v1.0.0

New Features

• [FEAT] Complete ETTh1/ETTh2/ETTm1 and option for unnormalized datasets. @kdgutier (#25)
• [FEAT] OldHierarchical + Favorita datasets @kdgutier (#24)
• Added PHM2008 dataset @kdgutier (#21)

Breaking Change

• remove losses and evaluation modules @jmoralez (#33)

Documentation

• Create CODE_OF_CONDUCT.md @tracykteal (#38)
• update readme @jmoralez (#35)
• add index @jmoralez (#32)

Enhancement

• remove numba dependency @jmoralez (#34)

v0.0.8

What's Changed

• [FEAT] Add distributed forecasts evaluation in #16. The new version includes the accuracy function (inspired by fable) to compute different metrics for different aggregations. This new function can also evaluate spark, dask, and ray dataframes.
• [FEAT] Add hierarchical data tests in #18. In #15 was pointed out that the Labour summing matrix was wrong. The dataset was updated with the right one, and tests were added to ensure the summing matrix is right.

Full Changelog: v0.0.7...v0.0.8

v0.0.7

What's Changed

• use provision-with-micromamba action in #11
• support async downloads in #10
• add M4 dataset and loss functions in #12
• [FEAT] Add M5 dataset in #14

New Contributors

• @jmoralez made their first contribution in #11

Full Changelog: v0.0.6...v0.0.7

v0.0.6

What's Changed

• [FEAT] M3 dataset in #7
• [FEAT] nbdev2 in #8
• [FEAT] Add long horizon dataset in #9

Full Changelog: v0.0.5...v0.0.6

v0.0.5

What's Changed

• [FEAT] Add horizon to hierarchical datasets by @FedericoGarza in #1
• feat: add tags to hier datasets by @FedericoGarza in #2
• fix: traffic tags by @FedericoGarza in #4
• [FEAT] Add test size for hierarchical datasets by @FedericoGarza in #5
• fix: labour covid and wiki2 horizon by @FedericoGarza in #6

Full Changelog: v0.0.3...v0.0.5

v0.0.3

Full Changelog: v0.0.2...v0.0.3

• Export HierarchicalData

v0.0.2

Full Changelog: v0.0.1...v0.0.2

v0.0.1

The first release of DatasetsForecast 🎉 🌮 .