GitLab

* speed up multi-threading sum

* Apply suggestions from code review

* Add support to optimize for NDCG at a given truncation level

In order to correctly optimize for NDCG@_k_, one should exclude pairs containing both documents beyond the top-_k_ (as they don't affect NDCG@_k_ when swapped).

* Update rank_objective.hpp

* Apply suggestions from code review
Co-authored-by: Guolin Ke <guolin.ke@outlook.com>

* Update rank_objective.hpp

remove the additional branching: get high_rank and low_rank by one "if".

* Update config.h

add description to lambdarank_truncation_level parameter

* Update Parameters.rst

* Update test_sklearn.py

update expected NDCG value for a test, as it was affected by the underlying change in the algorithm

* Update test_sklearn.py

update NDCG@3 reference value

* fix R learning-to-rank tests

* Update rank_objective.hpp

* Update include/LightGBM/config.h
Co-authored-by: Guolin Ke <guolin.ke@outlook.com>

* Update Parameters.rst
Co-authored-by: Guolin Ke <guolin.ke@outlook.com>
Co-authored-by: James Lamb <jaylamb20@gmail.com>

* fix subset bug

* typo

* add fixme tag

* bin mapper

* fix test

* fix add_features_from

* Update dataset.cpp

* fix merge bug

* added Python merge code

* added test for add_features

* Update dataset.cpp

* Update src/io/dataset.cpp

* continue implementing

* warn users about categorical features
Co-authored-by: StrikerRUS <nekit94-12@hotmail.com>
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

* setup CUDA CI job

* minor updates

* Update .vsts-ci.yml

* Update setup.sh

* Update .vsts-ci.yml

* Update .vsts-ci.yml

* try not to hardcode path

* Update lint_r_code.R

* improves logging in lint_r_code

* Update .ci/lint_r_code.R
Co-authored-by: James Lamb <jaylamb20@gmail.com>
Co-authored-by: James Lamb <jaylamb20@gmail.com>

Co-authored-by: James Lamb <jaylamb20@gmail.com>

* fix int64 write error

* attempt

* [WIP] [ci] [R-package] Add CI job that runs valgrind tests

* update all-successful

* install

* executable

* fix redirect stuff

* Apply suggestions from code review
Co-authored-by: Guolin Ke <guolin.ke@outlook.com>

* more flags

* add mc to msvc proj

* fix memory leak in mc

* Update monotone_constraints.hpp

* Update r_package.yml

* remove R_INT64_PTR

* disable openmp

* Update gbdt_model_text.cpp

* Update gbdt_model_text.cpp

* Apply suggestions from code review

* try to free vector

* free more memories.

* Update src/boosting/gbdt_model_text.cpp

* fix using

* try the UNPROTECT(1);

* fix a const pointer

* fix Common

* reduce UNPROTECT

* remove UNPROTECT(1);

* fix null handle

* fix predictor

* use NULL after free

* fix a leaking in test

* try more fixes

* test the effect of tests

* throw exception in Fatal

* add test back

* Apply suggestions from code review

* commet some tests

* Apply suggestions from code review

* Apply suggestions from code review

* trying to comment out tests

* Update openmp_wrapper.h

* Apply suggestions from code review

* Update configure

* Update configure.ac

* trying to uncomment

* more comments

* more uncommenting

* more uncommenting

* fix comment

* more uncommenting

* uncomment fully-commented out stuff

* try uncommenting more dataset tests

* uncommenting more tests

* ok getting closer

* more uncommenting

* free dataset

* skipping a test, more uncommenting

* more skipping

* re-enable OpenMP

* allow on OpenMP thing

* move valgrind to comment-only job

* Apply suggestions from code review
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

* changes from code review

* Apply suggestions from code review
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

* linting

* issue comments too

* remove issue_comment
Co-authored-by: Guolin Ke <guolin.ke@outlook.com>
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

* [ci] ignore R CMD CHECK warnings on new R version

* just update version

This allows for network retries, to scale well with the
number of machines, and still retains the existing functionality
for cases with smaller num_machines ( 500 )

Fixes #3301
Co-authored-by: Aakarsh Gopi <aakarsh@vaticlabs.com>

* Modified script to also remove pragma warnings.

This also includes modifying the scope of the pragma removal.
Previously this script only searched inside the ./src/include/LightGMB directory.
This was not inclusive enough to remove the warnings in files shown in the ticket.

* Adds CI test that exits if unknown pragma warnings are present.

* Expanding pragma removal to cpp and hpp files.

