From 7e677472e02210918a64a2c0a1da95bab62adacd Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marcin=20W=C4=85troba?= <markowanga@gmail.com>
Date: Sun, 15 Jan 2023 09:20:30 +0100
Subject: [PATCH] download_dataset command
---
new_datasets/iterate_hf_dataset.py | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/new_datasets/iterate_hf_dataset.py b/new_datasets/iterate_hf_dataset.py
index a280237..5d8caf2 100644
--- a/new_datasets/iterate_hf_dataset.py
+++ b/new_datasets/iterate_hf_dataset.py
@@ -8,10 +8,10 @@ def iterate_dataset(dataset_path: str, dataset_name: Optional[str], cache_dir: s
dataset_dict = datasets.load_dataset(dataset_path, dataset_name if len(dataset_name) > 0 else None,
cache_dir=cache_dir)
dataset = dataset_dict[split_name]
- for it in dataset[:items]:
- print(it)
counter = 0
for it in dataset:
+ if items > counter:
+ print(it)
counter += 1
print(f'all_items {counter}')
--
GitLab