Skip to content

GitLab

Switch branch/tag
  1. 10 Nov, 2020 1 commit
  3. 30 Oct, 2020 1 commit
  5. 29 Oct, 2020 1 commit
  7. 27 Oct, 2020 1 commit
    • Pavel Metrikov's avatar
      Add support to optimize for NDCG at a given truncation level (#3425) · ba0a1f8d
      Pavel Metrikov authored 
      

* 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: default avatarGuolin 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: default avatarGuolin Ke <guolin.ke@outlook.com>

* Update Parameters.rst
Co-authored-by: default avatarGuolin Ke <guolin.ke@outlook.com>
Co-authored-by: default avatarJames Lamb <jaylamb20@gmail.com>
      ba0a1f8d
  9. 26 Oct, 2020 1 commit
    • Guolin Ke's avatar
      Fix add features (#2754) · 53977f36
      Guolin Ke authored 
      

* 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: default avatarStrikerRUS <nekit94-12@hotmail.com>
Co-authored-by: default avatarNikita Titov <nekit94-08@mail.ru>
      53977f36
  11. 23 Sep, 2020 1 commit
    • Belinda Trotta's avatar
      Average precision score (#3347) · 28704900
      Belinda Trotta authored 
      * 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
      28704900
  13. 21 Sep, 2020 2 commits
  15. 20 Sep, 2020 1 commit
    • Belinda Trotta's avatar
      Auc mu weights (#3349) · 1782fcb1
      Belinda Trotta authored 
      * Update auc_mu metric to use data weights if provided

* Calculate class sizes and total weights in Init so we only do it once

* Fix lint error

* Empty commit to trigger CI jobs
      1782fcb1
  17. 06 Sep, 2020 1 commit
  19. 02 Sep, 2020 1 commit
  21. 11 Aug, 2020 2 commits
  23. 06 Aug, 2020 1 commit
  25. 02 Aug, 2020 1 commit
  27. 30 Jul, 2020 1 commit
  29. 15 Jul, 2020 1 commit
  31. 14 Jul, 2020 1 commit
  33. 28 Jun, 2020 2 commits
    • Ilya Matiach's avatar
      adding sparse support to TreeSHAP in lightgbm (#3000) · 9f367d11
      Ilya Matiach authored 
      * adding sparse support to TreeSHAP in lightgbm

* updating based on comments

* updated based on comments, used fromiter instead of frombuffer

* updated based on comments

* fixed limits import order

* fix sparse feature contribs to work with more than int32 max rows

* really fixed int64 max error and build warnings

* added sparse test with >int32 max rows

* fixed python side reshape check on sparse data

* updated based on latest comments

* fixed comments

* added CSC INT32_MAX validation to test, fixed comments
      9f367d11
    • Belinda Trotta's avatar
      Fix bug with interaction constraints (#3189) · d563aff9
      Belinda Trotta authored 
      * Fix bug: crashes when interaction_constraints is nonempty and not all features are used.

* Fix python lint error.
      d563aff9
  35. 27 Jun, 2020 1 commit
    • Alex's avatar
      [python][scikit-learn] new stacking tests and make number of features a property (#3173) · 72849466
      Alex authored 
      * modify attribute and include stacking tests

* backwards compatibility

* check sklearn version

* move stacking import

* Number of input features (#3173)

* Number of input features (#3173)

* Number of input features (#3173)

* Number of input features (#3173)

Split number of features and stacking tests.

* Number of input features (#3173)

Modify test name.

* Number of input features (#3173)

Update stacking tests for review comments.

* Number of input features (#3173)

* Number of input features (#3173)

* Number of input features (#3173)

* Number of input features (#3173)

Modify classifier test.

* Number of input features (#3173)

* Number of input features (#3173)

Check score.
      72849466
  37. 23 Jun, 2020 1 commit
    • Belinda Trotta's avatar
      Interaction constraints (#3126) · bca2da97
      Belinda Trotta authored 
      * Add interaction constraints functionality.

* Minor fixes.

* Minor fixes.

