huggingface / datasets Public

* Create metric card for seqeval

Proposing metric card for seqeval

* Update README.md

* Update metrics/seqeval/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/seqeval/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/seqeval/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/seqeval/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/seqeval/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/seqeval/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/seqeval/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/seqeval/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/seqeval/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/seqeval/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/seqeval/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/seqeval/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Create a metric card for Competition MATH

Proposing metric card for Competition MATH

* Update metrics/competition_math/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/competition_math/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/competition_math/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/competition_math/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/competition_math/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/competition_math/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/competition_math/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/competition_math/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/competition_math/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Initial draft for the MetaShift Dataset.

* add dataset preprocessing and yield images.

* use selected classes.

* format code as required.

* add selected_classes as a config parameter.

* update fields in Dataset Card.

* add dataset tagset.

* Update datasets/metashift/README.md

Rename card name.

Co-authored-by: Mario Šaško <[email protected]>

* Update datasets/metashift/README.md

Naming for links and add point of contact info.

Co-authored-by: Mario Šaško <[email protected]>

* Update datasets/metashift/README.md

Fix extra whitespace.

Co-authored-by: Mario Šaško <[email protected]>

* Update datasets/metashift/README.md

Extra full stop removed.

Co-authored-by: Mario Šaško <[email protected]>

* Update datasets/metashift/README.md

Add bibtex tag.

Co-authored-by: Mario Šaško <[email protected]>

* Update datasets/metashift/metashift.py

Cleaner code changes.

Co-authored-by: Mario Šaško <[email protected]>

* Update datasets/metashift/metashift.py

Use os.path.join instead.

Co-authored-by: Mario Šaško <[email protected]>

* Update datasets/metashift/metashift.py

Use staticmethod, remove print statements.

Co-authored-by: Mario Šaško <[email protected]>

* Update datasets/metashift/metashift.py

Add task template.

Co-authored-by: Mario Šaško <[email protected]>

* Update datasets/metashift/metashift.py

add static method.

Co-authored-by: Mario Šaško <[email protected]>

* add annotation info.

* use multi-line comment.

* add minor fixes.

* add the generated meta-graphs to the card as images.

* usage of os.path.join for src_image_path.

* add config to generate metashift-attributes dataset.

* add config to expose image metadata.

* add contants as config parameters.

* add Dataset Usage section to cards.

* add name, dataset version to MetashiftConfig.

* add dataset_infos.json

* pass URLs to images and add alt tags.

* set default classes as in original repo.

* add dummy data.

* format code.

* update dataset structure section for config options.

* Update datasets/metashift/README.md

CI fixes.

Co-authored-by: Quentin Lhoest <[email protected]>

* Update datasets/metashift/README.md

Correct task categories.

Co-authored-by: Quentin Lhoest <[email protected]>

* Update datasets/metashift/metashift.py

Add encoding.

Co-authored-by: Quentin Lhoest <[email protected]>

* add contributions section

* Update datasets/metashift/README.md

Add paperswithcode id.

Co-authored-by: Mario Šaško <[email protected]>

* Update datasets/metashift/README.md

Correct sentence.

Co-authored-by: Mario Šaško <[email protected]>

* Update datasets/metashift/README.md

Co-authored-by: Mario Šaško <[email protected]>

* Update datasets/metashift/README.md

Co-authored-by: Mario Šaško <[email protected]>

* Update datasets/metashift/README.md

Co-authored-by: Mario Šaško <[email protected]>

* Update datasets/metashift/README.md

Co-authored-by: Mario Šaško <[email protected]>

* Update datasets/metashift/README.md

Co-authored-by: Mario Šaško <[email protected]>

* Update datasets/metashift/README.md

add default classes info.

Co-authored-by: Mario Šaško <[email protected]>

* Update datasets/metashift/README.md

Co-authored-by: Mario Šaško <[email protected]>

* Update datasets/metashift/README.md

Co-authored-by: Mario Šaško <[email protected]>

* Update datasets/metashift/README.md

Co-authored-by: Mario Šaško <[email protected]>

* indent params list and update with suggestions.

