Skip to content

Remove Google Drive URL in spider dataset #4410

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 26, 2022
Merged

Remove Google Drive URL in spider dataset #4410

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion datasets/spider/dataset_infos.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"spider": {"description": "Spider is a large-scale complex and cross-domain semantic parsing and text-toSQL dataset annotated by 11 college students\n", "citation": "@article{yu2018spider,\n title={Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task},\n author={Yu, Tao and Zhang, Rui and Yang, Kai and Yasunaga, Michihiro and Wang, Dongxu and Li, Zifan and Ma, James and Li, Irene and Yao, Qingning and Roman, Shanelle and others},\n journal={arXiv preprint arXiv:1809.08887},\n year={2018}\n}\n", "homepage": "https://yale-lily.github.io/spider", "license": "CC BY-SA 4.0", "features": {"db_id": {"dtype": "string", "id": null, "_type": "Value"}, "query": {"dtype": "string", "id": null, "_type": "Value"}, "question": {"dtype": "string", "id": null, "_type": "Value"}, "query_toks": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "query_toks_no_value": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "question_toks": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}}, "post_processed": null, "supervised_keys": null, "builder_name": "spider", "config_name": "spider", "version": {"version_str": "1.0.0", "description": null, "major": 1, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 4743822, "num_examples": 7000, "dataset_name": "spider"}, "validation": {"name": "validation", "num_bytes": 682126, "num_examples": 1034, "dataset_name": "spider"}}, "download_checksums": {"https://drive.google.com/uc?export=download&id=1_AckYkinAnhqmRQtGsQgUKAnTHxxX5J0": {"num_bytes": 99736136, "checksum": "5ddff97bb1d421282c593e8d30ce0ce107270f4dd4a21d60eba4bf287d5956b1"}}, "download_size": 99736136, "post_processing_size": null, "dataset_size": 5425948, "size_in_bytes": 105162084}}
{"spider": {"description": "Spider is a large-scale complex and cross-domain semantic parsing and text-toSQL dataset annotated by 11 college students\n", "citation": "@article{yu2018spider,\n title={Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task},\n author={Yu, Tao and Zhang, Rui and Yang, Kai and Yasunaga, Michihiro and Wang, Dongxu and Li, Zifan and Ma, James and Li, Irene and Yao, Qingning and Roman, Shanelle and others},\n journal={arXiv preprint arXiv:1809.08887},\n year={2018}\n}\n", "homepage": "https://yale-lily.github.io/spider", "license": "CC BY-SA 4.0", "features": {"db_id": {"dtype": "string", "id": null, "_type": "Value"}, "query": {"dtype": "string", "id": null, "_type": "Value"}, "question": {"dtype": "string", "id": null, "_type": "Value"}, "query_toks": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "query_toks_no_value": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}, "question_toks": {"feature": {"dtype": "string", "id": null, "_type": "Value"}, "length": -1, "id": null, "_type": "Sequence"}}, "post_processed": null, "supervised_keys": null, "task_templates": null, "builder_name": "spider", "config_name": "spider", "version": {"version_str": "1.0.0", "description": null, "major": 1, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 4743786, "num_examples": 7000, "dataset_name": "spider"}, "validation": {"name": "validation", "num_bytes": 682090, "num_examples": 1034, "dataset_name": "spider"}}, "download_checksums": {"https://huggingface.co/datasets/spider/resolve/main/data/spider.zip": {"num_bytes": 99736136, "checksum": "5ddff97bb1d421282c593e8d30ce0ce107270f4dd4a21d60eba4bf287d5956b1"}}, "download_size": 99736136, "post_processing_size": null, "dataset_size": 5425876, "size_in_bytes": 105162012}}
2 changes: 1 addition & 1 deletion datasets/spider/spider.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,7 @@

_LICENSE = "CC BY-SA 4.0"

_URL = "https://drive.google.com/uc?export=download&id=1_AckYkinAnhqmRQtGsQgUKAnTHxxX5J0"
_URL = "https://huggingface.co/datasets/spider/resolve/main/data/spider.zip"


class Spider(datasets.GeneratorBasedBuilder):
Expand Down