File size: 20,709 Bytes
5fcdc9c
 
 
 
 
 
 
 
 
 
 
 
51cb4ac
5fcdc9c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51cb4ac
5fcdc9c
cf8f017
5fcdc9c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
da81802
51cb4ac
cbc61ac
31d86a5
 
 
 
85ac152
38da740
53c11ba
2d78e5f
31d86a5
53c11ba
31d86a5
3e3adae
85ac152
8b46865
38da740
a733616
31d86a5
e9ff044
fc60148
 
 
cfc1352
e9ff044
31d86a5
 
 
51cb4ac
5fcdc9c
 
 
 
 
 
 
 
 
 
14cf836
 
3aaa0cf
 
 
14cf836
3aaa0cf
9cf164b
51cb4ac
 
 
 
 
14cf836
 
 
 
5fcdc9c
 
 
 
 
 
 
 
 
 
 
51cb4ac
 
138e3ff
5fcdc9c
 
 
 
 
 
 
 
 
 
5106269
5fcdc9c
51cb4ac
 
 
138e3ff
5fcdc9c
21f0416
5fcdc9c
 
 
 
 
 
 
 
 
 
 
 
 
 
561f17b
 
 
5fcdc9c
561f17b
5fcdc9c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eae1e5f
8b4de75
 
 
 
 
 
6e3a8b1
8b4de75
5fcdc9c
 
 
 
 
0753339
5fcdc9c
0753339
 
 
5fcdc9c
 
 
 
 
 
 
51cb4ac
5fcdc9c
 
 
 
 
 
 
 
 
 
 
51cb4ac
 
0753339
51cb4ac
a4ae85b
b134874
baea0e2
0753339
228eaf8
51cb4ac
 
b134874
5fcdc9c
b134874
 
ab7f7b4
51cb4ac
 
 
 
 
5fcdc9c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2984573
 
d25e7b4
 
5fcdc9c
 
 
 
 
2287df6
5fcdc9c
 
 
 
2287df6
5fcdc9c
 
 
 
2287df6
5fcdc9c
 
 
 
2287df6
5fcdc9c
 
 
 
 
2287df6
 
5fcdc9c
 
 
 
 
2287df6
5fcdc9c
 
 
 
2287df6
5fcdc9c
 
 
 
2287df6
5fcdc9c
 
 
 
 
2287df6
5fcdc9c
 
 
 
 
2287df6
 
5fcdc9c
 
 
 
 
2287df6
5fcdc9c
 
 
 
 
2287df6
5fcdc9c
 
 
 
 
2287df6
5fcdc9c
 
 
 
 
2287df6
5fcdc9c
 
 
 
 
2287df6
 
5fcdc9c
 
 
 
 
2287df6
5fcdc9c
 
 
 
 
2287df6
5fcdc9c
 
 
 
 
2287df6
5fcdc9c
 
 
 
 
2287df6
5fcdc9c
 
 
 
 
2287df6
 
5fcdc9c
 
 
 
 
2287df6
5fcdc9c
 
 
 
 
2287df6
5fcdc9c
 
 
 
 
2287df6
5fcdc9c
 
 
 
 
2287df6
5fcdc9c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ab7f7b4
51cb4ac
 
 
b134874
 
51cb4ac
31d86a5
999ae97
 
ab7f7b4
 
 
 
 
 
03023e5
ab7f7b4
a1055ac
 
ab7f7b4
8988eea
ee973c9
ab7f7b4
76af97e
53c11ba
 
 
 
 
76af97e
 
a733616
 
240f632
31541f6
999ae97
 
 
 
 
b8ee3e0
 
 
 
 
 
 
999ae97
960ded6
 
 
 
999ae97
 
cfc4ee2
999ae97
 
 
 
 
cdad466
 
 
ea36de6
5fcdc9c
 
 
 
 
 
 
 
