GitLab

* new cuda framework

* add histogram construction kernel

* before removing multi-gpu

* new cuda framework

* tree learner cuda kernels

* single tree framework ready

* single tree training framework

* remove comments

* boosting with cuda

* optimize for best split find

* data split

* move boosting into cuda

* parallel synchronize best split point

* merge split data kernels

* before code refactor

* use tasks instead of features as units for split finding

* refactor cuda best split finder

* fix configuration error with small leaves in data split

* skip histogram construction of too small leaf

* skip split finding of invalid leaves

stop when no leaf to split

* support row wise with CUDA

* copy data for split by column

* copy data from host to CPU by column for data partition

* add synchronize best splits for one leaf from multiple blocks

* partition dense row data

* fix sync best split from task blocks

* add support for sparse row wise for CUDA

* remove useless code

* add l2 regression objective

* sparse multi value bin enabled for CUDA

* fix cuda ranking objective

* support for number of items <= 2048 per query

* speedup histogram construction by interleaving global memory access

* split optimization

* add cuda tree predictor

* remove comma

* refactor objective and score updater

* before use struct

* use structure for split information

* use structure for leaf splits

* return CUDASplitInfo directly after finding best split

* split with CUDATree directly

* use cuda row data in cuda histogram constructor

* clean src/treelearner/cuda

* gather shared cuda device functions

* put shared CUDA functions into header file

* change smaller leaf from <= back to < for consistent result with CPU

* add tree predictor

* remove useless cuda_tree_predictor

* predict on CUDA with pipeline

* add global sort algorithms

* add global argsort for queries with many items in ranking tasks

* remove limitation of maximum number of items per query in ranking

* add cuda metrics

* fix CUDA AUC

* remove debug code

* add regression metrics

* remove useless file

* don't use mask in shuffle reduce

* add more regression objectives

* fix cuda mape loss

add cuda xentropy loss

* use template for different versions of BitonicArgSortDevice

* add multiclass metrics

* add ndcg metric

* fix cross entropy objectives and metrics

* fix cross entropy and ndcg metrics

* add support for customized objective in CUDA

* complete multiclass ova for CUDA

* separate cuda tree learner

* use shuffle based prefix sum

* clean up cuda_algorithms.hpp

* add copy subset on CUDA

* add bagging for CUDA

* clean up code

* copy gradients from host to device

* support bagging without using subset

* add support of bagging with subset for CUDAColumnData

* add support of bagging with subset for dense CUDARowData

* refactor copy sparse subrow

* use copy subset for column subset

* add reset train data and reset config for CUDA tree learner

add deconstructors for cuda tree learner

* add USE_CUDA ifdef to cuda tree learner files

* check that dataset doesn't contain CUDA tree learner

* remove printf debug information

* use full new cuda tree learner only when using single GPU

* disable all CUDA code when using CPU version

* recover main.cpp

* add cpp files for multi value bins

* update LightGBM.vcxproj

* update LightGBM.vcxproj

fix lint errors

* fix lint errors

* fix lint errors

* update Makevars

fix lint errors

* fix the case with 0 feature and 0 bin

fix split finding for invalid leaves

create cuda column data when loaded from bin file

* fix lint errors

hide GetRowWiseData when cuda is not used

* recover default device type to cpu

* fix na_as_missing case

fix cuda feature meta information

* fix UpdateDataIndexToLeafIndexKernel

* create CUDA trees when needed in CUDADataPartition::UpdateTrainScore

* add refit by tree for cuda tree learner

* fix test_refit in test_engine.py

* create set of large bin partitions in CUDARowData

* add histogram construction for columns with a large number of bins

* add find best split for categorical features on CUDA

* add bitvectors for categorical split

* cuda data partition split for categorical features

* fix split tree with categorical feature

* fix categorical feature splits

* refactor cuda_data_partition.cu with multi-level templates

* refactor CUDABestSplitFinder by grouping task information into struct

* pre-allocate space for vector split_find_tasks_ in CUDABestSplitFinder

* fix misuse of reference

* remove useless changes

* add support for path smoothing

* virtual destructor for LightGBM::Tree

* fix overlapped cat threshold in best split infos

* reset histogram pointers in data partition and spllit finder in ResetConfig

* comment useless parameter

* fix reverse case when na is missing and default bin is zero

* fix mfb_is_na and mfb_is_zero and is_single_feature_column

* remove debug log

* fix cat_l2 when one-hot

fix gradient copy when data subset is used

* switch shared histogram size according to CUDA version

* gpu_use_dp=true when cuda test

* revert modification in config.h

* fix setting of gpu_use_dp=true in .ci/test.sh

* fix linter errors

* fix linter error

remove useless change

* recover main.cpp

* separate cuda_exp and cuda

* fix ci bash scripts

add description for cuda_exp

* add USE_CUDA_EXP flag

* switch off USE_CUDA_EXP

* revert changes in python-packages

* more careful separation for USE_CUDA_EXP

* fix CUDARowData::DivideCUDAFeatureGroups

fix set fields for cuda metadata

* revert config.h

* fix test settings for cuda experimental version

* skip some tests due to unsupported features or differences in implementation details for CUDA Experimental version

