Spaces:
Runtime error
Runtime error
Gagan Bhatia
commited on
Commit
•
684ff8e
1
Parent(s):
e1f665f
Update process_data.py
Browse files- src/data/process_data.py +1 -0
src/data/process_data.py
CHANGED
@@ -10,6 +10,7 @@ def process_data(split='train'):
|
|
10 |
|
11 |
df = pd.read_csv('data/raw/{}.csv'.format(split))
|
12 |
df.columns = ['Unnamed: 0', 'input_text', 'output_text']
|
|
|
13 |
df.to_csv('data/processed/{}.csv'.format(split))
|
14 |
|
15 |
|
|
|
10 |
|
11 |
df = pd.read_csv('data/raw/{}.csv'.format(split))
|
12 |
df.columns = ['Unnamed: 0', 'input_text', 'output_text']
|
13 |
+
df = df.sample(frac=params['split'], replace=True, random_state=1)
|
14 |
df.to_csv('data/processed/{}.csv'.format(split))
|
15 |
|
16 |
|