Nash-pAnDiTa commited on
Commit
ee1dc7d
·
verified ·
1 Parent(s): 6bf9f6c

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +11 -1
app.py CHANGED
@@ -24,8 +24,9 @@ def update_transcriptions(df, dataset, token,dataset_link):
24
  Update the transcriptions in the dataset and push it back to the Hugging Face Hub.
25
  """
26
  # Convert DataFrame back to Dataset
 
27
  updated_dataset = Dataset.from_pandas(df)
28
-
29
  # print(updated_dataset)
30
  # print(dataset)
31
 
@@ -74,6 +75,15 @@ def main():
74
  original_df.loc[original_df["index"] == row["index"], "transcription"] = row["transcription"]
75
 
76
  return "update Successful"
 
 
 
 
 
 
 
 
 
77
 
78
  def submit_changes(df, token,dataset_link):
79
  """
 
24
  Update the transcriptions in the dataset and push it back to the Hugging Face Hub.
25
  """
26
  # Convert DataFrame back to Dataset
27
+ df = delete_empty_rows(df)
28
  updated_dataset = Dataset.from_pandas(df)
29
+
30
  # print(updated_dataset)
31
  # print(dataset)
32
 
 
75
  original_df.loc[original_df["index"] == row["index"], "transcription"] = row["transcription"]
76
 
77
  return "update Successful"
78
+
79
+ def delete_empty_rows(updated_df):
80
+ """
81
+ Delete rows marked for removal from the dataset.
82
+ """
83
+ # Remove rows where transcription is empty or manually marked
84
+ updated_df = updated_df.dropna(subset=["transcription"])
85
+ updated_df = updated_df[updated_df["transcription"].str.strip() != ""]
86
+ return updated_df
87
 
88
  def submit_changes(df, token,dataset_link):
89
  """