TimeDiffusion v0.4.1

• Custom kernel_size support added to all base models

TimeDiffusion v0.4

1. Liquid base model TimeDiffuionLiquid added. Lightweight, fast, but less accurate than the main model.
2. Abstract class for all base models TimeDiffusionModel added.

TimeDiffusion v0.3

• Using TimeDiffusionProjector as base for TD framework with option to choose TimeDiffusionAttention.
• Model eval() fix in TD framework methods
• Additional time series forecasting examples added for bitcoin historical prices

TimeDiffusion v0.2.2

• Early stopping epochs patience mechanism added in TD.fit, alowing to interrupt learning process at the epoch end, if model hasn't learned anything new in latest epochs (validation quality hasn't improved)

TimeDiffusion v0.2.1

• Nan support added to:
• • DimUniversalStandardScaler
• • TD.restore method (TD.fit method already supported nans in mask positions)
• Removed redundant fill_mask parameter of TD.fit method

TimeDiffusion v0.2

• Few TD framework improvements and bug fixes related to scaling, typing and mask operations.
• Scaler tests and nan checks in model's and framework's tests added.

Full Changelog: v0.1.2...v0.2

TimeDiffusion v0.1.2

First release of TD framework. Could do following time series tasks: forecasting, imputation, synthesis and other custom tasks using restore method