Skip to content

Commit 0bdff36

Browse files
committed
check gist vs local and update gist with new datasets
1 parent 11079bb commit 0bdff36

File tree

1 file changed

+12
-1
lines changed

1 file changed

+12
-1
lines changed

kaggle_json.py

Lines changed: 12 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -79,7 +79,18 @@ def unformat_bytes(string):
7979
# read true dataset sizes from json file
8080
try:
8181
datasets_size = json.loads(gist.files['datasets_size.json'].content)
82-
print(f"Read {len(datasets_size)} dataset sizes from gist")
82+
# raise Exception("Gist version of datasets_size.json is not used, please use the local file instead")
83+
if os.path.exists('datasets_size.json'):
84+
with open('datasets_size.json','r') as f:
85+
local_datasets_size = json.load(f)
86+
if datasets_size == local_datasets_size:
87+
print(f"Read {len(datasets_size)} dataset sizes from gist")
88+
elif len(datasets_size.keys()) <= len(local_datasets_size.keys()):
89+
print(f"Read {len(local_datasets_size)} dataset sizes from local file - gist version is different has {len(datasets_size)} entries")
90+
datasets_size = local_datasets_size
91+
else:
92+
raise Exception("Gist version of datasets_size.json has more entries than local file, please check the local file ")
93+
8394
except Exception as e:
8495
print(f'Could not read datasets_size.json from gist: {e}')
8596
if os.path.exists('datasets_size.json'):

0 commit comments

Comments
 (0)