app.py

import nltk
nltk.download('stopwords')
nltk.download('punkt')
import pandas as pd
#classify_abs is a dependency for extract_abs
import classify_abs
import extract_abs
#pd.set_option('display.max_colwidth', None)
import streamlit as st
import spacy
import tensorflow as tf
import pickle

########## Title for the Web App ##########
st.title("Epidemiology Extraction Pipeline for Rare Diseases")
st.subheader("National Center for Advancing Translational Sciences (NIH/NCATS)") 


#### CHANGE SIDEBAR WIDTH ###
st.markdown(
    """
    <style>
    [data-testid="stSidebar"][aria-expanded="true"] > div:first-child {
        width: 275px;
    }
    [data-testid="stSidebar"][aria-expanded="false"] > div:first-child {
        width: 275px;
        margin-left: -400px;
    }
    </style>
    """,
    unsafe_allow_html=True,
)

#max_results is Maximum number of PubMed ID's to retrieve BEFORE filtering
max_results = st.sidebar.number_input("Maximum number of articles to find in PubMed", min_value=1, max_value=None, value=50)

filtering = st.sidebar.radio("What type of filtering would you like?",('Strict', 'Lenient', 'None'))

extract_diseases = st.sidebar.checkbox("Extract Rare Diseases", value=False)

@st.cache(allow_output_mutation=True)
def load_models():
    # load the tokenizer
    with open('tokenizer.pickle', 'rb') as handle:
        classify_tokenizer = pickle.load(handle)
    
    # load the model
    classify_model = tf.keras.models.load_model("LSTM_RNN_Model") 
    
    #classify_model_vars = classify_abs.init_classify_model()
    NER_pipeline, entity_classes = extract_abs.init_NER_pipeline()
    GARD_dict, max_length = extract_abs.load_GARD_diseases()
    return classify_tokenizer, classify_model, NER_pipeline, entity_classes, GARD_dict, max_length
    
with st.spinner('Loading Epidemiology Models and Dependencies...'):
    classify_tokenizer, classify_model, NER_pipeline, entity_classes, GARD_dict, max_length = load_models()
    #Load spaCy models which cannot be cached due to hash function error
    nlp = spacy.load('en_core_web_lg')
    nlpSci = spacy.load("en_ner_bc5cdr_md")
    nlpSci2 = spacy.load('en_ner_bionlp13cg_md')
    classify_model_vars = (nlp, nlpSci, nlpSci2, classify_model, classify_tokenizer)
st.success('All Models and Dependencies Loaded!')

disease_or_gard_id = st.text_input("Input a rare disease term or GARD ID.")

if disease_or_gard_id:
  df = extract_abs.streamlit_extraction(disease_or_gard_id, max_results, filtering,
                                        NER_pipeline, entity_classes, 
                                        extract_diseases,GARD_dict, max_length, 
                                        classify_model_vars)
  st.dataframe(df)
  st.balloons()
  #st.dataframe(data=None, width=None, height=None)
  
# st.code(body, language="python")