Update dataset.cli.py
Browse files- dataset.cli.py +2 -2
dataset.cli.py
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
|
| 3 |
|
| 4 |
from argparse import ArgumentParser
|
| 5 |
-
from datasets import
|
| 6 |
|
| 7 |
|
| 8 |
|
|
@@ -16,7 +16,7 @@ parser = ArgumentParser(
|
|
| 16 |
if name == '__main__':
|
| 17 |
|
| 18 |
parser.add_argument('-p', '--remote_path')
|
| 19 |
-
parser.add_argument('-o', '--output_file')
|
| 20 |
|
| 21 |
dataset = load_dataset(parser.dataset_path)
|
| 22 |
text = ''.join(s for s in dataset['train']['text']).encode('ascii', 'ignore').decode('ascii')
|
|
|
|
| 2 |
|
| 3 |
|
| 4 |
from argparse import ArgumentParser
|
| 5 |
+
from datasets import load_dataset
|
| 6 |
|
| 7 |
|
| 8 |
|
|
|
|
| 16 |
if name == '__main__':
|
| 17 |
|
| 18 |
parser.add_argument('-p', '--remote_path')
|
| 19 |
+
parser.add_argument('-o', '--output_file', default='dataset.txt')
|
| 20 |
|
| 21 |
dataset = load_dataset(parser.dataset_path)
|
| 22 |
text = ''.join(s for s in dataset['train']['text']).encode('ascii', 'ignore').decode('ascii')
|