8252bd7
5fcdc9c
 
 
51cb4ac
c03bccd
51cb4ac
5fcdc9c
 
 
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
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
# import all packages
import requests
import streamlit as st
from sklearn.model_selection import StratifiedKFold
from sklearn.model_selection import train_test_split
from sklearn.model_selection import KFold
# tokenizer
from transformers import AutoTokenizer, DistilBertTokenizerFast
# sequence tagging model + training-related 
from transformers import DistilBertForTokenClassification, Trainer, TrainingArguments
import numpy as np
import pandas as pd
import torch
import json
import sys
import os
from sklearn.metrics import classification_report
from pandas import read_csv
from sklearn.linear_model import LogisticRegression
import sklearn.model_selection
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.pipeline import Pipeline, FeatureUnion
import math
from sklearn.metrics import accuracy_score
from sklearn.metrics import precision_recall_fscore_support
from sklearn.model_selection import train_test_split
import json
import re
import numpy as np 
import pandas as pd
import re
import nltk
nltk.download("punkt")
import string
from sklearn.model_selection import train_test_split
from transformers import AutoTokenizer, Trainer, TrainingArguments, AutoModelForSequenceClassification, AutoConfig
import torch
from torch.utils.data import TensorDataset, DataLoader, RandomSampler, SequentialSampler
import itertools
import json
import glob
from transformers import TextClassificationPipeline, TFAutoModelForSequenceClassification, AutoTokenizer
from transformers import pipeline
import pickle
import urllib.request  
import csv
import pdfplumber
import pathlib 
import shutil
import webbrowser
from streamlit.components.v1 import html
import streamlit.components.v1 as components
from PyPDF2 import PdfReader
from huggingface_hub import HfApi
import io
from datasets import load_dataset

import huggingface_hub
from huggingface_hub import Repository
from datetime import datetime
import pathlib as Path
from requests import get
import urllib.request


DATASET_REPO_URL = "https://huggingface.co/datasets/Seetha/visual_files/raw/main/level2.json"
DATA_FILENAME = "level2.json"
#DATA_FILE = os.path.join(DATASET_REPO_URL, DATA_FILENAME)

# feedback_file = Path("https://huggingface.co/datasets/Seetha/visual_files/") / f"level2.json"
st.write(DATASET_REPO_URL)

HF_TOKEN = os.environ.get("HF_TOKEN")

# repo = Repository(
#     local_dir="huggingface-hub", clone_from=DATASET_REPO_URL, use_auth_token=HF_TOKEN
# )
#dataset = load_dataset('Seetha/visual_files')

# print("is none?", HF_TOKEN is None)

# print("hfh", huggingface_hub.__version__)


def main():

  st.title("Text to Causal Knowledge Graph")
  st.sidebar.title("Please upload your text documents in one file here:")
  k=2
  seed = 1
  k1= 5
  text_list = []
  causal_sents = []

  uploaded_file = None
  try:
      uploaded_file = st.sidebar.file_uploader("Choose a file", type = "pdf")
  except:
      uploaded_file = PdfReader('sample_anno.pdf')
      st.error("Please upload your own PDF to be analyzed")

  if uploaded_file is not None:
    reader = PdfReader(uploaded_file)
    for page in reader.pages:
      text = page.extract_text()
      text_list.append(text)
  else:
     st.error("Please upload your own PDF to be analyzed")
     st.stop()
      
  text_list_final = [x.replace('\n', '') for x in text_list]
  text_list_final = re.sub('"', '', str(text_list_final))
  
  sentences = nltk.sent_tokenize(text_list_final)
  
  result =[]
  for i in sentences:
    result1 = i.lower()
    result2 = re.sub(r'[^\w\s]','',result1)
    result.append(result2)
    
  tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased") #bert-base-uncased
  
  model_path = "checkpoint-2850"
  
  model = AutoModelForSequenceClassification.from_pretrained(model_path,id2label={0:'non-causal',1:'causal'})

  pipe1 = pipeline("text-classification", model=model,tokenizer=tokenizer)
  for sent in result:
    pred = pipe1(sent)
    for lab in pred:
        if lab['label'] == 'causal': #causal
            causal_sents.append(sent)

  model_name = "distilbert-base-cased"
  tokenizer = DistilBertTokenizerFast.from_pretrained(model_name)
  
