https://github.com/autogluon/fev - v0.6.0rc3

This is a pre-release version.

What's Changed

• Use ordinal encoding for dynamic categorical features in GluonTSAdapter by @shchur in https://github.com/autogluon/fev/pull/31
• Refactor Task class to include multiple rolling window evaluations by @shchur in https://github.com/autogluon/fev/pull/33
• Make covariate column names explicit by @shchur in https://github.com/autogluon/fev/pull/34
• make metrics customizable by @canerturkmen in https://github.com/autogluon/fev/pull/35
• Minor fixes to Task by @shchur in https://github.com/autogluon/fev/pull/37
• Fix Task.to_dict() with dict-based metrics by @shchur in https://github.com/autogluon/fev/pull/38

New Contributors

• @canerturkmen made their first contribution in https://github.com/autogluon/fev/pull/35

Full Changelog: https://github.com/autogluon/fev/compare/v0.6.0rc2...v0.6.0rc3

- Python
Published by shchur 6 months ago

https://github.com/autogluon/fev - v0.6.0rc2

This is a pre-release version.

What's Changed

• Minor fixes and optimizations by @shchur in https://github.com/autogluon/fev/pull/29
• Implement DartsAdapter by @shchur in https://github.com/autogluon/fev/pull/30

Full Changelog: https://github.com/autogluon/fev/compare/v0.6.0rc1...v0.6.0rc2

- Python
Published by shchur 7 months ago

https://github.com/autogluon/fev - v0.6.0rc1

This is a pre-release version.

What's Changed

• Update README.md by @shchur in https://github.com/autogluon/fev/pull/26
• Add multivariate <-> univariate conversion support by @shchur in https://github.com/autogluon/fev/pull/27

Full Changelog: https://github.com/autogluon/fev/compare/v0.5.0...v0.6.0rc1

- Python
Published by shchur 7 months ago

https://github.com/autogluon/fev - v0.5.0

Highlights

• Multivariate forecasting support: The users can now create multivariate tasks by setting the target_column to a list[str] with names of target columns when creating a Task. Check out the updated tutorial for more details.
• API changes: The following Task attributes have been deprecated. Results containing old names can still be used, but creating new tasks with deprecated attributes will produce a warning.
  • multiple_target_columns has been renamed to generate_univariate_targets_from.
  • min_ts_length has been replaced by min_context_length.
• Improved handling of short series: Previously, if some time series in the dataset were too short for the chosen horizon and cutoff combination, and exception would be raised. Now, these series will be automatically filtered out during dataset loading.

Changelog

• Add support for multivariate forecasting in Task by @shchur in https://github.com/autogluon/fev/pull/15
• Improve time series filtering based on cutoff, horizon and min_context_length by @shchur in https://github.com/autogluon/fev/pull/18
• Add TiRex results by @apointa in https://github.com/autogluon/fev/pull/17
• Fix seasonal differences for short series by @shchur in https://github.com/autogluon/fev/pull/20
• Expose prediction validation as a public method by @abdulfatir in https://github.com/autogluon/fev/pull/21
• Handle DatasetDict in clean_and_validate_predictions by @abdulfatir in https://github.com/autogluon/fev/pull/22

New Contributors

• @apointa made their first contribution in https://github.com/autogluon/fev/pull/17
• @abdulfatir made their first contribution in https://github.com/autogluon/fev/pull/21

Full Changelog: https://github.com/autogluon/fev/compare/v0.4.1...v0.5.0

- Python
Published by shchur 8 months ago

https://github.com/autogluon/fev -

This is a pre-release version.

Changes: - Expose prediction validation as a public method (#21) - Handle DatasetDict in clean_and_validate_predictions (#22)

- Python
Published by shchur 9 months ago

https://github.com/autogluon/fev - v0.5.0rc2

This is a pre-release version.

Changes: - Fix seasonal differences for short series (#20)

- Python
Published by shchur 9 months ago

https://github.com/autogluon/fev - v0.5.0rc1

This is a pre-release version.

Changes: * Add support for multivariate forecasting in Task (https://github.com/autogluon/fev/pull/15) * Improve time series filtering based on cutoff, horizon and mincontextlength (https://github.com/autogluon/fev/pull/18)

Full Changelog: https://github.com/autogluon/fev/compare/v0.4.1...v0.5.0rc1

- Python
Published by shchur 9 months ago

https://github.com/autogluon/fev - v0.4.1

Changes: - Increase datasets version range to >=2.15,<4.0

Full Changelog: https://github.com/autogluon/fev/compare/v0.4.0...v0.4.1

- Python
Published by shchur 11 months ago

https://github.com/autogluon/fev - v0.4.0

🚨 Highlights: - The v0.4.0 release fixes an annoying error related to dataset_fingerprint validation in fev.leaderboard. We therefore highly recommend upgrading to the newest version.

Changes: * Add support for rolling evaluation in TaskGenerator (https://github.com/autogluon/fev/pull/9) * Add new arguments num_rolling_windows, initial_cutoff and rolling_step_size to fev.task.TaskGenerator. These arguments make it possible to concisely define multiple backtesting splits from a single task. * Make dataset_fingerprint depend only on the dataset contents (https://github.com/autogluon/fev/pull/10) * This PR ensures that the dataset_fingerprint is not affected by, e.g., changes to the dataset README on Hugging Face. * Bump version to v0.4.0 (https://github.com/autogluon/fev/pull/11)

Full Changelog: https://github.com/autogluon/fev/compare/v0.3.0...v0.4.0

- Python
Published by shchur 11 months ago

https://github.com/autogluon/fev - v0.3.1

Changes: - Rerun evaluations using the latest version of datasets on Hugging Face (v1.3.0). This includes the fix to the frequency of the monash_hospital and dominick datasets - Remove monash_saugeenday dataset to fix the discrepancy between the Chronos paper and the leaderboard - Include results for TimesFM-2.0 - Make the error message caused by dataset fingerprint mismatch more informative

Full Changelog: https://github.com/autogluon/fev/compare/v0.3.0...v0.3.1

- Python
Published by shchur 12 months ago

https://github.com/autogluon/fev - v0.3.0

Changes: - Add method fev.utils.convert_long_df_to_hf_dataset for converting long format pd.DataFrame datasets to Hugging Face datasets.Dataset format - Extend documentation for datasets, tasks, benchmarks and models

Full Changelog: https://github.com/autogluon/fev/compare/v0.2.1...v0.3.0

- Python
Published by shchur about 1 year ago

https://github.com/autogluon/fev - v0.2.1

Changes: - Remove harmonic mean aggregation from fev.analysis.leaderboard()

Full Changelog: https://github.com/autogluon/fev/compare/v0.2.0...v0.2.1

- Python
Published by shchur about 1 year ago

https://github.com/autogluon/fev - v0.2.0

Changes: - Add a new column trained_on_this_dataset to the evaluation summary that tracks whether the model is used in zero-shot mode - Support new input formats for leaderboard() and pivot_table() methods

Full Changelog: https://github.com/autogluon/fev/compare/v0.1.0...v0.2.0

- Python
Published by shchur about 1 year ago

https://github.com/autogluon/fev - v0.1.0

Initial release

- Python
Published by shchur about 1 year ago