david-cortes
4546a8fded
[R-package] Use `cat()` instead of `print()` for metrics and callbacks ( #6171 )
2023-11-02 07:36:03 -05:00
Oliver Borchert
3405ee82b9
[python-package] Allow to pass Arrow table as training data ( #6034 )
2023-11-01 08:21:48 -05:00
James Lamb
fcf76bceb9
[ci] resolve warning in tests ( #6154 )
2023-10-26 12:58:21 -05:00
Oliver Borchert
2d358d5d20
[ci] use `mamba` instead of `conda` in macOS and Linux CI jobs ( #6140 )
2023-10-25 09:48:42 -05:00
James Lamb
8ed371cee4
set explicit number of threads in every OpenMP `parallel` region ( #6135 )
2023-10-09 20:05:51 -05:00
James Lamb
992f505665
factor out uses of omp_get_num_threads() and omp_get_max_threads() outside of OpenMP wrapper ( #6133 )
2023-10-08 22:43:49 -05:00
James Lamb
ad0255188c
remove unnecessary allocations in HistogramSumReducer ( #6132 )
2023-10-08 20:35:08 -05:00
shiyu1994
f901f47141
[CUDA] CUDA Quantized Training ( fixes #5606 ) ( #5933 )
...
* add quantized training (first stage)
* add histogram construction functions for integer gradients
* add stochastic rounding
* update docs
* fix compilation errors by adding template instantiations
* update files for compilation
* fix compilation of gpu version
* initialize gradient discretizer before share states
* add a test case for quantized training
* add quantized training for data distributed training
* Delete origin.pred
* Delete ifelse.pred
* Delete LightGBM_model.txt
* remove useless changes
* fix lint error
* remove debug loggings
* fix mismatch of vector and allocator types
* remove changes in main.cpp
* fix bugs with uninitialized gradient discretizer
* initialize ordered gradients in gradient discretizer
* disable quantized training with gpu and cuda
fix msvc compilation errors and warnings
* fix bug in data parallel tree learner
* make quantized training test deterministic
* make quantized training in test case more accurate
* refactor test_quantized_training
* fix leaf splits initialization with quantized training
* check distributed quantized training result
* add cuda gradient discretizer
* add quantized training for CUDA version in tree learner
* remove cuda computability 6.1 and 6.2
* fix parts of gpu quantized training errors and warnings
* fix build-python.sh to install locally built version
* fix memory access bugs
* fix lint errors
* mark cuda quantized training on cuda with categorical features as unsupported
* rename cuda_utils.h to cuda_utils.hu
* enable quantized training with cuda
* fix cuda quantized training with sparse row data
* allow using global memory buffer in histogram construction with cuda quantized training
* recover build-python.sh
enlarge allowed package size to 100M
2023-10-08 23:25:46 +08:00
James Lamb
3d9ada7657
[ci] [R-package] enforce more {lintr} checks ( #6130 )
2023-10-08 09:42:54 -05:00
José Morales
b793cd821c
ignore unknown parameters when loading from model file ( #6126 )
2023-10-06 22:43:40 -05:00
James Lamb
8f577de01f
fix compiler warnings for CPP tests ( #6124 )
2023-10-06 12:11:53 -05:00
James Lamb
3c7e38be27
[ci] [R-package] test against R 4.3 on Windows ( #6061 )
2023-10-06 08:21:32 -05:00
James Lamb
d45dca702e
[python-package] reorganize early stopping callback ( #6114 )
2023-10-05 12:45:51 -05:00
James Lamb
f175cebd2d
[python-package] simplify Dataset._compare_params_for_warning() ( #6120 )
2023-10-02 23:08:32 -05:00
James Lamb
63a882b740
[CUDA] drop CUDA 10 support, start supporting CUDA 12 ( fixes #5789 ) ( #6099 )
2023-09-30 08:34:50 -05:00
James Lamb
b7418dc8c9
[ci] fix sh-compatibility issue in build-cran-package.sh ( #6118 )
2023-09-29 11:00:25 -05:00
James Lamb
60a4a13e72
[python-package] remove unnecessary allocations in ctypes code ( #6111 )
2023-09-25 10:50:35 -05:00
James Lamb
7c9a985a47
[python-package] fix mypy errors in Dataset construction ( #6106 )
2023-09-21 21:37:03 -05:00
James Lamb
fe7f8fe646
[ci] ensure correct R version is used on GitHub Actions ( fixes #5640 ) ( #6107 )
2023-09-20 10:31:43 -05:00
James Lamb
aa489f43a9
[python-package] fix mypy error about eval result tuples ( #6105 )
2023-09-19 15:22:34 -05:00
James Lamb
646dfed913
[python-package] fix mypy error from Dataset.pandas_categorical ( #6098 )
2023-09-18 21:46:16 -05:00
Oliver Borchert
5792b5b21e
[ci] Fix typo in dependencies ( #6100 )
2023-09-14 21:47:57 -05:00
James Lamb
ab1eaa832d
[python-package] [R-package] include more params in model text representation ( fixes #6010 ) ( #6077 )
2023-09-13 17:35:38 -05:00
James Lamb
163416d2f5
[python-package] fix mypy errors related to eval result parsing in callbacks ( #6096 )
2023-09-13 15:38:16 -05:00
James Lamb
0b3d9da2eb
[python-package] mark EarlyStopException as part of public API ( #6095 )
2023-09-13 13:47:31 -05:00
James Lamb
1a6e6ff9f5
[python-package] fix mypy errors related to eval result tuples ( #6097 )
2023-09-13 11:43:08 -05:00
James Lamb
921479b99f
update to fmt 10.1.1, fast_double_parser 0.7.0 ( #6074 )
2023-09-12 13:40:41 -05:00
shiyu1994
a92bf3742b
[fix] fix quantized training ( fixes #5982 ) ( fixes #5994 ) ( #6092 )
...
