app.py

# -*- coding: utf-8 -*-
"""
Created on Tue Nov 22 09:54:41 2022

@author: luol2
"""



import streamlit as st
import argparse
from src.nn_model import bioTag_CNN,bioTag_BERT,bioTag_Bioformer
from src.dic_ner import dic_ont
from src.tagging_text import bioTag
import os
import time
import json
import sys
import nltk 
nltk.download('punkt')
nltk.download('averaged_perceptron_tagger')
nltk.download('wordnet')

st.set_page_config(
    page_title="PhenoTagger",
    page_icon=":shark:",
    #  layout="wide",
    initial_sidebar_state="expanded",
    menu_items={
        'Get Help': 'https://www.extremelycoolapp.com/help',
        'Report a bug': "https://www.extremelycoolapp.com/bug",
        'About': "# This is a header. This is an *extremely* cool app!"
    }
)
st.title('PhenoTagger Demo')




    


# with st.spinner('Model is being loaded..'):
  
#   print('load model done!')
 


    
with st.form(key="my_form"):
        
    @st.cache(allow_output_mutation=True)
    def load_model():
        ontfiles={'dic_file':'./dict_new/noabb_lemma.dic',
                  'word_hpo_file':'./dict_new/word_id_map.json',
                  'hpo_word_file':'./dict_new/id_word_map.json'}
        
        # if para_set['model_type']=='cnn':
        #     vocabfiles={'w2vfile':'../vocab/bio_embedding_intrinsic.d200',   
        #                 'charfile':'../vocab/char.vocab',
        #                 'labelfile':'../dict_new/lable.vocab',
        #                 'posfile':'../vocab/pos.vocab'}
        #     modelfile='../models/cnn_p5n5_b128_95_hponew1.h5'
        
        # elif para_set['model_type']=='bioformer':
        vocabfiles={'labelfile':'./dict_new/lable.vocab',
                    'config_path':'./vocab/bioformer-cased-v1.0/bert_config.json',
                    'checkpoint_path':'./vocab/bioformer-cased-v1.0/bioformer-cased-v1.0-model.ckpt-2000000',
                    'vocab_path':'./vocab/bioformer-cased-v1.0/vocab.txt'}
        modelfile='./vocab/bioformer_p5n5_b64_1e-5_95_hponew3.h5'
        # else:
        #     print('Model type is wrong, please select cnn or bioformer.')
        #     sys.exit()
        
    
        biotag_dic=dic_ont(ontfiles)    
    
        # if para_set['model_type']=='cnn':
        #     nn_model=bioTag_CNN(vocabfiles)
        #     nn_model.load_model(modelfile)
        # elif para_set['model_type']=='bioformer':
        nn_model=bioTag_Bioformer(vocabfiles)
        session=nn_model.load_model(modelfile)
        test_tag='1232'
        return nn_model,biotag_dic,test_tag,session


    #hyper-parameter
    st.sidebar.header("Hyperparameter Settings")
    sbform = st.sidebar.form("Hyper-paramiters")
    # para_model=sbform.selectbox('Model', ['cnn', 'bioformer'])
    para_overlap=sbform.selectbox('Return overlapping concepts', ['True', 'False'])
    para_abbr=sbform.selectbox('Identify abbreviations', ['True', 'False'])
    para_threshold = sbform.slider('Threshold:', min_value=0.5, max_value=0.95, value=0.95, step=0.05)
    sbform.form_submit_button("Setting")
    
    st.write('parameters:', para_overlap,para_abbr,para_threshold)
    nn_model,biotag_dic,test_tag,session=load_model()
    
    
    input_text = st.text_area(
        "Paste your text below (max 500 words)",
        height=510,
    )

    MAX_WORDS = 500
    import re
    res = len(re.findall(r"\w+", input_text))
    if res > MAX_WORDS:
        st.warning(
            "⚠️ Your text contains "
            + str(res)
            + " words."
            + " Only the first 500 words will be reviewed. Stay tuned as increased allowance is coming! 😊"
        )

        input_text = input_text[:MAX_WORDS]

    submit_button = st.form_submit_button(label="✨ Get me the data!")
    
    if para_overlap=='True':
        para_overlap=True
    else:
        para_overlap=False
    if para_abbr=='True':
        para_abbr=True
    else:
        para_abbr=False
    para_set={
              #model_type':para_model, # cnn or bioformer
              'onlyLongest':para_overlap, # False: return overlap concepts, True only longgest
              'abbrRecog':para_abbr,# False: don't identify abbr, True: identify abbr
              'ML_Threshold':para_threshold,# the Threshold of deep learning model
              }
    
    

if not submit_button:
    st.stop()
        

st.markdown(f"""**Results:**\n""")
# print('dic...........:',biotag_dic.keys())
print('........:',test_tag)
print('........!!!!!!:',input_text)
print('...input:',input_text)
tag_result=bioTag(session,input_text,biotag_dic,nn_model,onlyLongest=para_set['onlyLongest'], abbrRecog=para_set['abbrRecog'],Threshold=para_set['ML_Threshold'])
for ele in tag_result:
    start = ele[0]
    last = ele[1]
    mention = input_text[int(ele[0]):int(ele[1])]
    type='Phenotype'
    id=ele[2]
    score=ele[3]
    output=start+"\t"+last+"\t"+mention+"\t"+id+'\t'+score+"\n"
    st.info(output)