File size: 10,289 Bytes
91f38ae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
db65cd7
91f38ae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b805749
 
91f38ae
 
 
 
 
 
3489bcc
91f38ae
 
 
3489bcc
91f38ae
533a3db
 
 
db65cd7
fbab372
040e14b
 
db65cd7
 
0dde0c7
040e14b
db65cd7
 
 
 
040e14b
91f38ae
 
b805749
 
 
533a3db
b805749
 
 
533a3db
b805749
533a3db
 
b805749
533a3db
b805749
 
 
 
 
533a3db
b805749
 
533a3db
b805749
 
 
 
 
 
533a3db
b805749
 
 
 
533a3db
b805749
533a3db
b805749
 
 
 
 
 
 
 
 
533a3db
b805749
 
bc992a7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b805749
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
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
# 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('----------------')

            st.markdown("<h4 style='text-align: left; color: black;'> Sectoral Target Related Paragraphs Count </h4>", unsafe_allow_html=True)
            
            cols = list(hits.columns)
            sector_cols = list(set(cols) - {'TargetLabel','MitigationLabel','AdaptationLabel','GHGLabel','NetzeroLabel','NonGHGLabel','text','keep','page'})
            hits['Sector'] = hits.apply(lambda x: [col if x[col] == True for col in sector_cols],axis=1)
            hits['Sub-Target'] = hits.apply(lambda x: [col if x[col] == True for col in ['GHGLabel','NetzeroLabel','NonGHGLabel'],axis=1)
            placeholder= []
            for col in sector_cols:
                placeholder.append({'Sector':col,'Count':sum(hits[col] == True)})
                hits['Sector']
            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[['text','page','keep','MitigationLabel','AdaptationLabel','Sector','Sub-Target',]])
        else:
            st.info("🤔 No Targets Found")



def actions():
    if 'key1' in st.session_state:
        df = st.session_state['key1'].copy()
        df = df.drop(df.filter(regex='Score').columns, axis=1)
        df = df[df.ActionLabel==True].reset_index(drop=True)
        df['keep'] = True
        df.drop(columns = ['TargetLabel','PolicyLabel','PlansLabel','GHGLabel','NetzeroLabel','NonGHGLabel'], inplace=True)
        st.session_state['action_hits'] = df
    
def action_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['action_hits']
        if len(hits) !=0:
            # collecting some statistics
            count_action = sum(hits['ActionLabel'] == True)
            count_mitigation = sum(hits['MitigationLabel'] == True)
            count_adaptation = sum(hits['AdaptationLabel'] == True)
            

            c1, c2 = st.columns([1,1])
            with c1:
                st.write('**Action Related Paragraphs**: `{}`'.format(count_action))
                st.write('**Mitigation Related Paragraphs**: `{}`'.format(count_mitigation))
            with c2:
                st.write('**Adaptation Related Paragraphs**: `{}`'.format(count_adaptation))
            st.write('----------------')
            st.markdown("<h4 style='text-align: left; color: black;'> Sectoral Action Related Paragraphs Count </h4>", unsafe_allow_html=True)
            cols = list(hits.columns)
            sector_cols = list(set(cols) - {'ActionLabel','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 Actions Found")



def policy():
    if 'key1' in st.session_state:
        df = st.session_state['key1'].copy()
        df = df.drop(df.filter(regex='Score').columns, axis=1)
        df = df[df.PolicyLabel==True].reset_index(drop=True)
        df['keep'] = True
        df.drop(columns = ['TargetLabel','ActionLabel','PlansLabel','GHGLabel','NetzeroLabel','NonGHGLabel'], inplace=True)
        st.session_state['policy_hits'] = df
    
def policy_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['policy_hits']
        if len(hits) !=0:
            # collecting some statistics
            count_action = sum(hits['PolicyLabel'] == True)
            count_mitigation = sum(hits['MitigationLabel'] == True)
            count_adaptation = sum(hits['AdaptationLabel'] == True)
            

            c1, c2 = st.columns([1,1])
            with c1:
                st.write('**Policy Related Paragraphs**: `{}`'.format(count_action))
                st.write('**Mitigation Related Paragraphs**: `{}`'.format(count_mitigation))
            with c2:
                st.write('**Adaptation Related Paragraphs**: `{}`'.format(count_adaptation))
            st.write('----------------')
            st.markdown("<h4 style='text-align: left; color: black;'> Sectoral Policy Related Paragraphs Count </h4>", unsafe_allow_html=True)
            cols = list(hits.columns)
            sector_cols = list(set(cols) - {'PolicyLabel','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 Policy Found")

def plans():
    if 'key1' in st.session_state:
        df = st.session_state['key1'].copy()
        df = df.drop(df.filter(regex='Score').columns, axis=1)
        df = df[df.PlansLabel==True].reset_index(drop=True)
        df['keep'] = True
        df.drop(columns = ['TargetLabel','PolicyLabel','ActionLabel','GHGLabel','NetzeroLabel','NonGHGLabel'], inplace=True)
        st.session_state['plan_hits'] = df
    
def plans_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['plan_hits']
        if len(hits) !=0:
            # collecting some statistics
            count_action = sum(hits['PlansLabel'] == True)
            count_mitigation = sum(hits['MitigationLabel'] == True)
            count_adaptation = sum(hits['AdaptationLabel'] == True)
            

            c1, c2 = st.columns([1,1])
            with c1:
                st.write('**Plans Related Paragraphs**: `{}`'.format(count_action))
                st.write('**Mitigation Related Paragraphs**: `{}`'.format(count_mitigation))
            with c2:
                st.write('**Adaptation Related Paragraphs**: `{}`'.format(count_adaptation))
            st.write('----------------')
            st.markdown("<h4 style='text-align: left; color: black;'> Sectoral Plans Related Paragraphs Count </h4>", unsafe_allow_html=True)
            cols = list(hits.columns)
            sector_cols = list(set(cols) - {'PlanLabel','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 Plans Found")