from Tokenizer import Tokenizer
from LabelEncoder import LabelEncoder
from MakePredictions import make_predictions
from RandomAbstract import Choose_Random_text

MODEL_PATH = 'final_model.pt'
TOKENIZER_PATH = 'tokenizer.json'
LABEL_ENOCDER_PATH = "label_encoder.json"
EMBEDDING_FILE_PATH = 'glove.6B.300d.txt'

@st.cache()
def create_utils(model_path, tokenizer_path, label_encoder_path, embedding_file_path):
    tokenizer = Tokenizer.load(fp=tokenizer_path)
    label_encoder = LabelEncoder.load(fp=label_encoder_path)
    embedding_matrix = get_embeddings(embedding_file_path, tokenizer, 300)
    model = MachineModel(embedding_dim=300, vocab_size=len(tokenizer), hidden_dim=128, n_layers=3, linear_output=128, num_classes=len(label_encoder), pretrained_embeddings=embedding_matrix)
    model.load_state_dict(torch.load(model_path, map_location='cpu'))
    print(model)
    return model, tokenizer, label_encoder

def model_prediction(abstract, model, tokenizer, label_encoder):
    objective = ''
    background = ''
    method = ''
    conclusion = ''
    result = ''

    lines, pred = make_predictions(abstract, model, tokenizer, label_encoder)
    # pred, lines = make_predictions(abstract)

    for i, line in enumerate(lines):
        if pred[i] == 'OBJECTIVE':
            objective = objective + line
        
        elif pred[i] == 'BACKGROUND':
            background = background + line
        
        elif pred[i] == 'METHODS':
            method = method + line
        
        elif pred[i] == 'RESULTS':
            result = result + line
        
        elif pred[i] == 'CONCLUSIONS':
            conclusion = conclusion + line

    return objective, background, method, conclusion, result



def main():
    
    st.set_page_config(
        page_title="Using BERT Models for Sequential Text Classification in Biomedical Abstracts",
        page_icon="📄",
        layout="wide",
        initial_sidebar_state="expanded"
    )

    st.title('Using BERT Models for Sequential Text Classification in Biomedical Abstracts 📄 🔥')
    st.caption('A custom NLP classification model based on a transformer that is able to classify and simplify research abstracts and then classify it into smaller parts that can be made more simple and easy to understand')
    st.caption('Developed by Purbayan Majumder, Aman Khan and Rubina Das')
    # creating model, tokenizer and labelEncoder
    
    col1, col2 = st.columns(2)

    with col1:
        st.write('#### Enter Abstract Here !!')
        abstract = st.text_area(label='', height=200)

        agree = st.checkbox('Show Example Abstract')
        predict = st.button('Extract !')
        
        if agree:
            example_input = Choose_Random_text()
            st.info(example_input)
    
    # make prediction button logic
    if predict:
        with col2:
            with st.spinner('Waiting for prediction processing data to the utils....'):
                fetch_model, tokenizer, label_encoder = create_utils(MODEL_PATH, TOKENIZER_PATH, LABEL_ENOCDER_PATH, EMBEDDING_FILE_PATH)
                objective, background, methods, conclusion, result = model_prediction(abstract, fetch_model, tokenizer, label_encoder)

                st.markdown(f'### Objective : ')
                st.info(objective)
                # st.write(f'{objective}')
                st.markdown(f'### Background : ')
                st.info(background)
                # st.write(f'{background}')
                st.markdown(f'### Methods : ')
                st.info(methods)
                # st.write(f'{methods}')
                st.markdown(f'### Result : ')
                st.info(result)
                # st.write(f'{result}')
                st.markdown(f'### Conclusion : ')
                st.info(conclusion)
                # st.write(f'{conclusion}')



if __name__=='__main__': 
    main()