Data

Tools

Indexes

Applications

Experiments

Open Source Science

Recent Releases of https://github.com/timeseriesai/tsai

https://github.com/timeseriesai/tsai - v0.4.0

New Features

  • Applied necessary changes to the tsai library for full support on MPS devices.

Bugs Squashed

  • Updated TSiT and TSSequencer models to resolve compatibility issues on the MPS backend.
  • Modified the multimodal head to properly handle sequence predictions.

- Jupyter Notebook
Published by oguiza about 1 year ago

https://github.com/timeseriesai/tsai - 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

- Jupyter Notebook
Published by oguiza over 2 years ago

https://github.com/timeseriesai/tsai - 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)

- Jupyter Notebook
Published by oguiza over 2 years ago

https://github.com/timeseriesai/tsai - 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 ocontidxs 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)

- Jupyter Notebook
Published by oguiza almost 3 years ago

https://github.com/timeseriesai/tsai - v0.3.6

New Features

  • added optional activation to getXpreds (#715)

  • added external vocab option to dls (#705)

  • allow classification outputs with n dimensions (#704)

  • added getsweepconfig 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)

- Jupyter Notebook
Published by oguiza about 3 years ago

https://github.com/timeseriesai/tsai - 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)

- Jupyter Notebook
Published by oguiza over 3 years ago

https://github.com/timeseriesai/tsai - v0.3.4

New Features

  • compatibility with Pytorch 1.13 (#619)

  • added selvars to getrobustscale_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 getrobustscaler params with selvars (#615)

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

  • issue when using lists as selvars and selsteps in TSRandom2Value (#612)

  • fixed issue with featureimportance and stepimportance when using metrics (#609)

  • renamed data processing tfms featureidxs as selvars for consistency (#608)

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

- Jupyter Notebook
Published by oguiza over 3 years ago

https://github.com/timeseriesai/tsai - v0.3.2

Breaking Changes

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

  • replaced MultiEmbedding nembeds, embeddims and paddingidxs by ncatembeds, catembeddims and catpadding_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 gettimeperbatch and getdlpercentper_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)

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

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

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

- Jupyter Notebook
Published by oguiza over 3 years ago

https://github.com/timeseriesai/tsai - v0.3.1

Release notes

0.3.1

New Features

  • added StratifiedSampler to handle imbalanced datasets (#479)

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

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

  • added SmeLU activation function (#458)

  • added splitinchunks (#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 getdirsize 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)

  • splitinchunks incorrectly calculated (#455)

  • checkX() got an unexpected keyword argument 'coercetonumpy' (#415)

- Jupyter Notebook
Published by oguiza about 4 years ago

https://github.com/timeseriesai/tsai - 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 *

- Jupyter Notebook
Published by oguiza about 4 years ago

https://github.com/timeseriesai/tsai - v0.2.25

0.2.25

Breaking Changes

  • updated forwardgaps removing nanto_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 recallatspecificity metric (#342)

  • added trainmetrics argument to tslearner (#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 plotcalibrationcurve (#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)

  • selvars and selsteps 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)

- Jupyter Notebook
Published by oguiza over 4 years ago

https://github.com/timeseriesai/tsai - v0.2.24

Release notes

0.2.24

Breaking Changes

  • removed InceptionTSiT, InceptionTSiTPlus, ConvTSiT & ConvTSiTPlus (#276)

New Features

  • add stateful custom sklearn API type tfms: TSShrinkDataFrame, TSOneHotEncoder, TSCategoricalEncoder (#313)

  • Pytorch 1.10 compatibility (#311)

  • ability to pad at the start/ end of sequences and filter results in SlidingWindow (#307)

  • added bias_init to TSiT (#288)

  • plot permutation feature importance after a model's been trained (#286)

  • added separable as an option to MultiConv1d (#285)

  • Modified TSiTPlus to accept a feature extractor and/or categorical variables (#278)

Bugs Squashed

  • learn modules takes too long to load (#312)

  • error in roll2d and roll3d when passing index 2 (#304)

  • TypeError: unhashable type: 'numpy.ndarray' (#302)

  • ValueError: only one element tensors can be converted to Python scalars (#300)

  • unhashable type: 'numpy.ndarray' when using multiclass multistep labels (#298)

  • incorrect data types in NumpyDatasets subset (#297)

  • createfuturemask creates a mask in the past (#293)

  • NameError: name 'X' is not defined in learner.feature_importance (#291)

  • TSiT test fails on cuda (#287)

  • MultiConv1d breaks when ni == nf (#284)

  • WeightedPerSampleLoss reported an error when used with LDS_weights (#281)

  • pos_encoding transfer weight in TSiT fails (#280)

  • MultiEmbedding catpos and contpos are not in state_dict() (#277)

  • fixed issue with MixedDataLoader (#229), thanks to @Wabinab

- Jupyter Notebook
Published by oguiza over 4 years ago

https://github.com/timeseriesai/tsai - v0.2.23

Release notes

0.2.23

Breaking Changes

  • removed torch-optimizer dependency (#228)

New Features

  • added option to train MVP on random sequence lengths (#252)

  • added ability to pass an arch name (str) to learner instead of class (#217)

  • created convenience fns createdirectory and deletedirectory in utils (#213)

  • added option to create random array of given shapes and dtypes (#212)

  • my_setup() print your main system and package versions (#202)

  • added a new tutorial on how to train large datasets using tsai (#199)

  • added a new function to load any file as a module (#196)

  • Created CODEOFCONDUCT.md in https://github.com/timeseriesAI/tsai/pull/210

  • Add Optuna tutorial notebook by @dnth in https://github.com/timeseriesAI/tsai/pull/275

Bugs Squashed

  • Loading code just for inference takes too long (#273)

  • Fixed out-of-memory issue with large datasets on disk (#126)

  • AttributeError: module 'torch' has no attribute 'nantonum' (#262)

  • Fixed TypeError: unhashable type: 'numpy.ndarray' (#250)

  • Wrong link in paper references (#249)

  • remove default PATH which overwrites custom PATH (#238)

  • Predictions where not properly decoded when using with_decoded. (#237)

  • SettingWithCopyWarning: A value is trying to be set on a copy of a slice from a DataFrame (#221)

  • InceptionTimePlus wasn't imported by TSLearners (#218)

  • getsubsetdl fn is not properly creating a subset dataloader (#211)

  • Bug in WeightedPersSampleLoss (#203)

  • Bump nokogiri from 1.11.4 to 1.12.5 in /docs by @dependabot in https://github.com/timeseriesAI/tsai/pull/222

New Contributors

  • @geoHeil made their first contribution in https://github.com/timeseriesAI/tsai/pull/207
  • @dnth made their first contribution in https://github.com/timeseriesAI/tsai/pull/275

Full Changelog: https://github.com/timeseriesAI/tsai/compare/0.2.20...0.2.23

- Jupyter Notebook
Published by oguiza over 4 years ago

https://github.com/timeseriesai/tsai - v0.2.20

- Jupyter Notebook
Published by oguiza over 4 years ago

https://github.com/timeseriesai/tsai - v0.2.19

- Jupyter Notebook
Published by oguiza over 4 years ago