v0.3.9

• support to MPS backend. Both the MPS accelerator and the PyTorch backend are still experimental. As such, not all operations are currently supported.
• compatibility with torch 2.2
• ability to pass arch_config to multimodal models

v0.3.8

New Features

• added Hydra and HydraMultiRocket archs (#800)

Bugs Squashed

• UCR Dataset download link has been updated (#827)

• mWDNPlus now supports multidimensional outputs (#802)

• Fixed import issues with demo code in Readme.MD (#798)

v0.3.7

New Features

• added functionality to support inputs with static/ observed (time-dependent) features

• added functionality to support inputs with categorical/ continuous features

• added functionality to apply patches to time series models

• Added MultiRocket/ MultiRocketPlus architectures

• added TSSelfDropout (#790)

• added get_feat_idxs to calculate multimodal indices (#789)

• remaining features assigned to o_cont_idxs by default (#788)

• added patch encoder to MultiInputWrapper (#787)

• added TSTargetEncoder transform (#769)

• added TSRobustScaler to tfm pipelines (#763)

• added new tfms - TSDropIfTrueCols and ApplyFunc (#760)

• tensor slices in different devices when using TensorSplitter (#799)

Bugs Squashed

• mixed augmentations (MixUp1d, CutMix1d,..) are not updating labels (#791)

• get_UCR_data function fails due to changed download link (#785)

• error when using TSSelectColumns due to pandas df slicing (#762)

• short arrays create issues when running get_usable_idxs (#761)

• get_X_pred creates different probablities when using numpy array or torch tensor (#754)

• partial_n is applied to all datasets by default (#748)

• get_best_dls_params function still prints output when the verbose parameter is set to false (#737)

• using xresnet for vision classification raises an error (#728)

v0.3.6

New Features

• added optional activation to get_X_preds (#715)

• added external vocab option to dls (#705)

• allow classification outputs with n dimensions (#704)

• added get_sweep_config to wandb module (#687)

• added functionality to run pipeline sweeps (#686)

• added seed to learners to make training reproducible (#685)

• added functionality to filter df for required forecasting dates (#679)

• added option to train model on train only (#671)

Bugs Squashed

• access all available dataloaders in dls (#724)

• make all models ending in Plus work with ndim classification targets (#719)

• make all models ending in Plus work with ndim work with ndim regression/ forecasting targets (#718)

• added MiniRocket to get_arch (#717)

• fixed issue with get_arch missing new models (#709)

• valid_metrics causes an error when using TSLearners (#708)

• valid_metrics are not shown when an array is passed within splits (#707)

• TSDatasets w/o tfms and inplace=False creates new X (#695)

• Prediction and True Values Swapped in plot_forecast (utils.py) (#690)

• MiniRocket incompatible with latest scikit-learn version (#677)

• Df2xy causing incorrect splits (#666)

• Feature Importance & Step Importance Not working (#647)

• multi-horizon forecasting (#591)

• Issues saving models with TSMetaDataset Dataloader (#317)

v0.3.5

Breaking Changes

• removed default transforms from TSClassifier, TSRegressor and TSForecaster (#665)

New Features

• add option to pass an instantiated model to TSLearners (#650)

• Added PatchTST model to tsai (#638)

• Added new long-term time series forecasting tutorial notebook

Bugs Squashed

• Undefined variable (#662)

• Multivariate Regression and Forecasting basic tutorials throw an error (#629)

• TypeError: init() got an unexpected keyword argument 'custom_head' (#597)

• Issues with TSMultiLabelClassification (#533)

• Incompatible errors or missing functions in 'tutorial_nbs' notebooks, please fix. (#447)

• Saving models with TSUnwindowedDataset Dataloaders: AttributeError: 'TSUnwindowedDataset' object has no attribute 'new_empty' (#215)

v0.3.4

New Features

• compatibility with Pytorch 1.13 (#619)

• added sel_vars to get_robustscale_params (#610)

• added sel_steps to TSRandom2Value (#607)

• new walk forward cross-validation in tsai (#582)

Bugs Squashed

• fixed issue when printing an empty dataset wo transforms NoTfmLists (#622)

• fixed minor issue in get_robustscaler params with sel_vars (#615)

• fixed issue when using tsai in dev with VSCode (#614)

• issue when using lists as sel_vars and sel_steps in TSRandom2Value (#612)

• fixed issue with feature_importance and step_importance when using metrics (#609)

• renamed data processing tfms feature_idxs as sel_vars for consistency (#608)

• fixed issue when importing 'GatedTabTransformer' (#536)

v0.3.2

Breaking Changes

• replaced TSOneHot preprocessor by TSOneHotEncode using a different API (#502)

• replaced MultiEmbedding n_embeds, embed_dims and padding_idxs by n_cat_embeds, cat_embed_dims and cat_padding_idxs (#497)

New Features

• added GaussianNoise transform (#514)

• added TSSequencer model based on Sequencer: Deep LSTM for Image Classification paper (#508)