  
  
  model_path1 = "DistilBertforTokenclassification"
  
  model = DistilBertForTokenClassification.from_pretrained(model_path1) #len(unique_tags),, num_labels= 7, , id2label={0:'CT',1:'E',2:'C',3:'O'}
  pipe = pipeline('ner', model=model, tokenizer=tokenizer,aggregation_strategy='simple') #grouped_entities=True

  sentence_pred = []
  class_list = []
  entity_list = []
  for k in causal_sents:
    pred= pipe(k)
    #st.write(pred)
    for i in pred:
      
      sentence_pred.append(k)
      class_list.append(i['word'])
      entity_list.append(i['entity_group'])
  
  filename = 'Checkpoint-classification.sav'
  loaded_model = pickle.load(open(filename, 'rb'))
  loaded_vectorizer = pickle.load(open('vectorizefile_classification.pickle', 'rb'))

  pipeline_test_output = loaded_vectorizer.transform(class_list)
  predicted = loaded_model.predict(pipeline_test_output)
  pred1 = predicted
  level0 = []
  count =0
  for i in predicted:
    if i == 3:
      level0.append('Non-Performance')
      count +=1
    else:
      level0.append('Performance')
      count +=1

  list_pred = {0: 'Customers',1:'Employees',2:'Investors',3:'Non-performance',4:'Society',5:'Unclassified'}
  pred_val = [list_pred[i] for i in pred1]

  #print('count',count)
  for ind,(sent,preds) in enumerate(zip(class_list,pred_val)):
      if 'customers' in sent or 'client' in sent or 'consumer' in sent or 'user' in sent:
          pred_val[ind] = 'Customers'
      elif 'investor' in sent or 'finance' in sent or 'shareholder' in sent or 'stockholder' in sent or 'owners' in sent:
          pred_val[ind] = 'Investors'
      elif 'employee' in sent or 'worker' in sent or 'staff' in sent:
          pred_val[ind] = 'Employees'
      elif 'society' in sent or 'societal' in sent or 'social responsib*' in sent or 'social performance' in sent or 'community' in sent:
          pred_val[ind] = 'Society'

  sent_id, unique = pd.factorize(sentence_pred)

  final_list = pd.DataFrame(
      {'Id': sent_id,
       'Fullsentence': sentence_pred,
       'Component': class_list,
       'causeOrEffect': entity_list,
       'Labellevel1': level0,
       'Labellevel2': pred_val
      })
  s = final_list['Component'].shift(-1)
  m = s.str.startswith('##', na=False)
  final_list.loc[m, 'Component'] += (' ' + s[m])


  final_list1 = final_list[~final_list['Component'].astype(str).str.startswith('##')]
  
  li = []
  uni = final_list1['Id'].unique()
  for i in uni:
    df_new = final_list1[final_list1['Id'] == i]
    uni1 = df_new['Id'].unique()
    if 'E' not in df_new.values:
      li.append(uni1)
  out = np.concatenate(li).ravel()
  li_pan = pd.DataFrame(out,columns=['Id'])
  df3 = pd.merge(final_list1, li_pan[['Id']], on='Id', how='left', indicator=True) \
              .query("_merge == 'left_only'") \
              .drop("_merge",axis=1) 
  
  #df = df3.groupby(['Id','Fullsentence','causeOrEffect', 'Labellevel1', 'Labellevel2'])['Component'].apply(', '.join).reset_index()
  #st.write(df)

  #df = df3
  df3["causeOrEffect"].replace({"C": "cause", "E": "effect"}, inplace=True)
  df_final = df3[df3['causeOrEffect'] != 'CT'] 
  df3['New string'] = df_final['Component'].replace(r'[##]+', ' ', regex=True)

  df_final = df_final.drop("Component",axis=1)
  df_final.insert(2, "Component", df3['New string'], True)

  df_final1 = df_final[df_final['Component'].str.split().str.len().gt(1)]
    #st.write(df_final[df_final['Component'].str.len() != 1])
  #df_final1.to_csv('predictions.csv')
  
