File size: 8,705 Bytes
22b8e0b 72e4dad 570b6e4 22b8e0b 0e0caa9 22b8e0b 8c4c590 72e4dad 4df35da 570b6e4 5bc4948 72e4dad 22b8e0b ce1209f 22b8e0b 72e4dad 22b8e0b ce1209f 570b6e4 1984bd1 72e4dad 369dc03 ce1209f 369dc03 47453fe ce1209f 47453fe ce1209f 22b8e0b d3cc512 fb4cce0 e836bc5 72e4dad fb4cce0 da1c31e 05064f1 da1c31e fb4cce0 0e0caa9 ce1209f 5e6f5c6 0e0caa9 ce1209f 5bc4948 5e6f5c6 5bc4948 fb4cce0 0e0caa9 fb4cce0 0e0caa9 5bc4948 0e0caa9 5bc4948 0e0caa9 5e6f5c6 fb4cce0 e836bc5 fb4cce0 8c4c590 72e4dad |
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 |
# 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
import docx
from docx.shared import Inches
from docx.shared import Pt
from docx.enum.style import WD_STYLE_TYPE
from utils.sdg_classifier import sdg_classification
from utils.sdg_classifier import runSDGPreprocessingPipeline
from utils.keyword_extraction import keywordExtraction, textrank
import logging
logger = logging.getLogger(__name__)
def app():
with st.container():
st.markdown("<h2 style='text-align: center; color: black;'> SDG Classification and Keyphrase Extraction </h2>", 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("")
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']
allDocuments = runSDGPreprocessingPipeline(file_path,file_name)
if len(allDocuments['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(allDocuments['documents'])
sdg_labels = df.SDG.unique()
# tfidfkeywordList = []
textrankkeywordlist = []
for label in sdg_labels:
sdgdata = " ".join(df[df.SDG == label].text.to_list())
# tfidflist_ = keywordExtraction(label,[sdgdata])
textranklist_ = textrank(sdgdata, words = 20)
tfidfkeywordList.append({'SDG':label, 'TFIDF Keywords':tfidflist_})
textrankkeywordlist.append({'SDG':label, 'TextRank Keywords':textranklist_})
tfidfkeywordsDf = pd.DataFrame(tfidfkeywordList)
tRkeywordsDf = pd.DataFrame(textrankkeywordlist)
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, colors=colors, radius=2, center=(4, 4),
wedgeprops={"linewidth": 1, "edgecolor": "white"},
frame=False,labels =list(x.index))
# fig.savefig('temp.png', bbox_inches='tight',dpi= 100)
st.markdown("#### Anything related to SDGs? ####")
c4, c5, c6 = st.columns([2, 2, 2])
with c5:
st.pyplot(fig)
st.markdown("##### What keywords are present under SDG classified text? #####")
st.write("TFIDF BASED")
c1, c2, c3 = st.columns([1, 10, 1])
with c2:
st.table(tfidfkeywordsDf)
st.write("TextRank BASED")
c11, c12, c13 = st.columns([1, 10, 1])
with c12:
st.table(tRkeywordsDf)
c7, c8, c9 = st.columns([1, 10, 1])
with c8:
st.table(df)
else:
st.info("🤔 No document found, please try to upload it at the sidebar!")
logging.warning("Terminated as no document provided")
# 1. Keyword heatmap \n
# 2. SDG Classification for the paragraphs/texts in the document
#
# with st.container():
# if 'docs' in st.session_state:
# docs = st.session_state['docs']
# docs_processed, df, all_text, par_list = clean.preprocessingForSDG(docs)
# # paraList = st.session_state['paraList']
# logging.info("keybert")
# with st.spinner("Running Key bert"):
# kw_model = load_keyBert()
# keywords = kw_model.extract_keywords(
# all_text,
# keyphrase_ngram_range=(1, 3),
# use_mmr=True,
# stop_words="english",
# top_n=10,
# diversity=0.7,
# )
# st.markdown("## 🎈 What is my document about?")
# df = (
# DataFrame(keywords, columns=["Keyword/Keyphrase", "Relevancy"])
# .sort_values(by="Relevancy", ascending=False)
# .reset_index(drop=True)
# )
# df1 = (
# DataFrame(keywords, columns=["Keyword/Keyphrase", "Relevancy"])
# .sort_values(by="Relevancy", ascending=False)
# .reset_index(drop=True)
# )
# df.index += 1
# # Add styling
# cmGreen = sns.light_palette("green", as_cmap=True)
# cmRed = sns.light_palette("red", as_cmap=True)
# df = df.style.background_gradient(
# cmap=cmGreen,
# subset=[
# "Relevancy",
# ],
# )
# c1, c2, c3 = st.columns([1, 3, 1])
# format_dictionary = {
# "Relevancy": "{:.1%}",
# }
# df = df.format(format_dictionary)
# with c2:
#
# st.table(df) |