import streamlit as st
import os
import pkg_resources
# Using this wacky hack to get around the massively ridicolous managed env loading order
def is_installed(package_name, version):
try:
pkg = pkg_resources.get_distribution(package_name)
return pkg.version == version
except pkg_resources.DistributionNotFound:
return False
# shifted from below - this must be the first streamlit call; otherwise: problems
st.set_page_config(page_title = 'Vulnerability Analysis',
initial_sidebar_state='expanded', layout="wide")
@st.cache_resource # cache the function so it's not called every time app.py is triggered
def install_packages():
install_commands = []
if not is_installed("spaces", "0.12.0"):
install_commands.append("pip install spaces==0.17.0")
if not is_installed("pydantic", "1.8.2"):
install_commands.append("pip install pydantic==1.8.2")
if not is_installed("typer", "0.4.0"):
install_commands.append("pip install typer==0.4.0")
if install_commands:
os.system(" && ".join(install_commands))
# install packages if necessary
install_packages()
import appStore.vulnerability_analysis as vulnerability_analysis
import appStore.target as target_extraction
import appStore.doc_processing as processing
from utils.uploadAndExample import add_upload
from utils.vulnerability_classifier import label_dict
import pandas as pd
import plotly.express as px
#st.set_page_config(page_title = 'Vulnerability Analysis',
# initial_sidebar_state='expanded', layout="wide")
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)
add_upload(choice)
with st.container():
st.markdown("
Vulnerability Analysis 2.0
", unsafe_allow_html=True)
st.write(' ')
with st.expander("ℹ️ - About this app", expanded=False):
st.write(
"""
The Vulnerability Analysis App is an open-source\
digital tool which aims to assist policy analysts and \
other users in extracting and filtering references \
to different groups in vulnerable situations from public documents. \
We use Natural Language Processing (NLP), specifically deep \
learning-based text representations to search context-sensitively \
for mentions of the special needs of groups in vulnerable situations
to cluster them thematically.
""")
#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.
# - **Economy-wide Target**: Certain Target are applicable \
# not at specific Sector level but are applicable at economic \
# wide scale.
# - **Netzero**: Identifies if its Netzero Target or not.
# - 'NET-ZERO': target_labels = ['T_Netzero','T_Netzero_C']
# - 'Non Netzero Target': target_labels_neg = ['T_Economy_C',
# 'T_Economy_Unc','T_Adaptation_C','T_Adaptation_Unc','T_Transport_C',
# 'T_Transport_O_C','T_Transport_O_Unc','T_Transport_Unc']
# - 'Others': Other Targets beside covered above
# - **GHG Target**: GHG targets refer to contributions framed as targeted \
# outcomes in GHG terms.
# - 'GHG': target_labels_ghg_yes = ['T_Transport_Unc','T_Transport_C']
# - 'NON GHG TRANSPORT TARGET': target_labels_ghg_no = ['T_Adaptation_Unc',\
# 'T_Adaptation_C', 'T_Transport_O_Unc', 'T_Transport_O_C']
# - 'OTHERS': Other Targets beside covered above.
# - **Conditionality**: An “unconditional contribution” is what countries \
# could implement without any conditions and based on their own \
# resources and capabilities. A “conditional contribution” is one \
# that countries would undertake if international means of support \
# are provided, or other conditions are met.
# - **Action**: Actions are an intention to implement specific means of \
# achieving GHG reductions, usually in forms of concrete projects.
# - **Policies and Plans**: Policies are domestic planning documents \
# such as policies, regulations or guidlines, and Plans are broader \
# than specific policies or actions, such as a general intention \
# to ‘improve efficiency’, ‘develop renewable energy’, etc. \
# The 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 then fed to the **Vulnerability Classifier** which detects if
the paragraph contains any or multiple references to vulnerable groups.
""")
st.write("")
# Define the apps used
apps = [processing.app, vulnerability_analysis.app, target_extraction.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)
# If there is data stored
if 'key0' in st.session_state:
###################################################################
#with st.sidebar:
# topic = st.radio(
# "Which category you want to explore?",
# (['Vulnerability', 'Concrete targets/actions/measures']))
#if topic == 'Vulnerability':
# Assign dataframe a name
df_vul = st.session_state['key0']
col1, col2 = st.columns([1,1])
with col1:
# Header
st.subheader("Explore references to vulnerable groups:")
# Text
num_paragraphs = len(df_vul['Vulnerability Label'])
num_references = len(df_vul[df_vul['Vulnerability Label'] != 'Other'])
st.markdown(f""" The document contains a
total of {num_paragraphs} paragraphs.
We identified {num_references}
references to vulnerable groups.
In the pie chart on the right you can see the distribution of the different
groups defined. For a more detailed view in the text, see the paragraphs and
their respective labels in the table below.""", unsafe_allow_html=True)
with col2:
### Pie chart
# Create a df that stores all the labels
df_labels = pd.DataFrame(list(label_dict.items()), columns=['Label ID', 'Label'])
# Count how often each label appears in the "Vulnerability Labels" column
label_counts = df_vul['Vulnerability Label'].value_counts().reset_index()
label_counts.columns = ['Label', 'Count']
# Merge the label counts with the df_label DataFrame
df_labels = df_labels.merge(label_counts, on='Label', how='left')
# Configure graph
fig = px.pie(df_labels,
names="Label",
values="Count",
title='Label Counts',
hover_name="Count",
color_discrete_sequence=px.colors.qualitative.Plotly
)
#Show plot
st.plotly_chart(fig, use_container_width=True)
### Table
st.table(df_vul[df_vul['Vulnerability Label'] != 'Other'])
# vulnerability_analysis.vulnerability_display()
# elif topic == 'Action':
# policyaction.action_display()
# else:
# policyaction.policy_display()
#st.write(st.session_state.key0)