Spaces:
Sleeping
Sleeping
delete download_data file
Browse files- download_data.py +0 -36
download_data.py
DELETED
|
@@ -1,36 +0,0 @@
|
|
| 1 |
-
"""
|
| 2 |
-
Download corpus and embeddings from Google Drive
|
| 3 |
-
"""
|
| 4 |
-
import gdown
|
| 5 |
-
import os
|
| 6 |
-
from pathlib import Path
|
| 7 |
-
|
| 8 |
-
def download_data():
|
| 9 |
-
"""Download data files from Google Drive."""
|
| 10 |
-
|
| 11 |
-
# Create directory
|
| 12 |
-
Path('data_final/processed').mkdir(parents=True, exist_ok=True)
|
| 13 |
-
|
| 14 |
-
# Download corpus
|
| 15 |
-
if not os.path.exists('data_final/processed/corpus_with_embeddings.json'):
|
| 16 |
-
print("⏳ Downloading corpus...")
|
| 17 |
-
gdown.download(
|
| 18 |
-
id='1LmT3oEt_F4IccKKKqYk6-A7Yy6ipony5', # Replace with your Google Drive file ID
|
| 19 |
-
output='data_final/processed/corpus_with_embeddings.json',
|
| 20 |
-
quiet=False
|
| 21 |
-
)
|
| 22 |
-
print("✅ Corpus downloaded!")
|
| 23 |
-
|
| 24 |
-
# Download embeddings
|
| 25 |
-
if not os.path.exists('data_final/processed/embeddings.npy'):
|
| 26 |
-
print("⏳ Downloading embeddings...")
|
| 27 |
-
gdown.download(
|
| 28 |
-
id='1XG8_PsXFBjAVRET4pud_sklM_4iPPhdi', # Replace with your Google Drive file ID
|
| 29 |
-
output='data_final/processed/embeddings.npy',
|
| 30 |
-
quiet=False
|
| 31 |
-
)
|
| 32 |
-
print("✅ Embeddings downloaded!")
|
| 33 |
-
|
| 34 |
-
if __name__ == '__main__':
|
| 35 |
-
download_data()
|
| 36 |
-
print("✅ All data ready!")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|