* fix lint issue by adding a blank line

* fix lint errors by resorting imports

* fix lint errors by resorting imports

* fix lint errors by resorting imports

* merge cuda.yml and cuda_exp.yml

* update python version in cuda.yml

* remove cuda_exp.yml

* remove unrelated changes

* fix compilation warnings

fix cuda exp ci task name

* recover task

* use multi-level template in histogram construction

check split only in debug mode

* ignore NVCC related lines in parameter_generator.py

* update job name for CUDA tests

* apply review suggestions

* Update .github/workflows/cuda.yml
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

* Update .github/workflows/cuda.yml
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

* update header

* remove useless TODOs

* remove [TODO(shiyu1994): constrain the split with min_data_in_group] and record in #5062

* #include <LightGBM/utils/log.h> for USE_CUDA_EXP only

* fix include order

* fix include order

* remove extra space

* address review comments

* add warning when cuda_exp is used together with deterministic

* add comment about gpu_use_dp in .ci/test.sh

* revert changing order of included headers
Co-authored-by: Yu Shi <shiyu1994@qq.com>
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

* Turn `early_stopping` into a Callable class

* Fix

* Lint

* Remove print

* Fix order

* Revert "Lint"

This reverts commit 7ca8b557572446888cf793c0082d9a7efd1e29a7.

* Apply suggestion from code review

* Nit

* Lint

* Move callable class outside the func for pickling

* Move _pickle and _unpickle to tests utils

* Add early stopping callback picklability test

* Nit

* Fix

* Lint

* Improve type hint

* Lint

* Lint

* Add cloudpickle to test_windows

* Update tests/python_package_test/test_engine.py

* Fix

* Apply suggestions from code review

* Update test_windows.ps1

* Update .appveyor.yml

* Update test_windows.ps1

* Update .appveyor.yml

* [ci] [docs] use mamba for readthedocs builds (fixes #4954)

* update docs

* simplify build script and add docs flag to gitignore

* exit with non-0 if build fails

* update CI job

* add doxygen

* remove outdated requirement_base.txt reference

* use conda create instead of conda env create

* fix conda create flags

* add nodefaults to env.yml

* Update docs/README.rst
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

* try to fix check-docs CI job

* additional changes

* switch from mamba to miniforge

* simplify docker command and fix issues in local build script

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

* update docs and conda

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

* Update dockerfile-python

* Update README.md

* Update dockerfile.gpu

* Update dockerfile.gpu

* Update .vsts-ci.yml

* Update .appveyor.yml

* Update test_windows.ps1

* [ci] use conda-forge in CI jobs (fixes #4948)

* comment out more jobs

* try reverting graphviz patch, running more cuda jobs

* get graphviz from PyPI and try removing some patches for r-lintr

* start running appveyor again

* use conda-forge if using conda

* fix commands

* conda install graphviz

* try newer openmp

* pin below openmp 11.x

* focus on gpu task

* trying to narrow down error

* maybe gcc11 is the issue

* start adding other tests back

* pin openmp too

* maybe need to pin to gcc less than 10.x

* pin libgfortran and libstdcxx as well

* pin to gcc 9.3.0

* move constraints up to initial environment

* add all CI jobs back

* try installing python-graphviz separately

* try new lightgbm/vsts-agent image

* fix typo

* test if pinning gcc for linux gpu_source build is still necessary

* ok yes, pinning gcc is necessary

* test if Linux gpu_source works with Python 3.9.6

* no special exception for Linux gpu_source job

* pin to Python 3.9.6 in Linux gpu_source

* try explicitly asking for libstdcxx-ng for every linux build

* swap compilers

* switch compilers back

* revert accidental whitespace change

* comment out CI

* try Linux gpu_source with different Python versions

* Revert "try Linux gpu_source with different Python versions"

This reverts commit f6f63cbb9b4a9cf138f3580ae4223a8acdd0e94a.

* Revert "comment out CI"

This reverts commit ece191f01e3650c2f325e80ff86bfc8c485fb7bc.