• added TSPosition to be able to pass any steps list that will be concatenated to the input (#504)

• added TSPosition preprocessor to allow the concatenation of a custom position sequence (#503)

• added TSOneHot class to encode a variable on the fly (#501)

• added token_size and tokenizer arguments to tsai (#496)

• SmeLU activation function not found (#495)

• added example on how to perform inference, partial fit and fine tuning (#491)

• added get_time_per_batch and get_dl_percent_per_epoch (#489)

• added TSDropVars used to removed batch variables no longer needed (#488)

• added SmeLU activation function (#458)

• Feature request: gMLP and GatedTabTransformer. (#354)

• Pay Attention to MLPs - gMLP (paper, implementation)

• The GatedTabTransformer (paper, implementation);

Bugs Squashed

• after_batch tfms set to empty Pipeline when using dl.new() (#516)

• 00b_How_to_use_numpy_arrays_in_fastai: AttributeError: attribute 'device' of 'torch._C._TensorBase' objects is not writable (#500)

• getting regression data returns _check_X() argument error (#430)

• I wonder why only 'Nor' is displayed in dls.show_batch(sharvey=True). (#416)

v0.3.1

Release notes

0.3.1

New Features

• added StratifiedSampler to handle imbalanced datasets (#479)

• added seq_embed_size and seq_embed arguments to TSiT (#476)

• added get_idxs_to_keep that can be used to filter indices based on different conditions (#469)

• added SmeLU activation function (#458)

• added split_in_chunks (#454)

• upgraded min Python version to 3.7 (#450)

• added sampler argument to NumpyDataLoader and TSDataLoader (#436)

• added TSMask2Value transform which supports multiple masks (#431)

• added TSGaussianStandardize for improved ood generalization (#428)

• added get_dir_size function (#421)

Bugs Squashed

• slow import of MiniRocketMultivariate from sktime (#482)

• Fixed install from source fails on Windows (UnicodeDecodeError) (#470)

• TSDataset error oindex is not an attribute (#462)

• split_in_chunks incorrectly calculated (#455)

• _check_X() got an unexpected keyword argument 'coerce_to_numpy' (#415)

v0.3.0

Release notes

0.3.0

New Features

• Added function that pads sequences to same length (#410)

• Added TSRandomStandardize preprocessing technique (#396)

• New visualization techniques: model's feature importance and step importance (#393)

• Allow from tsai.basics import * to speed up loading (#320)

Bugs Squashed

• Separate core from non-core dependencies in tsai - pip install tsaiextras. This is an important change that:
  • reduces the time to pip install tsai
  • avoid errors during installation
  • reduces the time to load tsai using from tsai.all import *

v0.2.25

0.2.25

Breaking Changes

• updated forward_gaps removing nan_to_num (#331)

• TSRobustScaler only applied by_var (#329)

• remove add_na arg from TSCategorize (#327)

New Features

• added IntraClassCutMix1d (#384)

• added learn.calibrate_model method (#379)

• added analyze_array function (#378)

• Added TSAddNan transform (#376)

• added dummify function to create dummy data from original data (#366)

• added Locality Self Attention to TSiT (#363)

• added sel_vars argument to MVP callback (#349)

• added sel_vars argument to TSNan2Value (#348)

• added multiclass, weighted FocalLoss (#346)

• added TSRollingMean batch transform (#343)

• added recall_at_specificity metric (#342)

• added train_metrics argument to ts_learner (#341)

• added hist to PredictionDynamics for binary classification (#339)

• add padding_idxs to MultiEmbedding (#330)

Bugs Squashed

• sort_by data may be duplicated in SlidingWindowPanel (#389)

• create_script splits the nb name if multiple underscores are used (#385)

• added torch functional dependency to plot_calibration_curve (#383)

• issue when setting horizon to 0 in SlidingWindow (#382)

• replace learn by self in calibrate_model patch (#381)

• Argument d_head is not used in TSiTPlus (#380)

  • https://github.com/timeseriesAI/tsai/blob/6baf0ba2455895b57b54bf06744633b81cdcb2b3/tsai/models/TSiTPlus.py#L63

• replace default relu activation by gelu in TSiT (#361)

• sel_vars and sel_steps in TSDatasets and TSDalaloaders don't work when used simultaneously (#347)

• ShowGraph fails when recoder.train_metrics=True (#340)

• fixed 'se' always equal to 16 in MLSTM_FCN (#337)

• ShowGraph doesn't work well when train_metrics=True (#336)

• TSPositionGaps doesn't work on cuda (#333)

• XResNet object has no attribute 'backbone' (#332)

• import InceptionTimePlus in tsai.learner (#328)

• df2Xy: Format correctly without the need to specify sort_by (#324)

• bug in MVP code learn.model --> self.learn.model (#323)

• Colab install issues: importing the lib takes forever (#315)

• Calling learner.feature_importance on larger than memory dataset causes OOM (#310)