#   buffer = io.BytesIO()
#   with pd.ExcelWriter(buffer, engine="xlsxwriter") as writer:
#     df_final.to_excel(writer, sheet_name="Sheet1", index=False)
#     writer.close()
  
  count_NP_NP = 0
  count_NP_investor = 0
  count_NP_customer = 0
  count_NP_employees = 0
  count_NP_society = 0

  count_inv_np = 0
  count_inv_investor = 0
  count_inv_customer = 0
  count_inv_employee = 0
  count_inv_society = 0

  count_cus_np = 0
  count_cus_investor = 0
  count_cus_customer = 0
  count_cus_employee = 0
  count_cus_society = 0

  count_emp_np = 0
  count_emp_investor = 0
  count_emp_customer = 0
  count_emp_employee = 0
  count_emp_society = 0

  count_soc_np = 0
  count_soc_investor = 0
  count_soc_customer = 0
  count_soc_employee = 0
  count_soc_society = 0
  for i in range(0,df_final['Id'].max()):
    j = df_final.loc[df_final['Id'] == i]
    cause_tab = j.loc[j['causeOrEffect'] == 'cause']
    effect_tab = j.loc[j['causeOrEffect'] == 'effect']
    cause_coun_NP = (cause_tab.Labellevel2 == 'Non-performance').sum()
    effect_coun_NP = (effect_tab.Labellevel2 == 'Non-performance').sum()

    if (cause_coun_NP > 0) and (effect_coun_NP > 0):
        count_NP = cause_coun_NP if cause_coun_NP >= effect_coun_NP else effect_coun_NP
    else:
        count_NP = 0
    effect_NP_inv = (effect_tab.Labellevel2 == 'Investors').sum()
    if (cause_coun_NP > 0) and (effect_NP_inv > 0):
        count_NP_inv = cause_coun_NP if cause_coun_NP >= effect_NP_inv else effect_NP_inv
    else:
        count_NP_inv = 0
    effect_NP_cus = (effect_tab.Labellevel2 == 'Customers').sum()
    if (cause_coun_NP > 0) and (effect_NP_cus > 0):
        count_NP_cus = cause_coun_NP if cause_coun_NP >= effect_NP_cus else effect_NP_cus
    else:
        count_NP_cus = 0
    effect_NP_emp = (effect_tab.Labellevel2 == 'Employees').sum()
    if (cause_coun_NP > 0) and (effect_NP_emp > 0):
        count_NP_emp = cause_coun_NP if cause_coun_NP >= effect_NP_emp else effect_NP_emp
    else:
        count_NP_emp = 0
    effect_NP_soc = (effect_tab.Labellevel2 == 'Society').sum()
    if (cause_coun_NP > 0) and (effect_NP_soc > 0):
        count_NP_soc = cause_coun_NP if cause_coun_NP >= effect_NP_soc else effect_NP_soc
    else:
        count_NP_soc = 0

    cause_coun_inv = (cause_tab.Labellevel2 == 'Investors').sum()
    effect_coun_inv = (effect_tab.Labellevel2 == 'Non-performance').sum()
    if (cause_coun_inv > 0) and (effect_coun_inv > 0):
        count_NP_inv = cause_coun_inv if cause_coun_inv >= effect_coun_inv else effect_coun_inv
    else:
        count_NP_inv = 0

