Spaces:
GIZ
/
Running on CPU Upgrade

File size: 7,938 Bytes
22b8e0b
72e4dad
570b6e4
22b8e0b
 
 
 
 
0e0caa9
22b8e0b
40debb1
590f5f3
4df35da
fc140bc
 
72e4dad
 
fc140bc
72e4dad
 
fc140bc
 
 
 
 
 
 
 
 
 
 
72e4dad
22b8e0b
 
40debb1
22b8e0b
183851c
22b8e0b
 
 
72e4dad
22b8e0b
 
 
ce1209f
570b6e4
1984bd1
 
 
72e4dad
369dc03
ce1209f
 
 
 
 
369dc03
a3c251d
 
47453fe
 
ce1209f
 
 
 
 
 
 
 
 
 
 
 
 
47453fe
9de136f
a3c251d
47453fe
 
 
 
ce1209f
 
22b8e0b
 
40debb1
c8b3108
d3cc512
fb4cce0
fc140bc
fb4cce0
da1c31e
05064f1
f59362a
 
9f55059
 
fc140bc
 
9f55059
fc140bc
d7ce857
fb4cce0
 
 
 
 
 
d7ce857
f59362a
fc140bc
9f55059
d7ce857
0e0caa9
 
fc140bc
40debb1
d7ce857
9f55059
5bc4948
 
fb4cce0
 
 
 
aee56b8
6682efd
07dfa2c
aa8662e
5203baf
fb4cce0
0e0caa9
 
fb4cce0
 
ed16157
fb4cce0
 
 
62fb673
bcae986
9215ec6
397db2c
c8b3108
11e64f9
0e0caa9
9f55059
590f5f3
ea3aaf3
c8b3108
11e64f9
c8b3108
590f5f3
9c7cdba
e836bc5
fb4cce0
 
 
 
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
# 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
from st_aggrid.shared import ColumnsAutoSizeMode
from utils.sdg_classifier import sdg_classification
from utils.sdg_classifier import runSDGPreprocessingPipeline, load_sdgClassifier
from utils.keyword_extraction import textrank
import logging
logger = logging.getLogger(__name__)
from utils.checkconfig import getconfig


# Declare all the necessary variables
config = getconfig('paramconfig.cfg')
model_name = config.get('sdg','MODEL')
split_by = config.get('sdg','SPLIT_BY')
split_length = int(config.get('sdg','SPLIT_LENGTH'))
split_overlap = int(config.get('sdg','SPLIT_OVERLAP'))
remove_punc = bool(int(config.get('sdg','REMOVE_PUNC')))
split_respect_sentence_boundary = bool(int(config.get('sdg','RESPECT_SENTENCE_BOUNDARY')))
threshold = float(config.get('sdg','THRESHOLD'))
top_n = int(config.get('sdg','TOP_KEY'))


def app():

    #### APP INFO #####
    with st.container():
        st.markdown("<h1 style='text-align: center; color: black;'> SDG Classification and Keyphrase Extraction </h1>", unsafe_allow_html=True)
        st.write(' ')
        st.write(' ')

    with st.expander("ℹ️ - About this app", expanded=False):

        st.write(
            """     
            The *SDG Analysis* app is an easy-to-use interface built \
                in Streamlit for analyzing policy documents with respect to SDG \
                 Classification for the paragraphs/texts in the document and \
                extracting the keyphrase per SDG label - developed by GIZ Data \
                 and the Sustainable Development Solution Network. \n
            """)
        st.write("""**Document Processing:** The Uploaded/Selected document is \
            automatically cleaned and split into paragraphs with a maximum \
            length of 120 words using a Haystack preprocessing pipeline. The \
            length of 120 is an empirical value which should reflect the length \
            of a “context” and should limit the paragraph length deviation. \
            However, since we want to respect the sentence boundary the limit \
            can breach and hence this limit of 120 is tentative.  \n
            """)
        st.write("""**SDG cLassification:** The application assigns paragraphs \
            to 15 of the 17 United Nations Sustainable Development Goals (SDGs).\
            SDG 16 “Peace, Justice and Strong Institutions” and SDG 17 \
            “Partnerships for the Goals” are excluded from the analysis due to \
            their broad nature which could potentially inflate the results. \
            Each paragraph is assigned to one SDG only. Again, the results are \
            displayed in a summary table including the number of the SDG, a \
            relevancy score highlighted through a green color shading, and the \
            respective text of the analyzed paragraph. Additionally, a pie \
            chart with a blue color shading is displayed which illustrates the \
            three most prominent SDGs in the document. The SDG classification \
            uses open-source training [data](https://zenodo.org/record/5550238#.Y25ICHbMJPY) \
            from [OSDG.ai](https://osdg.ai/) which is a global \
            partnerships and growing community of researchers and institutions \
            interested in the classification of research according to the \
            Sustainable Development Goals. The summary table only displays \
            paragraphs with a calculated relevancy score above 85%.  \n""")

