doczyai-pipelines/streamlit/interface_1.py

import streamlit as st
from streamlit_extras.add_vertical_space import add_vertical_space
import os
import streamlit as st
import pandas as pd
from io import StringIO
from datetime import datetime
import boto3
import util
import requests

doczy_pipeline = 'https://8ir4vi1ri4.execute-api.us-east-2.amazonaws.com/dev/'

REDIRECT_URI = 'https://doczy.aarete.com:8501'
user_list = ['maamseek@aarete.com', 'smahdavian@aarete.com', 'ahinge@aarete.com', 'akadam@aarete.com'
, 'piragavarapu@aarete.com', 'umistry@aarete.com', 'pkatariya@aarete.com', 'kminhas@aarete.com', 'fmohiuddin@aarete.com']
st.set_page_config(layout = "wide")
# # Sidebar contents
# with st.sidebar:
#     st.title("Doczy.AI ™")
#     st.markdown(
#         """
#     ## About
#     This app extracts data from contracts
 
#     """
#     )
#     add_vertical_space(15)
#     # st.write("Doczy")

_,c1= st.columns([5,1])
try:
    putil.setup_page(REDIRECT_URI)
except:
    st.session_state['user_info'] = {'mail': 'maamseek@aarete.com', 'displayName': 'Mayank Aamseek'}
c1.write(f"User: **{st.session_state.user_info['displayName']}**")
user_mail = st.session_state.user_info['mail']

if user_mail in user_list: 

    s3_client = boto3.client('s3',
        region_name="us-east-1",
    )

    # to be replaced with snowflake data
    client_list = ['doczy-ai-client-1', 'Delaware First Health, Inc.', 'Community Health Choice, Inc','CareSource Network Partners LLC',
        'HealthNet of Cali', 'Oklahoma Complete Health, Inc', 'HealthFirst', 'Molina Healthcare of TX', 'AvMed', 'Arizona Care1st',
        'WellCare New Jersey']

    client_row = st.columns([0.1, 0.8])
    with client_row[0]:
        st.write("**Client Name**")
    with client_row[1]:
        client = st.selectbox('Client Name',(client_list), label_visibility = "collapsed")

    batch_objects = s3_client.list_objects_v2(Bucket=client
        , Prefix="", Delimiter='/')      

    batch_list = []
    for prefix in batch_objects['CommonPrefixes']:
        batch_list.append(prefix['Prefix'][:-1].split('/')[-1])

    path_row = st.columns([0.1, 0.8])
    with path_row[0]:
        st.write("**Batch ID**")
    with path_row[1]:
        batch_id = st.selectbox('**Batch ID**', batch_list, label_visibility = "collapsed")

    checks = st.columns([0.1, 0.12, 0.12, 0.12, 0.12, 0.12, 0.12, 0.12])
    with checks[0]:
        st.write("**Group No.**")
    with checks[1]:
        a = st.checkbox('Unique Key', key = str(1))
    with checks[2]:
        b = st.checkbox('Pricing Before Carveouts', key = str(2))
    with checks[3]:
        c = st.checkbox('Contract Related', key = str(3))
    with checks[4]:
        d = st.checkbox('Provider', key = str(4))
    with checks[5]:
        e = st.checkbox('Timeline', key = str(5))
    with checks[6]:
        f = st.checkbox('Carveout Indicator', key = str(6))
    with checks[7]:
        g = st.checkbox('Carveout Methodology', key = str(7))

    add_vertical_space(1)

    df = pd.DataFrame(columns=['Contract Name','Unique Key','Pricing Before Carveouts'
        , 'Contract Related', 'Provider', 'Timeline', 'Carveout Indicator', 'Carveout Methodology'])
    file_list = []
    file_objects = s3_client.list_objects_v2(Bucket=client
        , Prefix=batch_id+"/contracts_landing_zone/", Delimiter='/')