    effect_inv_inv = (effect_tab.Labellevel2 == 'Investors').sum()
    if (cause_coun_inv > 0) and (effect_inv_inv > 0):
        count_inv_inv = cause_coun_inv if cause_coun_inv >= effect_inv_inv else effect_inv_inv
    else:
        count_inv_inv = 0
    effect_inv_cus = (effect_tab.Labellevel2 == 'Customers').sum()
    if (cause_coun_inv > 0) and (effect_inv_cus > 0):
        count_inv_cus = cause_coun_inv if cause_coun_inv >= effect_inv_cus else effect_inv_cus
    else:
        count_inv_cus = 0
    effect_inv_emp = (effect_tab.Labellevel2 == 'Employees').sum()
    if (cause_coun_inv > 0) and (effect_inv_emp > 0):
        count_inv_emp = cause_coun_inv if cause_coun_inv >= effect_inv_emp else effect_inv_emp
    else:
        count_inv_emp = 0

    effect_inv_soc = (effect_tab.Labellevel2 == 'Society').sum()
    if (cause_coun_inv > 0) and (effect_inv_soc > 0):
        count_inv_soc = cause_coun_inv if cause_coun_inv >= effect_inv_soc else effect_inv_soc
    else:
        count_inv_soc = 0

    cause_coun_cus = (cause_tab.Labellevel2 == 'Customers').sum()
    effect_coun_cus = (effect_tab.Labellevel2 == 'Non-performance').sum()
    if (cause_coun_cus > 0) and (effect_coun_cus > 0):
        count_NP_cus = cause_coun_cus if cause_coun_cus >= effect_coun_cus else effect_coun_cus
    else:
        count_NP_cus = 0

    effect_cus_inv = (effect_tab.Labellevel2 == 'Investors').sum()
    if (cause_coun_cus > 0) and (effect_cus_inv > 0):
        count_cus_inv = cause_coun_cus if cause_coun_cus >= effect_cus_inv else effect_cus_inv
    else:
        count_cus_inv = 0

    effect_cus_cus = (effect_tab.Labellevel2 == 'Customers').sum()
    if (cause_coun_cus > 0) and (effect_cus_cus > 0):
        count_cus_cus = cause_coun_cus if cause_coun_cus >= effect_cus_cus else effect_cus_cus
    else:
        count_cus_cus = 0

    effect_cus_emp = (effect_tab.Labellevel2 == 'Employees').sum()
    if (cause_coun_cus > 0) and (effect_cus_emp > 0):
        count_cus_emp = cause_coun_cus if cause_coun_cus >= effect_cus_emp else effect_cus_emp
    else:
        count_cus_emp = 0

    effect_cus_soc = (effect_tab.Labellevel2 == 'Society').sum()
    if (cause_coun_cus > 0) and (effect_cus_soc > 0):
        count_cus_soc = cause_coun_cus if cause_coun_cus >= effect_cus_soc else effect_cus_soc
    else:
        count_cus_soc = 0

    cause_coun_emp = (cause_tab.Labellevel2 == 'Employees').sum()
    effect_coun_emp = (effect_tab.Labellevel2 == 'Non-performance').sum()
    if (cause_coun_emp > 0) and (effect_coun_emp > 0):
        count_NP_emp = cause_coun_emp if cause_coun_emp >= effect_coun_emp else effect_coun_emp
    else:
        count_NP_emp = 0

    effect_emp_inv = (effect_tab.Labellevel2 == 'Investors').sum()
    if (cause_coun_emp > 0) and (effect_emp_inv > 0):
        count_emp_inv = cause_coun_emp if cause_coun_emp >= effect_emp_inv else effect_emp_inv
    else:
        count_emp_inv = 0

    effect_emp_cus = (effect_tab.Labellevel2 == 'Customers').sum()
    if (cause_coun_emp > 0) and (effect_emp_cus > 0):
        count_emp_cus = cause_coun_emp if cause_coun_emp >= effect_emp_cus else effect_emp_cus
    else:
        count_emp_cus = 0

    effect_emp_emp = (effect_tab.Labellevel2 == 'Employees').sum()
    if (cause_coun_emp > 0) and (effect_emp_emp > 0):
        count_emp_emp = cause_coun_emp if cause_coun_emp >= effect_emp_emp else effect_emp_emp
    else:
        count_emp_emp = 0

