File size: 12,226 Bytes
1e0e995 ca33833 1e0e995 30b4e17 672a4a1 1e0e995 ca33833 6f76a2b 1e0e995 6f76a2b 1e0e995 6f76a2b 1e0e995 a17b4cf 68daa98 68835bd 68daa98 1e0e995 28f514c e1d2a9f 28f514c 876e883 28f514c 1e0e995 28f514c bf170b4 68daa98 68835bd ca33833 6f76a2b 1e0e995 8f06cde 91829c7 30b4e17 c48e316 dd21437 30b4e17 dd21437 1e0e995 6f76a2b 91829c7 1e0e995 30b4e17 dd21437 30b4e17 e1d2a9f 53dc094 e1d2a9f 30b4e17 e1d2a9f 672a4a1 30b4e17 9a74b5c dd21437 c48e316 9a74b5c dd21437 9a74b5c dd21437 30b4e17 8f06cde 28f514c |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 |
# 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 utils.target_classifier import load_targetClassifier, target_classification
import logging
logger = logging.getLogger(__name__)
from utils.config import get_classifier_params
from io import BytesIO
import xlsxwriter
import plotly.express as px
from pandas.api.types import (
is_categorical_dtype,
is_datetime64_any_dtype,
is_numeric_dtype,
is_object_dtype,
is_list_like)
# Declare all the necessary variables
classifier_identifier = 'target'
params = get_classifier_params(classifier_identifier)
## Labels dictionary ###
_lab_dict = {
'NEGATIVE':'NO TARGET INFO',
'TARGET':'TARGET',
}
@st.cache_data
def to_excel(df,hits):
# df['Target Validation'] = 'No'
# df['Netzero Validation'] = 'No'
# df['GHG Validation'] = 'No'
# df['Adapt-Mitig Validation'] = 'No'
# df['Sector'] = 'No'
len_df = len(df)
output = BytesIO()
writer = pd.ExcelWriter(output, engine='xlsxwriter')
df.to_excel(writer, index=False, sheet_name='rawdata')
hits = hits.drop(columns = ['Target Score','Netzero Score','GHG Score'])
hits.to_excel(writer,index=False,sheet_name = 'Target')
workbook = writer.book
# worksheet = writer.sheets['Sheet1']
# worksheet.data_validation('L2:L{}'.format(len_df),
# {'validate': 'list',
# 'source': ['No', 'Yes', 'Discard']})
# worksheet.data_validation('M2:L{}'.format(len_df),
# {'validate': 'list',
# 'source': ['No', 'Yes', 'Discard']})
# worksheet.data_validation('N2:L{}'.format(len_df),
# {'validate': 'list',
# 'source': ['No', 'Yes', 'Discard']})
# worksheet.data_validation('O2:L{}'.format(len_df),
# {'validate': 'list',
# 'source': ['No', 'Yes', 'Discard']})
# worksheet.data_validation('P2:L{}'.format(len_df),
# {'validate': 'list',
# 'source': ['No', 'Yes', 'Discard']})
writer.save()
processed_data = output.getvalue()
return processed_data
def app():
### Main app code ###
with st.container():
if 'key0' in st.session_state:
df = st.session_state.key0
#load Classifier
classifier = load_targetClassifier(classifier_name=params['model_name'])
st.session_state['{}_classifier'.format(classifier_identifier)] = classifier
if len(df) > 100:
warning_msg = ": This might take sometime, please sit back and relax."
else:
warning_msg = ""
df = target_classification(haystack_doc=df,
threshold= params['threshold'])
st.session_state.key1 = df
def target_display():
if 'key1' in st.session_state:
df = st.session_state.key1
st.caption(""" **{}** is splitted into **{}** paragraphs/text chunks."""\
.format(os.path.basename(st.session_state['filename']),
len(df)))
hits = df[df['Target Label'] == 'TARGET']
range_val = min(5,len(hits))
if range_val !=0:
# collecting some statistics
count_target = sum(hits['Target Label'] == 'TARGET')
count_netzero = sum(hits['Netzero Label'] == 'NETZERO TARGET')
count_ghg = sum(hits['GHG Label'] == 'GHG')
count_transport = sum([True if 'Transport' in x else False
for x in hits['Sector Label']])
c1, c2 = st.columns([1,1])
with c1:
st.write('**Target Paragraphs**: `{}`'.format(count_target))
st.write('**NetZero Related Paragraphs**: `{}`'.format(count_netzero))
with c2:
st.write('**GHG Target Related Paragraphs**: `{}`'.format(count_ghg))
st.write('**Transport Related Paragraphs**: `{}`'.format(count_transport))
# st.write('-------------------')
hits = hits.sort_values(by=['Target Score'], ascending=False)
hits = hits.reset_index(drop=True)
# netzerohit = hits[hits['Netzero Label'] == 'NETZERO']
# if not netzerohit.empty:
# netzerohit = netzerohit.sort_values(by = ['Netzero Score'], ascending = False)
# # st.write('-------------------')
# # st.markdown("###### Netzero paragraph ######")
# st.write('**Netzero paragraph** `page {}`: {}'.format(netzerohit.iloc[0]['page'],
# netzerohit.iloc[0]['text'].replace("\n", " ")))
# st.write("")
# else:
# st.info("🤔 No Netzero paragraph found")
# # st.write("**Result {}** `page {}` (Relevancy Score: {:.2f})'".format(i+1,hits.iloc[i]['page'],hits.iloc[i]['Relevancy'])")
# st.write('-------------------')
# st.markdown("###### Top few Target Classified paragraph/text results ######")
# range_val = min(5,len(hits))
# for i in range(range_val):
# # the page number reflects the page that contains the main paragraph
# # according to split limit, the overlapping part can be on a separate page
# st.write('**Result {}** (Relevancy Score: {:.2f}): `page {}`, `Sector: {}`,\
# `GHG: {}`, `Adapt-Mitig :{}`'\
# .format(i+1,hits.iloc[i]['Relevancy'],
# hits.iloc[i]['page'], hits.iloc[i]['Sector Label'],
# hits.iloc[i]['GHG Label'],hits.iloc[i]['Adapt-Mitig Label']))
# st.write("\t Text: \t{}".format(hits.iloc[i]['text'].replace("\n", " ")))
# hits = hits.reset_index(drop =True)
st.write('----------------')
