Spaces:
GIZ
/
Running on CPU Upgrade

File size: 7,063 Bytes
22b8e0b
550b85d
 
22b8e0b
 
b26b139
2663a97
 
 
1b62a9f
 
 
 
b26b139
 
fa191c0
2663a97
b26b139
 
 
fa191c0
2663a97
b26b139
 
fa191c0
b26b139
 
8c4c590
2663a97
 
 
 
 
 
 
 
 
 
 
1b62a9f
2663a97
1b62a9f
2663a97
 
22b8e0b
b26b139
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1b62a9f
 
b26b139
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2663a97
 
 
 
 
1b62a9f
 
 
 
2663a97
 
 
 
 
 
 
 
1b62a9f
 
 
 
 
dacf87d
1b62a9f
 
2663a97
 
 
 
 
 
 
 
1b62a9f
2663a97
 
1b62a9f
 
 
 
 
 
 
 
 
 
 
 
 
49548a6
 
 
495891a
1b62a9f
 
2663a97
 
 
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
# set path
import glob, os, sys; 
sys.path.append('../utils')

import streamlit as st
import ast
import logging
from utils.ndc_explorer import countrySpecificCCA, countrySpecificCCM
from utils.checkconfig import getconfig
from utils.semantic_search import runSemanticPreprocessingPipeline,process_semantic_output
from utils.semantic_search import semanticSearchPipeline, runSemanticPipeline
from st_aggrid import AgGrid
from st_aggrid.shared import ColumnsAutoSizeMode

# Reading data and Declaring necessary variables
with open('docStore/ndcs/countryList.txt') as dfile:
    countryList = dfile.read()
countryList = ast.literal_eval(countryList)
countrynames = list(countryList.keys())
    
with open('docStore/ndcs/cca.txt', encoding='utf-8', errors='ignore') as dfile:
    cca_sent = dfile.read()
cca_sent = ast.literal_eval(cca_sent)
            
with open('docStore/ndcs/ccm.txt', encoding='utf-8', errors='ignore') as dfile:
    ccm_sent = dfile.read()
ccm_sent = ast.literal_eval(ccm_sent)

config = getconfig('paramconfig.cfg')
split_by = config.get('coherence','SPLIT_BY')
split_length = int(config.get('coherence','SPLIT_LENGTH'))
split_overlap = int(config.get('coherence','SPLIT_OVERLAP'))
split_respect_sentence_boundary = bool(int(config.get('coherence',
                                    'RESPECT_SENTENCE_BOUNDARY')))
remove_punc = bool(int(config.get('coherence','REMOVE_PUNC')))
embedding_model = config.get('coherence','RETRIEVER')
embedding_model_format = config.get('coherence','RETRIEVER_FORMAT')
embedding_layer = int(config.get('coherence','RETRIEVER_EMB_LAYER'))
embedding_dim  = int(config.get('coherence','EMBEDDING_DIM'))
max_seq_len = int(config.get('coherence','MAX_SEQ_LENGTH')) 
retriever_top_k = int(config.get('coherence','RETRIEVER_TOP_K'))



def app():

    #### APP INFO #####
    with st.container():
        st.markdown("<h1 style='text-align: center;  \
                      color: black;'> Check NDC Coherence</h1>", 
                      unsafe_allow_html=True)
        st.write(' ')
        st.write(' ')
    with st.expander("ℹ️ - About this app", expanded=False):

        st.write(
            """     
            The *Check NDC Coherence* application provides easy evaluation of 
            coherence between a given policy document and a country’s (Intended)\
            Nationally Determined Contribution (INDCs/NDCs) using open-source \
            data from the German Institute of Development and Sustainability’s \
            (IDOS) [NDC Explorer]
            (https://klimalog.idos-research.de/ndc/#NDCExplorer/worldMap?NewAndUpdatedNDC??income???catIncome).\
            """)
        st.write("")
        st.write(""" User can select a country context via the drop-down menu \
            on the left-hand side of the application. Subsequently, the user is \
            given the opportunity to manually upload another policy document \
            from the same national context or to select a pre-loaded example \
            document. Thereafter, the user can choose between two categories \
            to compare coherence between the documents: climate change adaptation \
            and climate change mitigation. Based on the selected information, \
            the application identifies relevant paragraphs in the uploaded \
            document and assigns them to the respective indicator from the NDC \
            Explorer. Currently, the NDC Explorer has 20 indicators under \
            climate change mitigation (e.g., fossil fuel production, REDD+) and \
            22 indicators under climate change adaptation (e.g., sea level rise,\
            investment needs). The assignment of the paragraph to a corresponding\
            indicator is based on vector similarities in which only paragraphs \
            with similarity above 0.55  to the indicators are considered. """)
    
    with st.sidebar:

        option = st.selectbox('Select Country', (countrynames))
        countryCode = countryList[option]
        st.markdown("---")

        genre = st.radio( "Select Category",('Climate Change Adaptation', 
                                            'Climate Change Mitigation'))
        st.markdown("---")
    
    with st.container():
        if st.button("Check Coherence"):
            sent_cca = countrySpecificCCA(cca_sent,1,countryCode)
            sent_ccm = countrySpecificCCM(ccm_sent,1,countryCode)

            if 'filepath' in st.session_state:
                allDocuments = runSemanticPreprocessingPipeline(
                        file_path= st.session_state['filepath'],
                        file_name  = st.session_state['filename'],
                        split_by=split_by,
                        split_length= split_length,
                        split_overlap=split_overlap,
                        remove_punc= remove_punc,
                split_respect_sentence_boundary=split_respect_sentence_boundary)
                # genre = st.radio( "Select Category",('Climate Change Adaptation', 'Climate Change Mitigation'))
                if genre == 'Climate Change Adaptation':
                    sent_dict = sent_cca
                else:
                    sent_dict = sent_ccm
                sent_labels = []
                for key,sent in sent_dict.items():
                            sent_labels.append(sent)
                if len(allDocuments['documents']) > 100:
                    warning_msg = ": This might take sometime, please sit back and relax."
                else:
                    warning_msg = ""
                logging.info("starting Coherence analysis, \
                    country selected {}".format(option))
                with st.spinner("Performing Coherence Analysis for {} \
                    under {} category{}".format(option,genre,warning_msg)):
                    semanticsearch_pipeline, doc_store = semanticSearchPipeline(documents = allDocuments['documents'],
                            embedding_model= embedding_model, 
                            embedding_layer= embedding_layer,
                            embedding_model_format= embedding_model_format,
                            retriever_top_k= retriever_top_k,
                            embedding_dim=embedding_dim,
                            max_seq_len=max_seq_len, useQueryCheck=False)
                    raw_output = runSemanticPipeline(pipeline=semanticsearch_pipeline,queries=sent_labels)
                    results_df = process_semantic_output(raw_output)
                    data = results_df.drop(['answer','answer_offset',
                                'context_offset','context','retriever_score'],
                                axis = 1)
                    AgGrid(data, reload_data = False, update_mode="value_changed",
                    columns_auto_size_mode = ColumnsAutoSizeMode.FIT_CONTENTS)
                    
            else:
                st.info("🤔 No document found, please try to upload it at the sidebar!")
                logging.warning("Terminated as no document provided")