    effect_emp_soc = (effect_tab.Labellevel2 == 'Society').sum()
    if (cause_coun_emp > 0) and (effect_emp_soc > 0):
        count_emp_soc = cause_coun_emp if cause_coun_emp >= effect_emp_soc else effect_emp_soc
    else:
        count_emp_soc = 0

    cause_coun_soc = (cause_tab.Labellevel2 == 'Society').sum()
    effect_coun_soc = (effect_tab.Labellevel2 == 'Non-performance').sum()
    if (cause_coun_soc > 0) and (effect_coun_soc > 0):
        count_NP_soc = cause_coun_soc if cause_coun_soc >= effect_coun_soc else effect_coun_soc
    else:
        count_NP_soc = 0

    effect_soc_inv = (effect_tab.Labellevel2 == 'Investors').sum()
    if (cause_coun_soc > 0) and (effect_soc_inv > 0):
        count_soc_inv = cause_coun_soc if cause_coun_soc >= effect_soc_inv else effect_soc_inv
    else:
        count_soc_inv = 0

    effect_soc_cus = (effect_tab.Labellevel2 == 'Customers').sum()
    if (cause_coun_soc > 0) and (effect_soc_cus > 0):
        count_soc_cus = cause_coun_soc if cause_coun_soc >= effect_soc_cus else effect_soc_cus
    else:
        count_soc_cus = 0

    effect_soc_emp = (effect_tab.Labellevel2 == 'Employees').sum()
    if (cause_coun_soc > 0) and (effect_soc_emp > 0):
        count_soc_emp = cause_coun_soc if cause_coun_soc >= effect_soc_emp else effect_soc_emp
    else:
        count_soc_emp = 0

    effect_soc_soc = (effect_tab.Labellevel2 == 'Society').sum()
    if (cause_coun_soc > 0) and (effect_soc_soc > 0):
        count_soc_soc = cause_coun_soc if cause_coun_soc >= effect_soc_soc else effect_soc_soc
    else:
        count_soc_soc = 0

    count_NP_NP = count_NP_NP + count_NP
    count_NP_investor = count_NP_investor + count_NP_inv
    count_NP_customer = count_NP_customer + count_NP_cus
    count_NP_employees = count_NP_employees + count_NP_emp
    count_NP_society = count_NP_society + count_NP_soc

    count_inv_np = count_inv_np + count_NP_inv
    count_inv_investor = count_inv_investor + count_inv_inv
    count_inv_customer = count_inv_customer + count_inv_cus
    count_inv_employee = count_inv_employee + count_inv_emp
    count_inv_society = count_inv_society + count_inv_soc

    count_cus_np = count_cus_np + count_NP_cus
    count_cus_investor = count_cus_investor + count_cus_inv
    count_cus_customer = count_cus_customer + count_cus_cus
    count_cus_employee = count_cus_employee + count_cus_emp
    count_cus_society = count_cus_society + count_cus_soc

    count_emp_np = count_emp_np + count_NP_emp
    count_emp_investor = count_emp_investor + count_emp_inv
    count_emp_customer = count_emp_customer + count_emp_cus
    count_emp_employee = count_emp_employee + count_emp_emp
    count_emp_society = count_emp_society + count_emp_soc

    count_soc_np = count_soc_np + count_NP_soc
    count_soc_investor = count_soc_investor + count_soc_inv
    count_soc_customer = count_soc_customer + count_soc_cus
    count_soc_employee = count_soc_employee + count_soc_emp
    count_soc_society = count_soc_society + count_soc_soc
    
    df_tab = pd.DataFrame(columns = ['Non-performance', 'Investors', 'Customers', 'Employees', 'Society'],index=['Non-performance', 'Investors', 'Customers', 'Employees', 'Society'], dtype=object)
    
    df_tab.loc['Non-performance'] = [count_NP_NP, count_NP_investor, count_NP_customer, count_NP_employees, count_NP_society]
    df_tab.loc['Investors'] = [count_inv_np, count_inv_investor, count_inv_customer, count_inv_employee, count_inv_society]
    df_tab.loc['Customers'] = [count_cus_np, count_cus_investor, count_cus_customer, count_cus_employee, count_cus_society]
    df_tab.loc['Employees'] = [count_emp_np, count_emp_investor, count_emp_customer, count_emp_employee, count_emp_society]
    df_tab.loc['Society'] = [count_soc_np, count_soc_investor, count_soc_customer, count_soc_employee, count_soc_society]


