File size: 5,405 Bytes
2caced7 |
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('../udfPreprocess')
#import helper
#import needed libraries
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
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 udfPreprocess.sdg_classifier import sdg_classification
from udfPreprocess.sdg_classifier import runSDGPreprocessingPipeline
import configparser
import tempfile
import sqlite3
import logging
logger = logging.getLogger(__name__)
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=False):
st.write(
"""
The *Analyse Policy Document* 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 - developed by GIZ Data and the Sustainable Development Solution Network. \n
""")
st.markdown("")
with st.container():
if 'filepath' in st.session_state:
paraList = runSDGPreprocessingPipeline()
with st.spinner("Running SDG"):
df, x = sdg_classification(paraList)
# classifier = load_sdgClassifier()
# labels = classifier(par_list)
# labels_= [(l['label'],l['score']) for l in labels]
# df2 = DataFrame(labels_, columns=["SDG", "Relevancy"])
# df2['text'] = par_list
# df2 = df2.sort_values(by="Relevancy", ascending=False).reset_index(drop=True)
# df2.index += 1
# df2 =df2[df2['Relevancy']>.85]
# x = df2['SDG'].value_counts()
# df3 = df2.copy()
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? ####")
# 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)
# df2 = df2.style.background_gradient(
# cmap=cmGreen,
# subset=[
# "Relevancy",
# ],
# )
# format_dictionary = {
# "Relevancy": "{:.1%}",
# }
# df2 = df2.format(format_dictionary)
with c5:
st.pyplot(fig)
c7, c8, c9 = st.columns([1, 10, 1])
with c8:
st.table(df)
# 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) |