* remove libxml2 install, change CONDA path

* avoid installing conda in rchk job

* empty commit 1

* empty commit 2

* empty commit 3

* empty commit 4

* add more verbose logging around installation of python-graphviz

* empty commit 1

* get mamba info

* get more conda info

* add another mamba info call

* allow for other macOS environments in GHA configuration

* Revert "allow for other macOS environments in GHA configuration"

This reverts commit a3c7a19926be94e3719f5ae9100fbe30e87b35da.

* get more logs from mamba

* get Build.ArtifactsStagingDirectory

* get more logs and try to force re-installing everything

* clean cache after every step

* remove --update-all and make logs less verbose

* remove more print statements and uncomment jobs

* test if conda-clean issue fixes segfaults for gpu_source

* pin python version for gpu_source

* empty commit 1

* use miniforge instead

* empty commit 1

* Apply suggestions from code review

* bring workarounds back

* remove duplicated graphviz system-wide installation (reverts #4095, #4097, #4238)

* empty commit 1

* empty commit 2

* empty commit 3

* empty commit 4

* empty commit 5

* empty commit 6

* empty commit 7

* empty commit 8

* empty commit 9

* empty commit 10

* empty commit 10

* empty commit 10

* empty commit 10

* empty commit 11

* one more try

* try to downgrade Python version for Linux GPU job

* swap compilers

* Revert "swap compilers"

This reverts commit f04dc27b17920a69cbcba1254a8e109ce9791154.
Co-authored-by: Nikita Titov <nekit94-12@hotmail.com>
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

* [ci] manually create symlinks to R entrypoints on macOS (fixes #4988)

* exclude non-R CI jobs

* upgrade to R 4.1.2

* get logs for R install

* pin R 4.1.x jobs to macOS-10.15

* update to R 4.1.2 on Windows

* allow for non-latest macOS builds in GHA configuration

* fix prefix check

* fix config check

* more direct check for mac version

* uncomment other CIs

* update R version in CI job names

* Revert "[ci] ignore certificates for kitware apt channel in CUDA jobs (fixes #4646) (#4648)"

This reverts commit 10e0edc4.

* update cuda at CI

* Update .appveyor.yml

* Update .vsts-ci.yml

* Update python_package.yml

* Update setup.py

* Update test.sh

* Update .vsts-ci.yml

* Update setup.sh

* Update .vsts-ci.yml

* Update test.sh

* Update README.rst

* [R-package] [docs] add intro vignette (#3946)

* add 10 test vignettes

* Revert "add 10 test vignettes"

This reverts commit 40fb2e2f1982402798776ee44e4ec82fc4644d3d.

* Apply suggestions from code review
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>
Co-authored-by: Michael Mayer <mayermichael79@gmail.com>
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

* Update get_workflow_status.py

* Update get_workflow_status.py

* Update test.sh

* Update test.sh

* Update test.sh

* Update FindLibR.cmake

* Update r_package.yml

* Update FindLibR.cmake

* Update r_package.yml

* Update CMakeLists.txt

* Update CMakeLists.txt

* Update static_analysis.yml

* Update CMakeLists.txt

* Update test.sh

* Update CMakeLists.txt

* Update static_analysis.yml

* [R-package] parallelize compilation in CMake-based builds

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

* working on adding -j

* pass -j through to install.libs.R

* add docs on -j

* use -j4

* Update R-package/README.md
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

This reverts commit d62378b4.

* pin Dask version at CI

* Update .vsts-ci.yml

* Update .vsts-ci.yml

* workaround for Python 3.6

* Update test.sh

* [ci] use wch1/r-debug image in Solaris tests

* no git in valgrind tests

* [R-package] allow use of custom R executable building CRAN package

* Update build-cran-package.sh
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

* indicate support of Monterey and drop Catalina

* Update test.sh

* restore Mojave

* Update test_windows.ps1

* Update .appveyor.yml

* Update .appveyor.yml

* Use the latest gcc version in macOS CI jobs

* test: swap compilers

* Revert "test: swap compilers"

* Revert "test: swap compilers"

* [ci] ignore certificates for kitware apt channel in CUDA jobs (fixes #4646)

* try building from a fork

* Update .gitmodules

* Reffer to string type as `str` and and commas in `list of ...` types

* update `libpath.py` too

* [ci] upgrade R to 4.1.1

* try moving miktex errors

* [R-package] use C++ compiler for pre-compile checks on Windows

* install Matrix in valgrind test

* Add {Matrix} in more places in CI and docs

* use CXX11

* use flags specific to C++11

* missing backtick
Co-authored-by: Nikita Titov <nekit94-12@hotmail.com>

* [ci] move Solaris and valgrind test steps into scripts

* Update .github/workflows/r_solaris.yml
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

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

* remove preinstalled possibly conflicting software from PATH in CI jobs

* preserve pandoc

* [ci] add CI job running rchk

* try commenting out more stuff

* ignore R internal error

* pipes

* remove PROTECT()

* try removing testthat

* revert temporary testing changes

* call predict on one row of data to determine output shape

* make DaskLGBMRanker predict method equal to the others

* remove extra drop_axis

* [python-package] create Dataset from sampled data.

