AARETE\agupta
213 lines
6.9 KiB
Python
213 lines
6.9 KiB
Python
import os
|
|
import streamlit as st
|
|
from streamlit_extras.add_vertical_space import add_vertical_space
|
|
import pandas as pd
|
|
from datetime import datetime
|
|
import time
|
|
import constants
|
|
|
|
if 'uploading' not in st.session_state:
|
|
st.session_state.uploading = False
|
|
if 'upload_key' not in st.session_state:
|
|
st.session_state.upload_key = 0
|
|
if 'file_list' not in st.session_state:
|
|
st.session_state.file_list = []
|
|
if 'show_batchID' not in st.session_state:
|
|
st.session_state.show_batchID = False
|
|
if 'numFiles' not in st.session_state:
|
|
st.session_state.numFiles = 0
|
|
|
|
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")
|
|
|
|
# AARETE LOGO
|
|
x,y,z = st.columns([15,2,15])
|
|
with y:
|
|
st.image('aaretelogo.png')
|
|
|
|
hide_img_fs = '''
|
|
<style>
|
|
button[title="View fullscreen"]{
|
|
visibility: hidden;}
|
|
</style>
|
|
'''
|
|
st.markdown(hide_img_fs, unsafe_allow_html=True)
|
|
|
|
_,c1= st.columns([5,1])
|
|
st.session_state['user_info'] = {'mail': 'piragavarapu@aarete.com', 'displayName': 'Priya Iragavarapu'}
|
|
try:
|
|
c1.write(f"User: **{st.session_state.user_info['displayName']}**")
|
|
user_mail = st.session_state.user_info['mail']
|
|
except KeyError as e:
|
|
st.write("Session Expired.")
|
|
st.stop()
|
|
|
|
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',(constants.client_list), label_visibility = "collapsed", index = None)
|
|
|
|
file_row = st.columns([0.1, 0.8])
|
|
with file_row[0]:
|
|
st.write("**Upload Files**")
|
|
with file_row[1]:
|
|
file_list = st.file_uploader("Upload", type=['docx','tiff','pdf'], accept_multiple_files=True, label_visibility = "collapsed", help="Only PDF, TIFF and DOCX file formats are supported.", disabled=st.session_state.uploading, key = st.session_state.upload_key)
|
|
|
|
add_vertical_space(2)
|
|
df = pd.DataFrame(columns=['Contract Name'])
|
|
df['Contract Name'] = file_list
|
|
file_names = []
|
|
buttons = st.columns([0.4, 0.4, 0.2])
|
|
|
|
def set_uploading_state():
|
|
if not client == None and not len(file_list) == 0:
|
|
st.session_state.file_list = file_list
|
|
st.session_state.upload_key += 1
|
|
st.session_state.uploading = True
|
|
|
|
def save_uploaded_files(uploaded_files, save_path):
|
|
try:
|
|
if not os.path.exists(save_path):
|
|
os.makedirs(save_path)
|
|
for uploaded_file in uploaded_files:
|
|
with open(os.path.join(save_path, uploaded_file.name), 'wb') as f:
|
|
f.write(uploaded_file.getbuffer())
|
|
return True
|
|
except Exception as e:
|
|
st.error(f"Error saving files: {e}")
|
|
return False
|
|
|
|
with buttons[1]:
|
|
if st.button("Create Batch", on_click=set_uploading_state):
|
|
file_list = st.session_state.file_list
|
|
if client == None:
|
|
st.error("No Client Name Selected.")
|
|
elif len(file_list) == 0:
|
|
st.error("No Files Selected.")
|
|
else:
|
|
with st.spinner('Running...'):
|
|
time.sleep(2)
|
|
if (save_uploaded_files(file_list, os.path.join(os.getcwd(), f'temp/{client}'))):
|
|
st.session_state.numFiles = len(file_list)
|
|
st.session_state.uploading = False
|
|
st.session_state.show_batchID = True
|
|
st.rerun()
|
|
else:
|
|
st.error("Failed to upload the files.")
|
|
if st.session_state.show_batchID:
|
|
st.write(f"{st.session_state.numFiles} files uploaded successfully!")
|
|
# st.session_state.file_list = []
|
|
|
|
add_vertical_space(1)
|
|
|
|
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')
|
|
with checks[2]:
|
|
b = st.checkbox('Pricing Before Carveouts')
|
|
with checks[3]:
|
|
c = st.checkbox('Contract Related')
|
|
with checks[4]:
|
|
d = st.checkbox('Provider')
|
|
with checks[5]:
|
|
e = st.checkbox('Timeline')
|
|
with checks[6]:
|
|
f = st.checkbox('Carveout Indicator')
|
|
with checks[7]:
|
|
g = st.checkbox('Carveout Methodology')
|
|
|
|
add_vertical_space(1)
|
|
|
|
df = pd.DataFrame(columns=['Contract Name', 'Unique Key','Pricing Before Carveouts'
|
|
, 'Contract Related', 'Provider', 'Timeline', 'Carveout Indicator', 'Carveout Methodology'])
|
|
|
|
df['Contract Name'] = [file.name for file in st.session_state.file_list]
|
|
# df['Contract Name'] = st.session_state.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)
|
|
|
|
edited_df['REQUEST_USER'] = user_mail
|
|
edited_df['LATEST_FLAG BOOLEAN'] = True
|
|
edited_df['PIPELINE_KICKOFF_DATETIME'] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
|
edited_df['REQUEST_DATETIME'] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
|
|
|
@st.cache_data
|
|
def convert_df(df):
|
|
return df.to_csv(index=False).encode('utf-8')
|
|
|
|
csv = convert_df(edited_df)
|
|
|
|
additional_info = pd.DataFrame(columns=['CLIENT_NAME', 'REQUEST_USERNAME', 'REQUEST_DATETIME'])
|
|
additional_info.loc[0] = [client, st.session_state.user_info['mail'], datetime.now().strftime("%Y-%m-%d %H:%M:%S")]
|
|
st.write(additional_info)
|
|
|
|
st.session_state.contract_count = 0
|
|
contract_list = []
|
|
for index, row in edited_df.iterrows():
|
|
allow_run_for_contract = False
|
|
group_list = []
|
|
if row['Unique Key']:
|
|
group_list.append('A')
|
|
allow_run_for_contract = True
|
|
if row['Pricing Before Carveouts']:
|
|
group_list.append('B')
|
|
allow_run_for_contract = True
|
|
if row['Contract Related']:
|
|
group_list.append('C')
|
|
allow_run_for_contract = True
|
|
if row['Provider']:
|
|
group_list.append('D')
|
|
allow_run_for_contract = True
|
|
if row['Timeline']:
|
|
group_list.append('E')
|
|
allow_run_for_contract = True
|
|
if row['Carveout Indicator']:
|
|
group_list.append('F')
|
|
allow_run_for_contract = True
|
|
if row['Carveout Methodology']:
|
|
group_list.append('G')
|
|
allow_run_for_contract = True
|
|
if allow_run_for_contract: st.session_state.contract_count += 1
|
|
|
|
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"):
|
|
if not st.session_state.contract_count == len(edited_df):
|
|
st.error("Select at least one Group No. for every Contract")
|
|
else:
|
|
with st.spinner('Running...'):
|
|
time.sleep(2)
|
|
st.write("Success!")
|
|
st.write("Current processing time for A & C: 1 min")
|
|
st.write("Current processing time for B: 10 mins")
|
|
|