import streamlit as st import json import os # shifted from below - this must be the first streamlit call; otherwise: problems st.set_page_config(page_title = 'Climate Policy Analysis Assistant', initial_sidebar_state='expanded', layout="wide") import logging logging.getLogger().setLevel(logging.INFO) from utils.uploadAndExample import add_upload import appStore.doc_processing as processing import appStore.tapp as tapp_extraction import appStore.adapmit as adapmit import appStore.sector as sector import appStore.subtarget as subtarget import appStore.tapp_display as tapp_display import appStore.excel_convert as excel_convert from PIL import Image import pkg_resources installed_packages = pkg_resources.working_set with st.sidebar: # upload and example doc choice = st.sidebar.radio(label = 'Select the Document', help = 'You can upload the document \ or else you can try a example document', options = ('Upload Document', 'Try Example'), horizontal = True) with(open('docStore/sample/files.json','r')) as json_file: files = json.load(json_file) add_upload(choice, files) with st.container(): st.markdown("

Climate Policy Analysis Assistant

", unsafe_allow_html=True) st.write(' ') with st.expander("ℹ️ - About this app", expanded=False): st.write( """ Climate Policy Analysis Assistant (CPo_droid) is an open-source\ digital tool which aims to assist policy analysts and \ other users in extracting and filtering \ information from public documents in context of Climate Change Commitments and Strategies. """) c1, c2, c3 = st.columns([12,1,10]) with c1: st.write('**Definitions**') st.caption(""" - **Target**: Targets are an intention to achieve a specific result, \ for example, to reduce GHG emissions to a specific level \ (a GHG target) or increase energy efficiency or renewable \ energy to a specific level (a non-GHG target), typically by \ a certain date. There are are 3 subclass of targets: - **Netzero**: Identifies if its Netzero Target or not. - **GHG Target**: GHG targets refer to contributions framed as targeted \ outcomes in GHG terms. - **NonGHG Target**: Targets/contributions framed in NOT GHG terms like energy efficiency, sectoral-target like Distribution of 100K electric stoves etc. - **Action**: Actions are an intention to implement specific means of \ achieving GHG reductions, usually in forms of concrete projects. - **Policies**: Policies are domestic planning documents \ such as policies, regulations or guidlines. - **Plans**: Plans are broader than specific policies or actions, such as a general intention \ to ‘improve efficiency’, ‘develop renewable energy’, etc. \ These terms come from the World Bank's NDC platform and WRI's publication. """) #c1, c2, c3 = st.columns([12,1,10]) #with c1: # image = Image.open('docStore/img/flow.jpg') # st.image(image) with c3: st.write(""" What Happens in background? - Step 1: Once the document is provided to app, it undergoes *Pre-processing*.\ In this step the document is broken into smaller paragraphs \ (based on word/sentence count). - Step 2: The paragraphs are fed to **TAPP(Target/Action/Policy/Plan multilabel) Classifier** which detects if the paragraph contains any *TAPP* related information or not. - Step 3: The paragraphs which are detected containing some TAPP \ related information are then fed to multiple classifier to enrich the Information Extraction. These classifiers inlcude: Sector Classifier, Adaptation & Mitigation Classsifier, Conditionality Classifier. """) list_ = "" for package in installed_packages: list_ = list_ + f"{package.key}=={package.version}\n" st.download_button('Download Requirements', list_, file_name='requirements.txt') st.write("") # apps to be run apps = [processing.app, tapp_extraction.app, adapmit.app, sector.app, subtarget.app] # conditional.app, , category.app] multiplier_val =1/len(apps) if st.button("Analyze Document"): prg = st.progress(0.0) for i,func in enumerate(apps): func() prg.progress((i+1)*multiplier_val) prg.empty() if 'key1' in st.session_state: tapp_display.targets() tapp_display.actions() tapp_display.policy() tapp_display.plans() with st.sidebar: topic = st.radio( "Which category you want to explore?", ('Targets', 'Actions','Policy','Plans')) if topic == 'Targets': tapp_display.target_display() excel_convert.filter_dataframe('target_hits',['keep','text','Sector','Sub-Target','page']) with st.sidebar: st.write('-------------') df_xlsx = excel_convert.to_excel() st.download_button(label='📥 Download Result', data=df_xlsx , file_name= os.path.splitext(os.path.basename(st.session_state['filename']))[0]+'.xlsx') elif topic == 'Actions': tapp_display.action_display() excel_convert.filter_dataframe('action_hits',['keep','text','Sector','page']) with st.sidebar: st.write('-------------') df_xlsx = excel_convert.to_excel() st.download_button(label='📥 Download Result', data=df_xlsx , file_name= os.path.splitext(os.path.basename(st.session_state['filename']))[0]+'.xlsx') elif topic == 'Policy': tapp_display.policy_display() excel_convert.filter_dataframe('policy_hits',['keep','text','Sector','page']) with st.sidebar: st.write('-------------') df_xlsx = excel_convert.to_excel() st.download_button(label='📥 Download Result', data=df_xlsx , file_name= os.path.splitext(os.path.basename(st.session_state['filename']))[0]+'.xlsx') elif topic == 'Plans': tapp_display.plans_display() excel_convert.filter_dataframe('plan_hits',['keep','text','Sector','page']) with st.sidebar: st.write('-------------') df_xlsx = excel_convert.to_excel() st.download_button(label='📥 Download Result', data=df_xlsx , file_name= os.path.splitext(os.path.basename(st.session_state['filename']))[0]+'.xlsx') #excel_convert.filter_dataframe('target_hits',['keep','text','Parameter','page']) #with st.sidebar: # st.write('-------------') # df_xlsx = excel_convert.to_excel() # st.download_button(label='📥 Download Result', # data=df_xlsx , # file_name= os.path.splitext(os.path.basename(st.session_state['filename']))[0]+'.xlsx')