* Apply suggestions from code review

* Update datasets/metashift/metashift.py

Co-authored-by: Mario Šaško <[email protected]>
Co-authored-by: Quentin Lhoest <[email protected]>

…#4078)

* Test instantiation of module factories

* Fix GithubMetricModuleFactory instantiation with None download_config

* Create metric card for METEOR

Proposing a metric card for METEOR

* Update metrics/meteor/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/meteor/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/meteor/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update README.md

* Update README.md

removing NLTK requirement

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Fix docs on audio feature installation

* Remove mention as experimental feature

* Remove old wikipedia leftovers

* Fix some typos in wiki_snippets script

* Update metadata JSON of wiki_snippets dataset

* Update dataset card of wiki_snippets

* Fix tag in dataset card

* Add task tags to dataset card

* Make consistent the conversion to MB

* Add comment warning not to use load_dataset in another script

* Fix CLI dummy data generation

* Test CLI dummy data generation

* Fix style

* Increase max retries for GitHub metrics

* Address requested changes

* ✨ doc maintenance

* 🖍 apply feedback

* 🖍 use the shorthand syntax

* Create README.md

Proposing a CUAD metric card

* Update metrics/cuad/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/cuad/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/cuad/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/cuad/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Update metrics/cuad/README.md

Co-authored-by: Albert Villanova del Moral <[email protected]>

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Add metric card for bleu metric

* fix formatting for bleu metric card

* add How to Use intro

* add limitation to bleu mc

* fix example format, add original paper values

* fix example in metrics/bleu/README.md

Co-authored-by: Quentin Lhoest <[email protected]>

* fix next example in metrics/bleu/README.md

Co-authored-by: Quentin Lhoest <[email protected]>

Co-authored-by: Quentin Lhoest <[email protected]>

* specify format in soundfile.write() when encoding an array

* test encoding audio from array

* Support float data types in pearsonr/spearmanr metrics

* Update doctests

* update case_sensitive input to ignore_case for consistency with other inputs and metrics

* update ignore_punct input for consistency

* update input docs

* change input args because zh and ja are not the only asian languages

* add new examples to py file

* variable consistency

* add ter metric card

* fix metric card formatting

* fix ter style

* remove trailing whitespace

* fix example format

* fix example format in py file

* change input ignore_case back to case_sensitive

* remove trailing whitespace

* Create README.md

Code Eval metric card

* Update metrics/code_eval/README.md

Co-authored-by: Quentin Lhoest <[email protected]>

* Update metrics/code_eval/README.md

Co-authored-by: Quentin Lhoest <[email protected]>

Co-authored-by: Quentin Lhoest <[email protected]>

* Create README.md

Proposing a metric card for XNLI

* Update metrics/xnli/README.md

Co-authored-by: Quentin Lhoest <[email protected]>

* Update metrics/xnli/README.md

Co-authored-by: Quentin Lhoest <[email protected]>

* Update metrics/xnli/README.md

Co-authored-by: Quentin Lhoest <[email protected]>

Co-authored-by: Quentin Lhoest <[email protected]>

* update readme

* add link to zenodo DOIs

* Apply suggestions from code review

Co-authored-by: Albert Villanova del Moral <[email protected]>

Co-authored-by: Albert Villanova del Moral <[email protected]>

* Support streaming xcopa dataset

* Update metadata JSON

* Update dummy data

Co-authored-by: Pramesh <[email protected]>

…#4004)

* Replace broken Drive _URLS by links on github

* Change github urls.

* update dummy data

Co-authored-by: Quentin Lhoest <[email protected]>

* update link in wiki_bio dataset

* run linter and update dummy data

* fix markdown so that test passes (even though I didnt break it)

* init adversarial glue in hf datasets

* format and add card

* update label computation

* remove backslash

* remove print statement

* Update datasets/adv_glue/README.md

Co-authored-by: Quentin Lhoest <[email protected]>

* Update datasets/adv_glue/README.md

Co-authored-by: Quentin Lhoest <[email protected]>

* flesh out README.md

* Update datasets/adv_glue/README.md

advglue

Co-authored-by: Quentin Lhoest <[email protected]>

* Update datasets/adv_glue/README.md

Co-authored-by: Quentin Lhoest <[email protected]>

* update tags and fields

* update tags

* minor changes to trigger the CI

Co-authored-by: Quentin Lhoest <[email protected]>

* fix None issue with Sequence of dict

* update test

* move the None check up a bit

* replace yahoo_answers_topics data url

* update dummy data

* Adding Roman Urdu Hate Speech dataset

* Update Readme

* Update data structure sections in README

* Update Additional Information Section

* Update Contributions Section with some contents

* Remove typos in README

* Update Dataset Script

* Update Dummy_Data

* Apply suggestions from code review

Co-authored-by: Bhavish Pahwa <[email protected]>
Co-authored-by: Quentin Lhoest <[email protected]>