* fix leaf splits update after split in quantized training
* fix preparation ordered gradients for quantized training
* remove force_row_wise in distributed test for quantized training
* Update src/treelearner/leaf_splits.hpp
---------
Co-authored-by: James Lamb <jaylamb20@gmail.com>
2023-09-13 01:06:20 +08:00
James Lamb
cd39520c5e
bump development version to 4.1.0.99 ( #6090 )
2023-09-12 09:04:11 -05:00
david-cortes
5e592fe6ff
[python-package] Fix misdetected objective after multiple calls to `LGBMClassifier.fit` ( #6002 )
2023-09-11 21:53:36 -05:00
James Lamb
501ce1cb63
Release v4.1.0 ( #6076 )
2023-09-11 17:12:29 -05:00
Shinichi Hemmi
68621628ce
[python-package] [docs] Update key format of eval_hist in docstring example ( #5980 )
2023-09-08 15:34:05 -05:00
James Lamb
04b66e0662
[docs] add vaex-ml to list of external repositories ( #6085 )
2023-09-08 11:29:56 -05:00
James Lamb
e9fface2f7
[ci] [docs] fix broken ACM links ( #6083 )
2023-09-07 15:44:40 -05:00
Oliver Borchert
1d7ee63686
Remove superfluous todo from gitignore ( #6081 )
2023-09-06 13:00:18 -05:00
James Lamb
ee51120118
[python-package] simplify processing of pandas data ( #6066 )
2023-09-06 08:14:20 -05:00
mjmckp
8203306400
Fix updates in random forest model using GOSS data sample strategy ( #6017 )
2023-09-04 20:34:35 -05:00
James Lamb
5ea005790e
[ci] [R-package] test against R 4.3 on Linux and macOS ( #6075 )
2023-09-04 11:09:30 -05:00
david-cortes
bca716cc3c
[R-package] Fix misdetected objective when passing `lgb.Dataset` instance to `lightgbm()` ( #6005 )
2023-09-04 09:44:58 -05:00
Pavel Metrikov
7e34d23c05
Treat position bias via GAM in LambdaMART ( #5929 )
...