* Update .ci/test_r_package.sh

Removing unneeded conditions since this script will only run on Linux and Mac builds anyway.
Co-authored-by: James Lamb <jaylamb20@gmail.com>

* Update .ci/test_r_package.sh

Fixes typo
Co-authored-by: James Lamb <jaylamb20@gmail.com>

* replacing double quotes with single quotes

* Using a more portable find syntax so it works on macOS and Linux
Co-authored-by: James Lamb <jaylamb20@gmail.com>

* [R-package] Updated lgb.train.R with keyword arguments

* [R-package] Updated lgb.train.R with keyword arguments

* [R-package] Updated lgb.train.R with keyword arguments

* Update dockerfile-cli-only-distroless.gpu

* Update README.md

* Update README.md

* [R-package] [docs] Reorganize installation instructions (fixes #3320)

* more changes

* remove ability to use precompiled lib_lightgbm

* remove language about installing from the CRAN section

* move installation stuff

* Apply suggestions from code review
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

* fix anchor
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

* [ci] add R CI job with UBSAN

* stuff

* fix command

* update template

* fail on errors

* spaces

* trigger by comment

* stuff

* add all CI back

* trying things

* run sanitizers as a regular job

* remove comments

* sanitizers

* try to trigger UBSAN

* try to trigger failure

* remove int overflow

* remove testing change

* Apply suggestions from code review
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

* added new GPU docker files

* removed maintainer label

~ Added 'noexcept' specifier and defaulted desctructor.
Co-authored-by: Lucas DAVID <lucas@isdom.isoft.fr>

* [R-package] update DESCRIPTION per CRAN comments

* newlines

* Apply suggestions from code review
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

* more fixes

* update Rbuildignore

* more changes

* more changes per CRAN response

* add email

* run examples in CI

* add newest CRAN response

* add Solaris patch

* update patch

* another attempt at ifaddrs patch

* fix unnecessary comment

* update configure

* comments

* bump version

* tabs

* fix address alignment, required by cran (#3415)

* fix dataset binary file alignment

* many fixes

* fix warnings

* fix bug

* Update file_io.cpp

* Update file_io.cpp

* simplify code

* Apply suggestions from code review

* general

* remove unneeded alignment

* Update file_io.h

* int32 to byte8 alignment

* Apply suggestions from code review

* Apply suggestions from code review

* [R-package] add new copyright holder in DESCRIPTION (#3409)

* [R-package] add new copyright holder in DESCRIPTION

* fix role

* fixing conflicts

* [R-package] add new copyright holder in DESCRIPTION (#3409)

* [R-package] add new copyright holder in DESCRIPTION

* fix role

* trying to fix conflicts

* more fixes

* this will work

* update cran-comments

* simplify solaris, add more testing docs

* stuff

* remove rchck docs

* Apply suggestions from code review
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

* remove extra use of cat()

* change solaris check

* update docs

* remove testing code

* fix warning about cleanup not having execute permissions

* fix cmake builds

* remove blank line
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>
Co-authored-by: Guolin Ke <guolin.ke@outlook.com>

* [R-package] [ci] Make Windows CI fail if R CMD check fails

* restore fix

* catch more errors

* remove testing

* fix processx calls

* try to get status code

* more logs

* trying something

* stuff

* previous changes

* uncomment

* [R-package] add 'cleanup' script to handle left-behind Makevars

* always install library for checkbashisms

see #3390. Also added isTRUE for some of the logical checks, please advise if this is okay

* rename R-package workflow

* Revert "[ci] fix R CMD check issue 'unable to verify current time' (#3341)"

This reverts commit 0038a662.

* Revert "Revert "[ci] fix R CMD check issue 'unable to verify current time' (#3341)""

This reverts commit e2307418aa7aa7b237f0eb46f43c0535473cf462.

* Update serial_tree_learner.cpp

* Update src/treelearner/serial_tree_learner.cpp

* stable multi-threading reduction

* Update src/treelearner/serial_tree_learner.cpp

* more fixes

* Apply suggestions from code review

* Apply suggestions from code review

* Update src/boosting/gbdt.cpp

* Update gbdt.cpp

* Update gbdt.cpp

* Apply suggestions from code review

* fix dataset binary file alignment

* many fixes

* fix warnings

* fix bug

* Update file_io.cpp

* Update file_io.cpp

* simplify code

* Apply suggestions from code review

* general

* remove unneeded alignment

* Update file_io.h

* int32 to byte8 alignment

* Apply suggestions from code review

* Apply suggestions from code review

* fix warnings

* Apply suggestions from code review

* Update feature_group.h

* Update feature_group.h

* Update src/treelearner/serial_tree_learner.cpp

* Update multiclass_metric.hpp

* [python] fix dangerous default for eval_at in LGBMRanker

* use a tuple

* five

* Update python-package/lightgbm/sklearn.py
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

[R-package] Fix incorrect num_iterations, early_stopping_round in saved models (fixes #2208, #2468) (#3368)

* params to string

* add tests

* more  tests

* stop skipping training continuation test (fixes #2468)

* remove unnecessary code

* [R-package] add new copyright holder in DESCRIPTION

* fix role

* [R-package] use keyword arguments in internal function calls

* empty commit

* Implement average precision score

* Fix lint errors

* Change name to average_precision

* Add to R-package list of metrics

* Empty commit to trigger CI jobs

* Change name to average_precision