* Change lambda to function.

* Fix gpu bug, remove extra blank lines.

* Fix gpu bug.

* Fix style issues.

* Try to fix segfault on MACOS.

* Fix bug.

* Fix bug.

* Fix bugs.

* Change parameter format for R.

* Fix R style issues.

* Change string formatting code.

* Change docs to say R package not supported.

* Remove R functionality, moving to separate PR.

* Keep track of branch features in tree object.

* Only track branch features when feature interactions are enabled.

* Fix lint error.

* Update docs and simplify tests.
      bca2da97
  39. 11 Jun, 2020 1 commit
  41. 03 May, 2020 1 commit
    • Belinda Trotta's avatar
      Path smoothing (#2950) · e50a9151
      Belinda Trotta authored 
      * Path smoothing

* Try to fix issue with gpu version.

* Fix failing CI for R package.

* Minor fixes.

* Minor refactor.

* Restore old code to get CI working.

* Fix style issues.

* Fix ci for R package.

* Minor fixes for docs and code style.

* Update docs.
      e50a9151
  43. 30 Apr, 2020 1 commit
  45. 25 Apr, 2020 1 commit
  47. 10 Apr, 2020 2 commits
  49. 09 Apr, 2020 1 commit
    • CharlesAuguste's avatar
      Pr3 monotone constraints splits penalization (#2939) · 505a145f
      CharlesAuguste authored 
      

* Add the monotone penalty parameter to the config.

* Pass tree in the necessary functions so it can be used in ComputeBestSplitForFeature.

* Add monotone penalty.

* Added link to the original report.

* Add tests.

* Fix GPU.

* Revert "Pass tree in the necessary functions so it can be used in ComputeBestSplitForFeature."

This reverts commit 37757e8e8f3a2c82a604f4af9a926da616660d2e.

* Revert "Fix GPU."

This reverts commit e49eeee41c883f3c97fd5cdbd53c9288094bffb6.

* Added a shared pointer to the tree so the constraints can use it too.

* Moved check on monotone penalty to config.cpp.

* Python linting.

* Use AssertTrue instead of assert_.

* Fix penalization in test.

* Make GPU deterministic in tests.

* Rename tree to tree_ in monotone constraints.

* Replaced epsilon by kEplison.

* Typo.

* Make tree pointer const.

* Update src/treelearner/monotone_constraints.hpp
Co-Authored-By: default avatarGuolin Ke <guolin.ke@outlook.com>

* Update src/treelearner/monotone_constraints.hpp
Co-Authored-By: default avatarGuolin Ke <guolin.ke@outlook.com>

* Added alias for the penalty.

* Remove useless comment.

* Save CI time.

* Refactor test_monotone_penalty_max.

* Update include/LightGBM/config.h
Co-Authored-By: default avatarNikita Titov <nekit94-08@mail.ru>

* Fix doc to be in line with previous config change commit.
Co-authored-by: default avatarCharles Auguste <auguste@dubquantdev801.ire.susq.com>
Co-authored-by: default avatarGuolin Ke <guolin.ke@outlook.com>
Co-authored-by: default avatarNikita Titov <nekit94-08@mail.ru>
      505a145f
  51. 23 Mar, 2020 1 commit
    • CharlesAuguste's avatar
      Improving monotone constraints ("Fast" method; linked to #2305, #2717) (#2770) · a8c1e0a1
      CharlesAuguste authored 
      

* Add util functions.

* Added monotone_constraints_method as a parameter.

* Add the intermediate constraining method.

* Updated tests.

* Minor fixes.

* Typo.

* Linting.

* Ran the parameter generator for the doc.

* Removed usage of the FeatureMonotone function.

* more fixes

* Fix.

* Remove duplicated code.

* Add debug checks.

* Typo.

* Bug fix.

* Disable the use of intermediate monotone constraints and feature sampling at the same time.

* Added an alias for monotone constraining method.

* Use the right variable to get the number of threads.

* Fix DEBUG checks.

* Add back check to determine if histogram is splittable.

* Added forgotten override keywords.

