Pypots

In this refactoring version, we
1. applied SAITS loss function to the newly added imputation models (Crossformer, PatchTST, DLinear, ETSformer, FEDformer, Informer, and Autoformer) in v0.4, and add the arguments `MIT_weight` and `ORT_weight` in them for users to balance the multi-task learning;
2. modularized all neural network models and put their modules in the package [`pypots.nn.modules`](https://github.com/WenjieDu/PyPOTS/tree/main/pypots/nn/modules);
3. removed deprecated metric funcs (e.g. `pypots.utils.metrics.cal_mae` that has been replaced by `pypots.utils.metrics.calc_mae`);

What's Changed
* Apply SAITS loss to newly added models and update the docs by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/346
* Modularize neural network models by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/348
* Modularize NN models, remove deprecated metric funcs, and update docs by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/349
* Remove `pypots.imputation.locf.modules` and add assertions for BTTF by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/350
* Test building package during CI by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/353
* Avoid the import error `MessagePassing not defined` by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/351


**Full Changelog**: https://github.com/WenjieDu/PyPOTS/compare/v0.4...v0.4.1

**Full Changelog**: https://github.com/WenjieDu/PyPOTS/compare/v0.3.2...v0.4

1. fixed an issue that stopped us from running Raindrop on multiple CUDA devices;
2. added Mean and Median as naive imputation methods;

What's Changed
* Refactor LOCF, fix Raindrop on multiple cuda devices, and update docs by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/308
* Remind how to display the figs rather than invoking plt.show() by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/310
* Update the docs and requirements by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/311
* Fixing some bugs, updating the docs and requirements by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/312
* Make CI workflows only test with Python v3.7 and v3.11 by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/313
* Update the docs and release v0.3.2 by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/314
* Add mean and median as imputation methods, and update docs by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/317


**Full Changelog**: https://github.com/WenjieDu/PyPOTS/compare/v0.3.1...v0.3.2

A bug in the calculation of the delta matrix (time-decay matrix) discussed in 294 gets fixed in this update.

What's Changed
* Update logo URLs by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/293
* Fixing the issue in delta calculation by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/297
* Fixing the issue in time-decay matrix calculation and simplify the code by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/298
* Roll back the delta calculation of M-RNN to the same with GRU-D by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/300


**Full Changelog**: https://github.com/WenjieDu/PyPOTS/compare/v0.3...v0.3.1

Happy New Year, dear friends! 🥳

New features and updated APIs in PyPOTS are brought to you here! In v0.3, we

1. added TimesNet as an imputation model;
2. simplified the structure of `val_set`. In previous versions, you had to give `indicating_mask` in the dictionary `val_set` that tells PyPOTS to use which values to validate the model. Now you only need to give `X_ori` (i.e. `X_intact` before) and `X`, both leaving their missing data as NaNs. PyPOTS will handle everything left to evaluate the model for you;
3. enabled PyPOTS to tune hyperparameters for external models (implemented with the PyPOTS framework but haven't been integrated into PyPOTS);
4. updated the package `pypots.data.saving`. Separated the functions for pickle saving and h5py saving, and added `load_dict_from_h5` that can inverse (deserialize) the process of `save_dict_into_h5`;
5. fixed some bugs (255, 263, 266, 280, 282, 286, 289);


What's Changed
* Code refactor by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/251
* Adding TimesNet as an imputation model by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/252
* Adding TimesNet, refactoring code, and updating docs by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/253
* Fixing CSDI gtmask bug by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/255
* Fixing CSDI `gt_mask` issue, and setting a fixed random seed for testing cases by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/256
* Making CSDI return all n_sampling_times imputation samples by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/258
* Adding get_random_seed(), and adding func calc_quantile_crps() by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/260
* Making CSDI val process same as the original by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/262
* Fix missing argument attn_dropout in imputation Transformer by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/263
* Adding visualization functions by AugustJW in https://github.com/WenjieDu/PyPOTS/pull/267
* Add cluster plotting functions in pypots.utils.visualization by vemuribv in https://github.com/WenjieDu/PyPOTS/pull/182
* Fixing unstable nonstationary norm, adding `utils.visual`, and doing some code refactoring by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/266
* Updating package `pypots.data.saving` by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/268
* Enabling to tune hyperparameters for outside models implemented with PyPOTS framework by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/269
* Simplifying the structure of val_set, and using a consistent strategy when lazy-loading val_set by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/272
* Renaming X_intact into X_ori, and adding matplotlib as a dependency by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/274
* Simplifying val_set, renaming X_intact, and adding unit tests for the visual package by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/275
* Update GP-VAE by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/277
* Updating GP-VAE, adding load_dict_from_h5, etc. by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/278
* Adding _check_inputs() for error calculation functions by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/279
* Fixing CSDI, adding placeholder for epoch num in logging by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/280
* Fixing the infinite loop in LOCF by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/282
* Update docs by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/285
* Updating docs, fixing CSDI&LOCF&MRNN, and adding the strategy to save all models by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/284
* Making PyPOTS able to save all models during training, checking if d_model=n_heads*d_k for SAITS and Transformer by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/287
* Fixing MRNN by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/286
* Fix issues in MRNN and update the hyperparameter tuning functionality by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/288
* Fixing the type error of random_seed in pypots.cli.tuning and updating the docs by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/289
* Updating load_dict_from_h5() by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/290


**Full Changelog**: https://github.com/WenjieDu/PyPOTS/compare/v0.2.1...v0.3

Here are updates,

1. for missing values after LOCF imputation (that are missing since the first step hence LOCF doesn't work), we added more options to handle them. Please refer to the argument `first_step_imputation` in [LOCF docs](https://docs.pypots.com/en/latest/pypots.imputation.html#module-pypots.imputation.locf). The default option is "zero" in previous versions, but we've changed it to "backward" which is more reasonable;
2. enabled SAITS to return latent attention weights from blocks in predict() for advanced analysis e.g. in 178;
3. renamed model saving and loading functions save_model() and load_model() into save() and load();


What's Changed
* Check if X_intact contains missing data for imputation models, check and list mismatched hyperparameters in the tuning mode by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/234
* Make SAITS return attention weights in predict() by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/239
* Adding other options for the first step imputation in LOCF by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/240
* Fixing the problem about staling issues by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/244
* Testing with Python 3.11 and support it by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/246
* Rename save_model() and load_model() into save() and load() by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/247
* Refactoring save_model() and load_model(), and updating docs by WenjieDu in https://github.com/WenjieDu/PyPOTS/pull/249


**Full Changelog**: https://github.com/WenjieDu/PyPOTS/compare/v0.2...v0.2.1