appStore/target.py

# set path
import glob, os, sys; 
sys.path.append('../utils')

#import needed libraries
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import streamlit as st
from utils.target_classifier import load_targetClassifier, target_classification 
import logging
logger = logging.getLogger(__name__)
from utils.config import get_classifier_params
from io import BytesIO
import xlsxwriter
import plotly.express as px

# Declare all the necessary variables
classifier_identifier = 'target'
params  = get_classifier_params(classifier_identifier)

## Labels dictionary ###
_lab_dict = {
            'NEGATIVE':'NO TARGET INFO',
            'TARGET':'TARGET',
            }

@st.cache_data
def to_excel(df):
    len_df = len(df)
    output = BytesIO()
    writer = pd.ExcelWriter(output, engine='xlsxwriter')
    df.to_excel(writer, index=False, sheet_name='Sheet1')
    workbook = writer.book
    worksheet = writer.sheets['Sheet1']
    worksheet.data_validation('E2:E{}'.format(len_df), 
                              {'validate': 'list', 
                               'source': ['No', 'Yes', 'Discard']})
    writer.save()
    processed_data = output.getvalue()
    return processed_data

def app():

    #### APP INFO #####
    #     st.write(
    #         """     
    #         The **Target Extraction** app is an easy-to-use interface built \
    #             in Streamlit for analyzing policy documents for \
    #              Classification of the paragraphs/texts in the document *If it \
    #             contains any Economy-Wide Targets related information* - \
    #             developed by GIZ Data Service Center, GFA, IKI Tracs, \
    #              SV Klima and SPA. \n
    #         """)


    ### Main app code ###
    with st.container():
        if 'key0' in st.session_state:
            df = st.session_state.key0

            #load Classifier
            classifier = load_targetClassifier(classifier_name=params['model_name'])
            st.session_state['{}_classifier'.format(classifier_identifier)] = classifier
            if len(df) > 100:
                warning_msg = ": This might take sometime, please sit back and relax."
            else:
                warning_msg = ""
                
            df  = target_classification(haystack_doc=df,
                                    threshold= params['threshold'])
            st.session_state.key1 = df

          # # excel part
            # temp = df[df['Relevancy']>threshold]
            
            # df['Validation'] =  'No'
            # df_xlsx = to_excel(df)
            # st.download_button(label='📥 Download Current Result',
            #                 data=df_xlsx ,
            #                 file_name= 'file_target.xlsx')
              
def target_display():
    if  'key1' in st.session_state:
        df = st.session_state.key1
        hits  = df[df['Target Label'] == 'TARGET']
        range_val = min(5,len(hits))
        if range_val !=0:
            count_df = df['Target Label'].value_counts()
            count_df = count_df.rename('count')
            count_df = count_df.rename_axis('Target Label').reset_index()
            count_df['Label_def'] = count_df['Target Label'].apply(lambda x: _lab_dict[x])

            fig = px.bar(count_df, y="Label_def", x="count", orientation='h', height=200)
            c1, c2 = st.columns([1,1])
            with c1:
                st.plotly_chart(fig,use_container_width= True)
            
            count_netzeo = sum(hits['Netzero Label'] == 'NETZERO')
            count_ghg = sum(hits['GHG Label'] == 'LABEL_2')
            count_economy = sum([True if 'Economy-wide' in x else False 
                              for x in hits['Sector Label']])

            with c2:
                st.write('**NetZero Targets**: `{}`'.format(count_netzeo))
                st.write('**GHG Targets**: `{}`'.format(count_ghg))
                st.write('**Economy-wide Targets**: `{}`'.format(count_economy))
            hits = hits.sort_values(by=['Relevancy'], ascending=False)
            st.write("")
            st.markdown("###### Top few Target Classified paragraph/text results ######")
            range_val = min(5,len(hits))
            for i in range(range_val):
                # the page number reflects the page that contains the main paragraph 
                # according to split limit, the overlapping part can be on a separate page
                st.write('**Result {}** `page {}` (Relevancy Score: {:.2f})'.format(i+1,hits.iloc[i]['page'],hits.iloc[i]['Relevancy']))                        
                st.write("\t Text: \t{}".format(hits.iloc[i]['text'].replace("\n", " ")))
        else:
            st.info("🤔 No Targets found")