GitLab

[ci] prefer CPython in Windows test environment and use safer approach for cleaning up network (fixes #5509) (#5510)

remove redundant whitespaces

* add multiclass objective for cuda_exp

* remove debug code

* add includes requested by lint checks

* fix compilation failure for cuda with cuda-9.0

* clean code

* add feature interaction constraint for cuda_exp

* test feature interaction constraints for cuda_exp

* remove useless check

* update comment

* change percentile in CUDARegressionL1loss::BoostFromScore to 0.5

* add lambdarank for cuda_exp

* support unlimited number of ranks in labels

* fix lint errors

* remove warning for lambdarank with cuda_exp

* Update src/objective/cuda/cuda_rank_objective.hpp
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

* Update src/objective/cuda/cuda_rank_objective.hpp
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

* Update cuda_column_data.hpp

* Update cuda_metadata.hpp

* Update cuda_objective_function.hpp

* Update cuda_row_data.hpp

* Update cuda_regression_objective.hpp

* [python-package] add type hints on Dataset constructors

* fix __init_from_list_np2d() hint

* add return type

* define a DatasetHandle type

fix a typo in docs/Features.rst

* add huber regression for cuda_exp

* renew tree output on GPU

add test cases for regression objectives

* remove useless changes

* add white space

* fix test_regression

Rename num_classes to be more clear

* add (l1) regression objective for cuda_exp

* remove RenewTreeOutputCUDA from CUDARegressionL2loss

* remove mutable and use CUDAVector

* remove white spaces

* remove TODO and document in (#5459)

* add (l2) regression objective for cuda_exp

* fix lint errors

* correct time tag

* add binary objective for cuda_exp

* include <string> and <vector>

* exchange include ordering

* fix length of score to copy in evaluation

* fix EvalOneMetric

* fix cuda binary objective and prediction when boosting on gpu

* Add white space

* fix BoostFromScore for CUDABinaryLogloss

update log in test_register_logger

* include <algorithm>

* simplify shared memory buffer