* [python-package] create Dataset from List[Sequence].

1. Use random access for data sampling
2. Support read data from multiple input files
3. Read data in batch so no need to hold all data in memory

* [python-package] example: create Dataset from multiple HDF5 file.

* fix: revert is_class implementation for seq

* fix: unwanted memory view reference for seq

* fix: seq is_class accepts sklearn matrices

* fix: requirements for example

* fix: pycode

* feat: print static code linting stage

* fix: linting: avoid shell str regex conversion

* code style: doc style

* code style: isort

* fix ci dependency: h5py on windows

* [py] remove rm files in test seq
https://github.com/microsoft/LightGBM/pull/4089#discussion_r612929623

* docs(python): init_from_sample summary

https://github.com/microsoft/LightGBM/pull/4089#discussion_r612903389



* remove dataset dump sample data debugging code.

* remove typo fix.

Create separate PR for this.

* fix typo in src/c_api.cpp
Co-authored-by: James Lamb <jaylamb20@gmail.com>

* style(linting): py3 type hint for seq

* test(basic): os.path style path handling

* Revert "feat: print static code linting stage"

This reverts commit 10bd79f7f8258bea8e61c3abb8c9c7e4456a916d.

* feat(python): sequence on validation set

* minor(python): comment

* minor(python): test option hint

* style(python): fix code linting

* style(python): add pydoc for ref_dataset

* doc(python): sequence
Co-authored-by: shiyu1994 <shiyu_k1994@qq.com>

* revert(python): sequence class abc

* chore(python): remove rm_files

* Remove useless static_assert.

* refactor: test_basic test for sequence.

* fix lint complaint.

* remove dataset._dump_text in sequence test.

* Fix reverting typo fix.

* Apply suggestions from code review
Co-authored-by: James Lamb <jaylamb20@gmail.com>

* Fix type hint, code and doc style.

* fix failing test_basic.

* Remove TODO about keep constant in sync with cpp.

* Install h5py only when running python-examples.

* Fix lint complaint.

* Apply suggestions from code review
Co-authored-by: James Lamb <jaylamb20@gmail.com>

* Doc fixes, remove unused params_str in __init_from_seqs.

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

* Remove unnecessary conda install in windows ci script.

* Keep param as example in dataset_from_multi_hdf5.py

* Add _get_sample_count function to remove code duplication.

* Use batch_size parameter in generate_hdf.

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

* Fix after applying suggestions.

* Fix test, check idx is instance of numbers.Integral.

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

* Expose Sequence class in Python-API doc.

* Handle Sequence object not having batch_size.

* Fix isort lint complaint.

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

* Update docstring to mention Sequence as data input.

* Remove get_one_line in test_basic.py

* Make Sequence an abstract class.

* Reduce number of tests for test_sequence.

* Add c_api: LGBM_SampleCount, fix potential bug in LGBMSampleIndices.

* empty commit to trigger ci

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

* Rename to LGBM_GetSampleCount, change LGBM_SampleIndices out_len to int32_t.

Also rename total_nrow to num_total_row in c_api.h for consistency.

* Doc about Sequence in docs/Python-Intro.rst.

* Fix: basic.py change LGBM_SampleIndices out_len to int32.

* Add create_valid test case with Dataset from Sequence.

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

* Apply suggestions from code review
Co-authored-by: shiyu1994 <shiyu_k1994@qq.com>

* Remove no longer used DEFAULT_BIN_CONSTRUCT_SAMPLE_CNT.

* Update python-package/lightgbm/basic.py
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>
Co-authored-by: Willian Zhang <willian@willian.email>
Co-authored-by: Willian Z <Willian@Willian-Zhang.com>
Co-authored-by: James Lamb <jaylamb20@gmail.com>
Co-authored-by: shiyu1994 <shiyu_k1994@qq.com>
Co-authored-by: Nikita Titov <nekit94-08@mail.ru>

* run cpp tests with sanitizers

* re-trigger CI

* continue

* small cleanup

* restore cpp test