File size: 7,713 Bytes
22b8e0b 188bcc5 22b8e0b 188bcc5 22b8e0b 188bcc5 22b8e0b 2d65499 22b8e0b a48c117 22b8e0b a48c117 2d65499 a48c117 22b8e0b |
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 |
# set path
import glob, os, sys; sys.path.append('../udfPreprocess')
#import helper
import udfPreprocess.docPreprocessing as pre
import udfPreprocess.cleaning as clean
#import needed libraries
import seaborn as sns
from pandas import DataFrame
from keybert import KeyBERT
from transformers import pipeline
import matplotlib.pyplot as plt
import numpy as np
import streamlit as st
import pandas as pd
import tempfile
import sqlite3
def app():
with st.container():
st.markdown("<h1 style='text-align: center; color: black;'> SDSN x GIZ Policy Action Tracking v0.1</h1>", unsafe_allow_html=True)
st.write(' ')
st.write(' ')
with st.expander("ℹ️ - About this app", expanded=True):
st.write(
"""
The *Analyse Policy Document* app is an easy-to-use interface built in Streamlit for analyzing policy documents - developed by GIZ Data and the Sustainable Development Solution Network. \n
1. Keyword heatmap \n
2. SDG Classification for the paragraphs/texts in the document
"""
)
st.markdown("")
st.markdown("")
st.markdown("## 📌 Step One: Upload document ")
with st.container():
docs = None
# asking user for either upload or select existing doc
choice = st.radio(label = 'Select the Document',
help = 'You can upload the document \
or else you can try a example document',
options = ('Upload Document', 'Try Example'),
horizontal = True)
if choice == 'Upload Document':
uploaded_file = st.file_uploader('Upload the File', type=['pdf', 'docx', 'txt'])
if uploaded_file is not None:
with tempfile.NamedTemporaryFile(mode="wb") as temp:
bytes_data = uploaded_file.getvalue()
temp.write(bytes_data)
st.write("Uploaded Filename: ", uploaded_file.name)
file_name = uploaded_file.name
file_path = temp.name
docs = pre.load_document(file_path, file_name)
docs_processed, df, all_text, par_list = clean.preprocessingForSDG(docs)
#haystackDoc, dataframeDoc, textData, paraList = clean.preprocessing(docs)
else:
# listing the options
option = st.selectbox('Select the example document',
('Ethiopia: 10 Year Development Plan',
'South Africa:Low Emission strategy'))
if option is 'South Africa:Low Emission strategy':
file_name = file_path = 'sample/South Africa_s Low Emission Development Strategy.txt'
st.write("Selected document:", file_name.split('/')[1])
# with open('sample/South Africa_s Low Emission Development Strategy.txt') as dfile:
# file = open('sample/South Africa_s Low Emission Development Strategy.txt', 'wb')
else:
# with open('sample/Ethiopia_s_2021_10 Year Development Plan.txt') as dfile:
file_name = file_path = 'sample/Ethiopia_s_2021_10 Year Development Plan.txt'
st.write("Selected document:", file_name.split('/')[1])
if option is not None:
docs = pre.load_document(file_path,file_name)
# haystackDoc, dataframeDoc, textData, paraList = clean.preprocessing(docs)
docs_processed, df, all_text, par_list = clean.preprocessingForSDG(docs)
if docs is not None:
@st.cache(allow_output_mutation=True)
def load_keyBert():
return KeyBERT()
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)
)
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)
######## SDG classiciation
# @st.cache(allow_output_mutation=True)
# def load_sdgClassifier():
# classifier = pipeline("text-classification", model= "../models/osdg_sdg/")
# return classifier
# load from disc (github repo) for performance boost
@st.cache(allow_output_mutation=True)
def load_sdgClassifier():
classifier = pipeline("text-classification", model= "jonas/roberta-base-finetuned-sdg")
return classifier
classifier = load_sdgClassifier()
# # not needed, par list comes from pre_processing function already
# word_list = all_text.split()
# len_word_list = len(word_list)
# par_list = []
# par_len = 130
# for i in range(0,len_word_list // par_len):
# string_part = ' '.join(word_list[i*par_len:(i+1)*par_len])
# par_list.append(string_part)
labels = classifier(par_list)
labels_= [(l['label'],l['score']) for l in labels]
df = DataFrame(labels_, columns=["SDG", "Relevancy"])
df['text'] = par_list
df = df.sort_values(by="Relevancy", ascending=False).reset_index(drop=True)
df.index += 1
df =df[df['Relevancy']>.85]
x = df['SDG'].value_counts()
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))
st.markdown("## 🎈 Anything related to SDGs?")
c4, c5, c6 = st.columns([2, 2, 2])
# 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",
],
)
format_dictionary = {
"Relevancy": "{:.1%}",
}
df = df.format(format_dictionary)
with c5:
st.pyplot(fig)
c7, c8, c9 = st.columns([1, 5, 1])
with c8:
st.table(df)
|