        st.write("""**Keyphrase Extraction:** The application extracts 15 \
            keyphrases from the document, calculates a respective relevancy \
            score, and displays the results in a summary table. The keyphrases \
            are extracted using using [Textrank](https://github.com/summanlp/textrank)\
            which is an easy-to-use computational less expensive \
            model leveraging combination of TFIDF and Graph networks.
            """)
        st.markdown("")

    
    ### Main app code ###
    with st.container():
        if st.button("RUN SDG Analysis"):
                   
            if 'filepath' in st.session_state:
                file_name = st.session_state['filename']
                file_path = st.session_state['filepath']
                classifier = load_sdgClassifier(classifier_name=model_name)
                st.session_state['sdg_classifier'] = classifier
                all_documents = runSDGPreprocessingPipeline(file_name= file_name,
                                        file_path= file_path, split_by= split_by,
                                        split_length= split_length,
                split_respect_sentence_boundary= split_respect_sentence_boundary,
                split_overlap= split_overlap, remove_punc= remove_punc)

                if len(all_documents['documents']) > 100:
                    warning_msg = ": This might take sometime, please sit back and relax."
                else:
                    warning_msg = ""

                with st.spinner("Running SDG Classification{}".format(warning_msg)):

                    df, x = sdg_classification(haystack_doc=all_documents['documents'],
                                                threshold= threshold)
                    df = df.drop(['Relevancy'], axis = 1)
                    sdg_labels = x.SDG.unique()
                    textrank_keyword_list = []
                    for label in sdg_labels:
                        sdgdata = " ".join(df[df.SDG == label].text.to_list())
                        textranklist_ = textrank(textdata=sdgdata, words= top_n)
                        if len(textranklist_) > 0:
                            textrank_keyword_list.append({'SDG':label, 'TextRank Keywords':",".join(textranklist_)})
                    textrank_keywords_df = pd.DataFrame(textrank_keyword_list)


                    plt.rcParams['font.size'] = 25
                    colors = plt.get_cmap('Blues')(np.linspace(0.2, 0.7, len(x)))
                    # plot
                    fig, ax = plt.subplots()
                    ax.pie(x['count'], colors=colors, radius=2, center=(4, 4),
                        wedgeprops={"linewidth": 1, "edgecolor": "white"},
                        textprops={'fontsize': 14}, 
                        frame=False,labels =list(x.SDG_Num),
                        labeldistance=1.2)
                    # fig.savefig('temp.png', bbox_inches='tight',dpi= 100)
                    

                    st.markdown("#### Anything related to SDGs? ####")

                    c4, c5, c6 = st.columns([1,2,2])

                    with c5:
                        st.pyplot(fig)
                    with c6:
                        labeldf = x['SDG_name'].values.tolist()
                        labeldf = "<br>".join(labeldf)
                        st.markdown(labeldf, unsafe_allow_html=True)
                    st.write("")
                    st.markdown("###### What keywords are present under SDG classified text? ######")

                    AgGrid(textrank_keywords_df, reload_data = False, 
                            update_mode="value_changed",
                    columns_auto_size_mode = ColumnsAutoSizeMode.FIT_CONTENTS)
                    st.write("")
                    st.markdown("###### Top few SDG Classified paragraph/text results ######")

                    AgGrid(df, 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")