FDSRashid commited on
Commit
cffe818
·
verified ·
1 Parent(s): d3d6de3

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +8 -0
app.py CHANGED
@@ -32,6 +32,14 @@ features = Features({'matn': Value('string'), 'taraf_ID': Value('string'), 'book
32
 
33
  dataset = load_dataset("FDSRashid/hadith_info", data_files = 'All_Matns.csv',token = Secret_token, features = features)
34
  matn_info = dataset['train'].to_pandas()
 
 
 
 
 
 
 
 
35
  isnad_info = load_dataset('FDSRashid/hadith_info',token = Secret_token, data_files = 'isnad_info.csv', split = 'train').to_pandas()
36
  isnad_info['Hadiths Cleaned'] = isnad_info['Hadiths'].apply(lambda x: [re.findall(pattern, string)[0].split("_") for string in x[1:-1].split(',')])
37
 
 
32
 
33
  dataset = load_dataset("FDSRashid/hadith_info", data_files = 'All_Matns.csv',token = Secret_token, features = features)
34
  matn_info = dataset['train'].to_pandas()
35
+ matn_info = matn_info.drop(97550)
36
+ matn_info = matn_info.drop(307206)
37
+ matn_info['taraf_ID'] = matn_info['taraf_ID'].replace('KeyAbsent', -1)
38
+
39
+
40
+ matn_info['taraf_ID'] = matn_info['taraf_ID'].astype(int)
41
+
42
+
43
  isnad_info = load_dataset('FDSRashid/hadith_info',token = Secret_token, data_files = 'isnad_info.csv', split = 'train').to_pandas()
44
  isnad_info['Hadiths Cleaned'] = isnad_info['Hadiths'].apply(lambda x: [re.findall(pattern, string)[0].split("_") for string in x[1:-1].split(',')])
45