    if st.button("Read the contracts from Path"):
        for obj in file_objects.get('Contents',[]):
            if not obj['Key'].endswith('/'):
                file_list.append(obj['Key'].split('/')[-1])

        df['Contract Name'] = file_list
        # df['Request ID'] = range(len(file_list))
        # df['Contract ID'] = file_list
        df['Unique Key'] = a
        df['Pricing Before Carveouts'] = b
        df['Contract Related'] = c
        df['Provider'] = d
        df['Timeline'] = e
        df['Carveout Indicator'] = f
        df['Carveout Methodology'] = g
        dir_path = os.path.dirname(os.path.realpath(__file__))
        print(f'DEBUGGING: PWD= {dir_path}')
        df.to_csv('temp1.csv', index=False)

    add_vertical_space(1)
    df2 = pd.read_csv('temp1.csv')
    edited_df = st.data_editor(df2)

    @st.cache_data 
    def convert_df(df):
       return df.to_csv(index=False).encode('utf-8')

    csv = convert_df(edited_df)
    edited_df = edited_df.reset_index()  # make sure indexes pair with number of rows

    # additional_info = pd.DataFrame(columns=['REQUEST_ID','T_DRIVE_PATH','CLIENT_NAME'
    # , 'GROUP_NAME', 'REQUEST_USERNAME', 'REQUEST_DATETIME'])
    additional_info = pd.DataFrame(columns=['CLIENT_NAME', 'BATCH_ID', 'REQUEST_USERNAME', 'REQUEST_DATETIME'])
    additional_info.loc[0] = [client, batch_id, st.session_state.user_info['mail'], datetime.now().strftime("%Y-%m-%d %H:%M:%S")]
    st.write(additional_info)

    # contract_list = []
    # for index, row in edited_df.iterrows():
    #     group_list = []
    #     if row['Unique Key']:
    #         group_list.append('Unique Key')
    #     if row['Pricing Before Carveouts']:
    #         group_list.append('Pricing Before Carveouts')
    #     if row['Contract Related']:
    #         group_list.append('Contract Related')
    #     if row['Provider']:
    #         group_list.append('Provider')
    #     if row['Timeline']:
    #         group_list.append('Timeline')
    #     if row['Carveout Indicator']:
    #         group_list.append('Carveout Indicator')
    #     if row['Carveout Methodology']:
    #         group_list.append('Carveout Methodology')
    #     entry_dict = {
    #         "contract_name": row['Contract Name'],
    #         "groups": group_list,
    #         "contract_source_path": "batches/batch_1/"+client+"/"+row['Contract Name']
    #     }
    #     contract_list.append(entry_dict)

    # myobj = {
    #   "s3_bucket": 'doczy-dev-infra-textract',
    #   "batch_id": "1",
    #   "client_name": client,
    #   "username": user_mail,
    #   "contract_list": contract_list
    # }

    buttons = st.columns([0.8, 0.2])
    with buttons[0]:
        st.download_button("Download Table", csv, "file.csv", "text/csv", key='download-csv')
    with buttons[1]:
        if st.button("Run Doczy.AI Pipeline"):
            csv_buf = StringIO()
            additional_info.to_csv(csv_buf, header=True, index=False)
            csv_buf.seek(0)
            s3_client.put_object(Bucket='doczy-dev-infra-raw-data-ingestion', Body=csv_buf.getvalue(), Key='training_interface/request_submission.csv')
            csv_buf = StringIO()
            edited_df.to_csv(csv_buf, header=True, index=False)
            csv_buf.seek(0)
            s3_client.put_object(Bucket='doczy-dev-infra-raw-data-ingestion', Body=csv_buf.getvalue(), Key='training_interface/contract_config.csv')
            try:
                save_to_sf('load_request_and_contract_submissions', "request_submission_file_name"
                    , "contract_config_file_name", "request_submission.csv", "contract_config.csv")
            except:
                st.write("running locally")


else:
    st.write("Access Denied")