GitLab

 Hotfix for bug in boostings implementation

Updates in LightGBM implementation:
- LightGBM migrated from `SkLearnEvaluationStrategy` to separate `BoostingStrategy`.
- Support for using encoded and unencoded categorical features.
- Support for splitting data for the eval set to avoid overfitting the model.
- Support to use boosting type 'gbdt', 'dart', 'goss'.
- A parameter for early stopping added for fitting the model.
- Automated checks for hyperparameters, with editing if they are mistaken.
- Updates to default_params & search_space.
- New feature: Plot features importance after fitting.

--

author: @RomanKharkovskoy 
co-author: @apovidlo

* chore: bring back cgru and cgru in default pipeline tests

* feat: speed up models tests by parametrizing

* feat: restore fast_ica model on constant data test

* fix: change xgbreg to xgboostreg in docs

* fix: pass input_data in xgboost integration test

* style: remove try block in serializable test

* feat: specify xgboost and xgboostreg models

Updates in Xgboost implementation:
- Xgboost migrated from SkLearnEvaluationStrategy to separate BoostingStrategy.
- Support for using encoded and unencoded categorical features.
- Support for splitting data for the eval set to avoid overfitting the model.
- Support to use booster strategy 'gbtree', 'dart', 'gblinear'.
- A parameter for early stopping added for fitting the model.
- Automated checks for hyperparameters, with editing if they are mistaken.
- Updates to default_params & search_space.
- New feature: Plot features importance after fitting.

--

author: @RomanKharkovskoy 
co-author: @apovidlo 

Fix of copying categorical features in data splitting

* Initial assumption fit time takes numner of folds into accound

Your unit-test coverage report stops uploading about 2 month ago (just like with Fedot.Industrial). It is almost invisible issue, because it doesn't invoke any exception during execution. But it could be found in action logs if you unfold `Codecove-coverage`:

Error: Codecov token not found. Please provide Codecov token with -t flag.
Warning: Codecov: Failed to properly create commit: The process '/home/runner/work/_actions/codecov/codecov-action/v4/dist/codecov' failed with exit code 1

* data: add data for multitarget classification

* fix: prevent stratify with unbalanced classes

* test: add multitarget classification stratify test

* Automated autopep8 fixes

* fix: fix path for test data

* Automated autopep8 fixes

---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

* fix: use forecast method instead of predict

* fix: remove custom logging layer 45, defaulting to logging.INFO

* test: add unit for a smoothing+gaussian_filter+ets pipeline

* feat: add logger to abstract data operation implementation

* feat: add default pca fall back on fit error

* style: add comment about a fast_ica workaround

* feat: add convergence warning interception, defaulting to additive ets

* feat: add correct_params tag to ets

* pin scipy version

* pin gensim version

* pin unyanked scipy version

* pin scipy versions to python versions

* simplify pin for scipy

* fix: add positive appropriation for a window_size param

* test: test positive _window_size in topo extractor

* Update target_array check in data.py

* fix: change ets seasonal_periods search space

* feat: add ETSModel params validation

* fix: add logging on action of params change

* fix: resolve gensim dependency to a specific commit

Fixes #4567

custom link fix

Jupiter docker added, docker folder created, docker files moved to that folder, readme created (#1271)

* Jupiter docker file added, docker folder added, docker files moved to the docker folder

* readme updated

* Docs fixes

* Missed logloss test added

* Cache cleaning implemented for tests

* Update sktime version matching to Support Python 3.11 and 3.12 installation

* Pin sktime version to 0.24.2

* test with different python version specifiers

* Version upd

* Bug fixes

* Cache clear feature

Moved ripser to extra-dependencies

Added a report on time consuming in API. The following steps are presented in this report:
- 'Data Definition (fit)': Time spent on data definition in fit().
- 'Data Preprocessing': Total time spent on preprocessing data, includes fitting and predicting stages.
- 'Fitting (summary)': Total time spent on Composing, Tuning and Training Inference.
- 'Composing': Time spent on searching for the best pipeline.
- 'Train Inference': Time spent on training the pipeline found during composing.
- 'Tuning (composing)': Time spent on hyperparameters tuning in the whole fitting, if with_tune is True.
- 'Tuning (after)': Time spent on .tune() (hyperparameters tuning) after composing.
- 'Data Definition (predict)': Time spent on data definition in predict().
- 'Predicting': Time spent on predicting (inference).

Bumps [readthedocs-sphinx-search](https://github.com/readthedocs/readthedocs-sphinx-search) from 0.1.1 to 0.3.2.
- [Changelog](https://github.com/readthedocs/readthedocs-sphinx-search/blob/main/CHANGELOG.rst)
- [Commits](https://github.com/readthedocs/readthedocs-sphinx-search/compare/0.1.1...0.3.2

)

---
updated-dependencies:
- dependency-name: readthedocs-sphinx-search
  dependency-type: direct:production
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* Create deleteme.md

* Delete deleteme.md

* Change permissions to read in slash-command-dispatch.yml

* Automated autopep8 fixes

* Change BaseException to Exception

* remove backslash

* remove backslashes

* remove backslashes

* Automated autopep8 fixes

* Fix E501

* Fix backslash

* add ignore imports for autopep8

* restore numpy import

* Automated autopep8 fixes

* Fix E402

* Automated autopep8 fixes

* fix parentheses

---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

* add fast topo

* fix fast topo

* Automated autopep8 fixes

* pep8

* add to initial assumption

* make code more clear in `fit` method

* add `fast_topoligical_features` to docs

* fix aligment for pipeline builders in `TSForecastingAssumptions`

* add topo to `FedotBuilder` docs

* fix table in docs

* add params to fast_topo

* change params and add it to tuner search space

* fix integration tests

* add new param stride

* fix param

* dirty speedup

* delete ica from initial assumption due to instability

* fix documentation

* fix test

* delete fast_topo from assumption and delete fast_train tag

---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

topo hotfix

TopologicalFeaturesImplementation was added

* Change permission to read in slash-command-dispatch.yml

* Change permission to none in slash-command-dispatch.yml

* Change trigger event from push to PR in autopep8.yml