st.title("Auto Filter Dataframes in Streamlit")
filter_dataframe(hits)
# filtered_df = filtered_df[filtered_df.keep == True]
# st.write('Explore the data')
# AgGrid(hits)
df_xlsx = to_excel(df,st.session_state['target_hits'])
with st.sidebar:
st.write('-------------')
st.download_button(label='📥 Download Result',
data=df_xlsx ,
file_name= os.path.splitext(os.path.basename(st.session_state['filename']))[0]+'.xlsx')
# st.write(
# """This app accomodates the blog [here](https://blog.streamlit.io/auto-generate-a-dataframe-filtering-ui-in-streamlit-with-filter_dataframe/)
# and walks you through one example of how the Streamlit
# Data Science Team builds add-on functions to Streamlit.
# """
# )
def filter_dataframe(df: pd.DataFrame) -> pd.DataFrame:
"""
Adds a UI on top of a dataframe to let viewers filter columns
Args:
df (pd.DataFrame): Original dataframe
Returns:
pd.DataFrame: Filtered dataframe
"""
modify = st.checkbox("Add filters")
if not modify:
st.session_state['target_hits'] = df
return
df = df.copy()
# Try to convert datetimes into a standard format (datetime, no timezone)
# for col in df.columns:
# if is_object_dtype(df[col]):
# try:
# df[col] = pd.to_datetime(df[col])
# except Exception:
# pass
# if is_datetime64_any_dtype(df[col]):
# df[col] = df[col].dt.tz_localize(None)
modification_container = st.container()
with modification_container:
to_filter_columns = st.multiselect("Filter dataframe on", df.columns)
for column in to_filter_columns:
left, right = st.columns((1, 20))
left.write("↳")
# Treat columns with < 10 unique values as categorical
if is_list_like(df[column]):
list_vals = set(x for lst in df[column].tolist() for x in lst)
user_multi_input = right.multiselect(
f"Values for {column}",
list_vals,
default=list_vals,
)
df = df[df[column].str.contains(user_multi_input)]
elif is_categorical_dtype(df[column]) or df[column].nunique() < 10:
user_cat_input = right.multiselect(
f"Values for {column}",
df[column].unique(),
default=list(df[column].unique()),
)
df = df[df[column].isin(user_cat_input)]
elif is_numeric_dtype(df[column]):
_min = float(df[column].min())
_max = float(df[column].max())
step = (_max - _min) / 100
user_num_input = right.slider(
f"Values for {column}",
_min,
_max,
(_min, _max),
step=step,
)
df = df[df[column].between(*user_num_input)]
# df[df[column].between(*user_num_input)]
# elif is_datetime64_any_dtype(df[column]):
# user_date_input = right.date_input(
# f"Values for {column}",
# value=(
# df[column].min(),
# df[column].max(),
# ),
# )
# if len(user_date_input) == 2:
# user_date_input = tuple(map(pd.to_datetime, user_date_input))
# start_date, end_date = user_date_input
# df = df.loc[df[column].between(start_date, end_date)]
else:
user_text_input = right.text_input(
f"Substring or regex in {column}",
)
if user_text_input:
df = df[df[column].str.contains(user_text_input)]
df['keep'] = True
df = st.data_editor(
df,
column_config={
"keep": st.column_config.CheckboxColumn(
help="Select which rows to keep",
default=False,
)
},
disabled=list(set(df.columns) - {'keep'}),
hide_index=True,
)
st.session_state['target_hits'] = df
return
# df = pd.read_csv(
# "https://raw.githubusercontent.com/mcnakhaee/palmerpenguins/master/palmerpenguins/data/penguins.csv"
# )
# else:
# st.info("🤔 No Targets found")
# count_df = df['Target Label'].value_counts()
# count_df = count_df.rename('count')
# count_df = count_df.rename_axis('Target Label').reset_index()
# count_df['Label_def'] = count_df['Target Label'].apply(lambda x: _lab_dict[x])
# st.plotly_chart(fig,use_container_width= True)
# count_netzero = sum(hits['Netzero Label'] == 'NETZERO')
# count_ghg = sum(hits['GHG Label'] == 'LABEL_2')
# count_economy = sum([True if 'Economy-wide' in x else False
# for x in hits['Sector Label']])
# # excel part
# temp = df[df['Relevancy']>threshold]
# df['Validation'] = 'No'
# df_xlsx = to_excel(df)
# st.download_button(label='📥 Download Current Result',
# data=df_xlsx ,
# file_name= 'file_target.xlsx') |