import nltk
nltk.download('stopwords')
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

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

#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)

with st.spinner('Loading Epidemiology Models and Dependencies...'):
    classify_model_vars = classify_abs.init_classify_model()
    st.success('Epidemiology Classification Model Loaded!')
    NER_pipeline, entity_classes = extract_abs.init_NER_pipeline()
    st.success('Epidemiology Extraction Model Loaded!')
    GARD_dict, max_length = extract_abs.load_GARD_diseases()
st.success('All Models and Dependencies Loaded!')

GARD_Disease_Id = st.text_input("Input a rare disease term or GARD ID.", value="Fellman syndrome")

if text:
  df = extract_abs.search_term_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")