app.py

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("<h2 style='text-align: center; color: black;'> Climate Policy Analysis Assistant </h2>", 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()
    elif topic == 'Policy':
        tapp_display.policy_display()
    elif topic == 'Plans':
        tapp_display.plans_display()
        
        #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')