* Update dataset.h
* Update metadata.cpp
* Update rank_objective.hpp
* Update metadata.cpp
* Update rank_objective.hpp
* Update metadata.cpp
* Update dataset.h
* Update rank_objective.hpp
* Update metadata.cpp
* Update test_engine.py
* Update test_engine.py
* Add files via upload
* Update test_engine.py
* Update test_engine.py
* Update test_engine.py
* Update test_engine.py
* Update test_engine.py
* Update _rank.train.position
* Update test_engine.py
* Update test_engine.py
* Update test_engine.py
* Update test_engine.py
* Update _rank.train.position
* Update _rank.train.position
* Update test_engine.py
* Update _rank.train.position
* Update test_engine.py
* Update test_engine.py
* Update test_engine.py
* Update test_engine.py
* Update test_engine.py
* Update the position of import statement
* Update rank_objective.hpp
* Update config.h
* Update config_auto.cpp
* Update rank_objective.hpp
* Update rank_objective.hpp
* update documentation
* remove extra blank line
* Update src/io/metadata.cpp
Co-authored-by: James Lamb <jaylamb20@gmail.com>
* Update src/io/metadata.cpp
Co-authored-by: James Lamb <jaylamb20@gmail.com>
* remove _rank.train.position
* add position in python API
* fix set_positions in basic.py
* Update Advanced-Topics.rst
* Update Advanced-Topics.rst
* Update Advanced-Topics.rst
* Update Advanced-Topics.rst
* Update Advanced-Topics.rst
* Update Advanced-Topics.rst
* Update Advanced-Topics.rst
* Update Advanced-Topics.rst
* Update Advanced-Topics.rst
* Update Advanced-Topics.rst
* Update Advanced-Topics.rst
* Update docs/Advanced-Topics.rst
Co-authored-by: James Lamb <jaylamb20@gmail.com>
* Update docs/Advanced-Topics.rst
Co-authored-by: James Lamb <jaylamb20@gmail.com>
* Update Advanced-Topics.rst
* Update Advanced-Topics.rst
* Update Advanced-Topics.rst
* Update Advanced-Topics.rst
* remove List from _LGBM_PositionType
* move new position parameter to the last in Dataset constructor
* add position_filename as a parameter
* Update docs/Advanced-Topics.rst
Co-authored-by: James Lamb <jaylamb20@gmail.com>
* Update docs/Advanced-Topics.rst
Co-authored-by: James Lamb <jaylamb20@gmail.com>
* Update Advanced-Topics.rst
* Update src/objective/rank_objective.hpp
Co-authored-by: James Lamb <jaylamb20@gmail.com>
* Update src/io/metadata.cpp
Co-authored-by: James Lamb <jaylamb20@gmail.com>
* Update metadata.cpp
* Update python-package/lightgbm/basic.py
Co-authored-by: James Lamb <jaylamb20@gmail.com>
* Update python-package/lightgbm/basic.py
Co-authored-by: James Lamb <jaylamb20@gmail.com>
* Update python-package/lightgbm/basic.py
Co-authored-by: James Lamb <jaylamb20@gmail.com>
* Update python-package/lightgbm/basic.py
Co-authored-by: James Lamb <jaylamb20@gmail.com>
* Update src/io/metadata.cpp
Co-authored-by: James Lamb <jaylamb20@gmail.com>
* more infomrative fatal message
address more comments
* update documentation for more flexible position specification
* fix SetPosition
add tests for get_position and set_position
* remove position_filename
* remove useless changes
* Update python-package/lightgbm/basic.py
Co-authored-by: James Lamb <jaylamb20@gmail.com>
* remove useless files
* move position file when position set in Dataset
* warn when positions are overwritten
* skip ranking with position test in cuda
* split test case
* remove useless import
* Update test_engine.py
* Update test_engine.py
* Update test_engine.py
* Update docs/Advanced-Topics.rst
Co-authored-by: James Lamb <jaylamb20@gmail.com>
* Update Parameters.rst
* Update rank_objective.hpp
* Update config.h
* update config_auto.cppp
* Update docs/Advanced-Topics.rst
Co-authored-by: James Lamb <jaylamb20@gmail.com>
* fix randomness in test case for gpu
---------
Co-authored-by: shiyu1994 <shiyu_k1994@qq.com>
Co-authored-by: James Lamb <jaylamb20@gmail.com>
2023-09-04 17:05:46 +08:00
James Lamb
1881a50178
reduce verbosity of some log messages ( #6073 )
2023-09-03 13:41:01 -05:00
Kyle Engel
2cae109b32
[docs] Fix typo in README ( #6071 )
2023-09-01 20:24:48 -05:00
James Lamb
858eeb54a2
[docs] fix broken links ( #6059 )
2023-08-23 12:21:46 -04:00
James Lamb
32a5dbea98
[python-package] remove CVBooster._append() ( #6057 )
2023-08-22 23:13:56 -04:00
James Lamb
4ea170f30a
[python-package] use dataclass for CallbackEnv ( #6048 )
2023-08-21 12:05:37 -05:00
James Lamb
5fe84f8f3b
[python-package] make it possible to build wheels without internet connection ( fixes #5979 ) ( #6042 )
2023-08-20 20:24:55 -05:00
James Lamb
c60bc739b0
[ci] [python-package] add more linting checks ( #6049 )
2023-08-19 07:01:28 -05:00
James Lamb
aafdf7415c
[ci] prevent lock-threads from locking issues with label 'feature request' ( #6047 )
2023-08-18 21:55:39 -05:00
James Lamb
7a801f7b7b
[ci] add bot to lock inactive issues and PRs ( #6037 )
2023-08-15 15:12:16 -05:00
James Lamb
e0d63b5735
[ci] fix GPG key download for R Linux jobs ( fixes #6038 ) ( #6039 )
...
* [ci] fix GPG key download for R Linux jobs
* force use of the new config file
* empty commit
2023-08-15 10:12:31 +08:00