* patchtsmixer initial commit

* x,y->context_values,target_values, unittest addded

* cleanup code

* minor

* return hidden states

* model tests, partial integration tests

* ettm notebook temporary

* minor

* config mask bug fix, tests updated

* final ETT notebooks

* add selfattn

* init

* added docstrings

* PatchTSMixerForPretraining -> PatchTSMixerForMaskPretraining

* functionality tests added

* add start and input docstrings

* docstring edits

* testcase edits

* minor changes

* docstring error fixed

* ran make fixup

* finalize integration tests and docs

* minor

* cleaned gitignore

* added dataclass decorator, ran black formatter

* ran ruff

* formatting

* add slow decorator

* renamed in_Channel to input_size and default to 1

* shorten dataclass names

* use smaller model for testing

* moved the 3 heads to the modeling file

* use scalers instead of revin

* support forecast_channel_indices

* fix regression scaling

* undo reg. scaling

* removed unneeded classes

* forgot missing

* add more layers

* add copied positional_encoding

* use patchmask from patchtst

* removed dependency on layers directory

* formatting

* set seed

* removed unused imports

* fixed forward signature test

* adding distributional head for PatchTSMixerForecasting

* add generate to forecast

* testcases for generate

* add generate and distributional head for regression

* raise Exception for negative values for neg binominal distribution

* formatting changes

* remove copied from patchtst and add TODO for test passing

* make copies

* doc edits

* minor changes

* format issues

* minor changes

* minor changes

* format docstring

* change some class names to PatchTSMixer + class name

Transpose to PatchTSMixerTranspose
GatedAttention to PatchTSMixerGatedAttention

* change NormLayer to PatchTSMixerNormLayer

* change MLP to PatchTSMixerMLP

* change PatchMixer to PatchMixerBlock, FeatureMixer to FeatureMixerBlock

* change ChannelFeatureMixer to ChannelFeatureMixerBlock

* change PatchMasking to PatchTSMixerMasking

* change Patchify to PatchTSMixerPatchify

* list to `list`

* fix docstrings

* formatting

* change bs to batch_size, edit forecast_masking

* edit random_masking

* change variable name and update docstring in PatchTSMixerMasking

* change variable name and update docstring in InjectScalerStatistics4D

* update forward call in PatchTSMixerTranspose

* change variable name and update docstring in PatchTSMixerNormLayer

* change variable name and update docstring in PatchTSMixerMLP

* change variable name and update docstring in ChannelFeatureMixerBlock

* formatting

* formatting issues

* docstring issue

* fixed observed_mask type in docstrings

* use FloatTensor type

* formatting

* fix rescaling issue in forecasting, fixed integration tests

* add docstring from decorator

* fix docstring

* Update README.md

Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>

* Update src/transformers/models/patchtsmixer/configuration_patchtsmixer.py

Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>

* Update src/transformers/models/patchtsmixer/modeling_patchtsmixer.py

Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>

* Update src/transformers/models/patchtsmixer/configuration_patchtsmixer.py

Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>

* Update src/transformers/models/patchtsmixer/modeling_patchtsmixer.py

Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>

* PatchTSMixerChannelFeatureMixerBlock

* formatting

* ForPretraining

* use num_labels instead of n_classes

* remove commented out code

* docstring fixed

* nn.functional used instead of one letter F

* x_tmp renamed

* one letter variable x removed from forward calls

* one letter variable y removed

* remove commented code

* rename patch_size, in_channels, PatchTSMixerBackbone

* add config to heads

* add config to heads tests

* code reafactoring to use config instead of passing individual params

* Cdocstring fixes part 1

* docstring fixes part 2

* removed logger.debug

* context_values -> past_values

* formatting changes

* pe -> positional_encoding

* removed unused target variable

* self.mode logic fixed

* formatting change

* edit docstring and var name

* change n_targets to num_targets

* rename input_size to num_input_channels

* add head names with prefix PatchTSMixer

* edit docstring in PatchTSMixerForRegression

* fix var name change in testcases

* add PatchTSMixerAttention

* return dict for all exposed classes, test cases added

* format

* move loss function to forward call

* make style

* adding return dict/tuple

* make repo-consistency

* remove flatten mode

* code refactoring

* rename data

* remove PatchTSMixer and keep only PatchTSMixerEncoder

* docstring fixes

* removed unused code

* format

* format

* remove contiguous and formatting changes

* remove model description from config

* replace asserts with ValueError

* remove nn.Sequential from PatchTSMixerNormLayer

* replace if-else with map

* remove all nn.Sequential

* format

* formatting

* fix gradient_checkpointing error after merge, and formatting

* make fix-copies

* remove comments

* reshape

* doesnt support gradient checkpointing

* corect Patchify

* masking updates

* batchnorm copy from

* format checks

* scaler edits

* remove comments

* format changes

* remove self.config

* correct class PatchTSMixerMLP(nn.Module):

* makr fix

* doc updates

* fix-copies

* scaler class correction

* doc edits

* scaler edits

* update readme with links

* injectstatistics add

* fix-copies

* add norm_eps option to LayerNorm

* format changes

* fix copies

* correct make copies

* use parametrize

* fix doc string

* add docs to toctree

* make style

* doc segmenting

* docstring edit

* change forecast to prediction

* edit doc

* doc edits

* remove PatchTSMixerTranspose

* add PatchTSMixerPositionalEncoding and init position_enc

* remove positional_encoding

* edit forecast_masking, remove forecast_mask_ratios

* fix broken code

* var rename target_values -> future_values

* num_features -> d_model

* fix broken code after master merge

* repo consistency

* use postional embedding

* prediction_logits -> prediction_outputs, make fix-copies

* uncommented @slow

* minor changes

* loss first in tuple

* tuple and dict same ordering

* style edits

* minor changes

* dict/tuple consistent enablement

* Update src/transformers/models/patchtsmixer/modeling_patchtsmixer.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* Update tests/models/patchtsmixer/test_modeling_patchtsmixer.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* Update src/transformers/models/patchtsmixer/modeling_patchtsmixer.py

Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* fix formatting

* formatting

* usage tip

* test on cpu only

* add sample usage

* change PatchTSMixerForClassification to PatchTSMixerForTimeSeriesClassification

* push changes

* fix copies

* std scaling set to default True case

* minor changes

* stylechanges

---------

Co-authored-by: Arindam Jati <arindam.jati@ibm.com>
Co-authored-by: vijaye12 <vijaye12@in.ibm.com>
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
Co-authored-by: nnguyen <nnguyen@us.ibm.com>
Co-authored-by: vijaye12 <vijaykr.e@gmail.com>
Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>
Co-authored-by: Nam Nguyen <namctin@gmail.com>
Co-authored-by: Wesley Gifford <79663411+wgifford@users.noreply.github.com>
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>