#  df_tab = pd.DataFrame({
#      'Non-performance': [count_NP_NP, count_NP_investor, count_NP_customer, count_NP_employees, count_NP_society],
#      'Investors': [count_inv_np, count_inv_investor, count_inv_customer, count_inv_employee, count_inv_society],
#      'Customers': [count_cus_np, count_cus_investor, count_cus_customer, count_cus_employee, count_cus_society],
#      'Employees': [count_emp_np, count_emp_investor, count_emp_customer, count_emp_employee, count_emp_society],
#      'Society': [count_soc_np, count_soc_investor, count_soc_customer, count_soc_employee, count_soc_society]},
#       index=['Non-performance', 'Investors', 'Customers', 'Employees', 'Society'])

  #df_tab.to_csv('final_data.csv')
  
  buffer = io.BytesIO()
  with pd.ExcelWriter(buffer, engine="xlsxwriter") as writer:
    df_tab.to_excel(writer,sheet_name="count_result",index=False)
    df_final1.to_excel(writer,sheet_name="Detailed_results",index=False)
    writer.close()
  #df = pd.read_csv('final_data.csv', index_col=0)
#474-515
  # # Convert to JSON format
  json_data = []
  for row in df_tab.index:
    for col in df_tab.columns:
      json_data.append({
            'source': row,
            'target': col,
            'value': int(df_tab.loc[row, col])
        })
  # base_url = "https://huggingface.co/datasets/Seetha/visual_files/tree/main"
  # dataset = load_dataset(base_url, data_files='https://huggingface.co/datasets/Seetha/visual_files/blob/main/level2.json')

  #st.write(dataset)
  
  # Write JSON to file
  #with open(DATA_FILE, 'w') as f: #w+
  with urllib.request.urlopen(DATASET_REPO_URL) as response:
      data = response.read()
      with open(DATASET_REPO_URL,'w') as f:
          st.write(f)
          f.write(json.dump(json_data))
    #json.dump(json_data, f)
    #repo.push_to_hub()
  # commit_url = repo.push_to_hub()
  # st.write(commit_url)
  #dataset = load_dataset("seetha/visual_files")
  #repo.push_to_hub("level2.json")
  #   # repo.git_pull()
  #   # repo.git_add("ch.json")
  #   # repo.git_commit(commit_message="add ch.json :)")
  #   # repo.push()

  df_final1.to_csv('predictions.csv')
  csv_file = "predictions.csv"
  json_file = "detailedResults.json"

  # Open the CSV file and read the data
  with open(csv_file, "r") as f:
    csv_data = csv.DictReader(f)

    #   # Convert the CSV data to a list of dictionaries
    data_list = []
    for row in csv_data:
        data_list.append(dict(row))

  # # Convert the list of dictionaries to JSON
  json_data = json.dumps(data_list)

  # # Write the JSON data to a file
  # #with open("smalljson.json", "r+") as fi:
  #   #data = fi.read()
  #   #fi.seek(0)
  with open('detailedResults.json','w') as fi:
    #data = json.load(fi)
    fi.write(json_data)
  
  def convert_df(df):

  #IMPORTANT: Cache the conversion to prevent computation on every rerun

    return df.to_csv().encode('utf-8')

               

  csv1 = convert_df(df_final1.astype(str))
  csv2 = convert_df(df_tab.astype(str))

  with st.container():
    
    st.download_button(label="Download the result table",data=buffer,file_name="t2cg_outputs.xlsx",mime="application/vnd.ms-excel")
    

if __name__ == '__main__':
    main()