File size: 3,146 Bytes
91f38ae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
db65cd7
91f38ae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
db65cd7
91f38ae
 
 
 
 
 
3489bcc
91f38ae
 
 
3489bcc
91f38ae
db65cd7
fbab372
db65cd7
 
0dde0c7
db65cd7
 
 
 
318de35
91f38ae
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
# 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 st_aggrid import AgGrid
import logging
logger = logging.getLogger(__name__)
from io import BytesIO
import xlsxwriter
import plotly.express as px
from pandas.api.types import (
    is_categorical_dtype,
    is_datetime64_any_dtype,
    is_numeric_dtype,
    is_object_dtype,
    is_list_like)


           
            
def targets():
    if 'key1' in st.session_state:
        df = st.session_state['key1'].copy()
        idx = df['NetzeroLabel_Score'].idxmax()
        netzero_placeholder = df.loc[idx, 'text']
        df = df.drop(df.filter(regex='Score').columns, axis=1)
        df = df[df.TargetLabel==True].reset_index(drop=True)
        df['keep'] = True
        df.drop(columns = ['ActionLabel','PolicyLabel','PlansLabel'], inplace=True)
        st.session_state['target_hits'] = df
        st.session_state['netzero'] = netzero_placeholder
    
def target_display():
    if 'key1' in st.session_state:
        st.caption(""" **{}** is splitted into **{}** paragraphs/text chunks."""\
                          .format(os.path.basename(st.session_state['filename']),
                                 len(st.session_state['key0'])))   
        
        hits  = st.session_state['target_hits']
        if len(hits) !=0:
            # collecting some statistics
            count_target = sum(hits['TargetLabel'] == True)
            count_ghg = sum(hits['GHGLabel'] == True)
            count_netzero = sum(hits['NetzeroLabel'] == True)
            count_nonghg = sum(hits['NonGHGLabel'] == True)
            count_Mitigation = sum(hits['MitigationLabel'] == True)
            count_Adaptation = sum(hits['AdaptationLabel'] == True)
            

            c1, c2 = st.columns([1,1])
            with c1:
                st.write('**Target Related Paragraphs**: `{}`'.format(count_target))
                st.write('**Netzero Related Paragraphs**: `{}`'.format(count_netzero))
                st.write('**Mitigation Related Paragraphs**: `{}`'.format(count_mitigation))
            with c2:
                st.write('**GHG Target Related Paragraphs**: `{}`'.format(count_ghg))
                st.write('**NonGHG Target Related Paragraphs**: `{}`'.format(count_nonghg))
                st.write('**Adaptation Related Paragraphs**: `{}`'.format(count_adaptation))
            st.write('----------------')
            cols = list(hits.columns)
            sector_cols = list(set(cols) - {'TargetLabel','MitigationLabel','AdaptationLabel','GHGLabel','NetzeroLabel','NonGHGLabel','text','keep','page'})
            placeholder= []
            for col in sector_cols:
                placeholder.append({'Sector':col,'Count':sum(hits[col] == True)})
            sector_df = pd.DataFrame.from_dict(placeholder)
            fig = px.bar(sector_df, x='Sector', y='Count')
            st.plotly_chart(fig,use_container_width= True)
                
            st.dataframe(hits)
        else:
            st.info("🤔 No Targets Found")