Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -14,22 +14,17 @@ import torch
|
|
14 |
import json
|
15 |
import sys
|
16 |
import os
|
17 |
-
#from datasets import load_metric
|
18 |
from sklearn.metrics import classification_report
|
19 |
from pandas import read_csv
|
20 |
from sklearn.linear_model import LogisticRegression
|
21 |
import sklearn.model_selection
|
22 |
from sklearn.feature_extraction.text import TfidfTransformer
|
23 |
from sklearn.feature_extraction.text import CountVectorizer
|
24 |
-
#from sklearn.naive_bayes import MultinomialNB
|
25 |
-
#from sklearn.model_selection import GridSearchCV
|
26 |
from sklearn.pipeline import Pipeline, FeatureUnion
|
27 |
import math
|
28 |
from sklearn.metrics import accuracy_score
|
29 |
from sklearn.metrics import precision_recall_fscore_support
|
30 |
from sklearn.model_selection import train_test_split
|
31 |
-
#from sklearn.metrics import Scorer
|
32 |
-
#from sklearn.metrics import SCORERS
|
33 |
import json
|
34 |
import re
|
35 |
import numpy as np
|
@@ -37,13 +32,8 @@ import pandas as pd
|
|
37 |
import re
|
38 |
import nltk
|
39 |
nltk.download("punkt")
|
40 |
-
#stemmer = nltk.SnowballStemmer("english")
|
41 |
-
#from nltk.corpus import stopwords
|
42 |
import string
|
43 |
from sklearn.model_selection import train_test_split
|
44 |
-
# import seaborn as sns
|
45 |
-
# from sklearn.metrics import confusion_matrix
|
46 |
-
# from sklearn.metrics import classification_report, ConfusionMatrixDisplay
|
47 |
from transformers import AutoTokenizer, Trainer, TrainingArguments, AutoModelForSequenceClassification, AutoConfig
|
48 |
import torch
|
49 |
from torch.utils.data import TensorDataset, DataLoader, RandomSampler, SequentialSampler
|
@@ -54,13 +44,7 @@ from transformers import TextClassificationPipeline, TFAutoModelForSequenceClass
|
|
54 |
from transformers import pipeline
|
55 |
import pickle
|
56 |
import urllib.request
|
57 |
-
# from sklearn.feature_extraction.text import TfidfTransformer
|
58 |
-
# from sklearn.feature_extraction.text import CountVectorizer
|
59 |
-
#from PyPDF2 import PdfReader
|
60 |
-
#from urllib.request import urlopen
|
61 |
-
#from tabulate import tabulate
|
62 |
import csv
|
63 |
-
#import gdown
|
64 |
import pdfplumber
|
65 |
import pathlib
|
66 |
import shutil
|
@@ -505,7 +489,7 @@ def main():
|
|
505 |
|
506 |
# Write JSON to file
|
507 |
#with open(DATA_FILE, 'w') as f: #w+
|
508 |
-
with
|
509 |
st.write(f)
|
510 |
f.write(json.dump(json_data))
|
511 |
#json.dump(json_data, f)
|
|
|
14 |
import json
|
15 |
import sys
|
16 |
import os
|
|
|
17 |
from sklearn.metrics import classification_report
|
18 |
from pandas import read_csv
|
19 |
from sklearn.linear_model import LogisticRegression
|
20 |
import sklearn.model_selection
|
21 |
from sklearn.feature_extraction.text import TfidfTransformer
|
22 |
from sklearn.feature_extraction.text import CountVectorizer
|
|
|
|
|
23 |
from sklearn.pipeline import Pipeline, FeatureUnion
|
24 |
import math
|
25 |
from sklearn.metrics import accuracy_score
|
26 |
from sklearn.metrics import precision_recall_fscore_support
|
27 |
from sklearn.model_selection import train_test_split
|
|
|
|
|
28 |
import json
|
29 |
import re
|
30 |
import numpy as np
|
|
|
32 |
import re
|
33 |
import nltk
|
34 |
nltk.download("punkt")
|
|
|
|
|
35 |
import string
|
36 |
from sklearn.model_selection import train_test_split
|
|
|
|
|
|
|
37 |
from transformers import AutoTokenizer, Trainer, TrainingArguments, AutoModelForSequenceClassification, AutoConfig
|
38 |
import torch
|
39 |
from torch.utils.data import TensorDataset, DataLoader, RandomSampler, SequentialSampler
|
|
|
44 |
from transformers import pipeline
|
45 |
import pickle
|
46 |
import urllib.request
|
|
|
|
|
|
|
|
|
|
|
47 |
import csv
|
|
|
48 |
import pdfplumber
|
49 |
import pathlib
|
50 |
import shutil
|
|
|
489 |
|
490 |
# Write JSON to file
|
491 |
#with open(DATA_FILE, 'w') as f: #w+
|
492 |
+
with open('https://huggingface.co/datasets/Seetha/visual_files/raw/main/level2.json','w') as f:
|
493 |
st.write(f)
|
494 |
f.write(json.dump(json_data))
|
495 |
#json.dump(json_data, f)
|