* Perform monotone constraint update only when necessary.

* Small refactor of FastLeafConstraints.

* Post rebase commit.

* Small refactor.

* Typo.

* Added comment and slightly improved logic of monotone constraints.

* Forgot a const.

* Vectors that are to be modified need to be pointers.

* Rename FastLeafConstraints to IntermediateLeafConstraints to match documentation.

* Remove overload of GoUpToFindLeavesToUpdate.

* Stop memory leaking.

* Fix cpplint issues.

* Fix checks.

* Fix more cpplint issues.

* Refactor config monotone constraints method.

* Typos.

* Remove useless empty lines.

* Add new line to separate includes.

* Replace unsigned ind by size_t.

* Reduce number of trials in tests to decrease CI time.

* Specify monotone constraints better in tests.

* Removed outer loop in test of monotone constraints.

* Added categorical features to the monotone constraints tests.

* Add blank line.

* Regenerate parameters automatically.

* Speed up ShouldKeepGoingLeftRight.
Co-authored-by: default avatarCharles Auguste <auguste@dubquantdev801.ire.susq.com>
Co-authored-by: default avatarguolinke <guolin.ke@outlook.com>
      a8c1e0a1
  53. 20 Mar, 2020 1 commit
    • Lukas Pfannschmidt's avatar
      [python] handle RandomState object in Scikit-learn Api (#2904) · cf0a992e
      Lukas Pfannschmidt authored 
      

* Add handling of RandomState object, which is standard for sklearn methods.

LightGBM expects an integer seed instead of an object.
If passed object is RandomState, we choose random integer based on its state to seed the underlying low level code.
While chosen random integer is only in the range between 1 and 1e10 I expect it to have enough entropy (?) to not matter in practice.

* Add RandomState object to random_state docstring.

* remove blank line

* Use property to handle setting random_state.
This enables setting cloned estimators with the set_params method in sklearn.

* Add docstring to attribute.

* Fix and simplify docstring.

* Add test case.

* Use maximal int for datatype in seed derivation.

* Replace random_state property with interfacing in fit method.
Derives int seed for C code only when fitting and keeps RandomState object as param.

* Adapt unit test to property change.

* Extended test case and docstring
Co-Authored-By: default avatarNikita Titov <nekit94-08@mail.ru>

* Add more equality checks (feature importance, best iteration/score).

* Add equality comparison of boosters represented by strings.
Remove useless best_iteration_ comparison (we do not use early_stopping).

* fix whitespace

* Test if two subsequent fits produce different models

* Apply suggestions from code review
Co-Authored-By: default avatarNikita Titov <nekit94-08@mail.ru>
Co-authored-by: default avatarNikita Titov <nekit94-08@mail.ru>
      cf0a992e
  55. 16 Mar, 2020 2 commits
  57. 06 Mar, 2020 1 commit
  59. 05 Mar, 2020 1 commit
    • Guolin Ke's avatar
      speed up `FindBestThresholdFromHistogram` (#2867) · 77d92b7c
      Guolin Ke authored 
      * speed up for const hessian

* rename template

* some refactorings

* refine

* refine

* simplify codes

* fix random in feature histogram

* code refine

* refine

* try fix

* make gcc happy

* remove timer

* rollback some changes

* more templates

* fix a bug

* reduce the cost of timer

* fix gpu

* fix bug

* fix gpu
      77d92b7c
  61. 27 Feb, 2020 1 commit
  63. 26 Feb, 2020 1 commit
  65. 25 Feb, 2020 1 commit
  67. 24 Feb, 2020 1 commit
  69. 20 Feb, 2020 1 commit
    • Joan Fontanals's avatar
      Add capability to get possible max and min values for a model (#2737) · 18e7de4f
      Joan Fontanals authored 
      

* Add capability to get possible max and min values for a model

* Change implementation to have return value in tree.cpp, change naming to upper and lower bound, move implementation to gdbt.cpp

* Update include/LightGBM/c_api.h
Co-Authored-By: default avatarNikita Titov <nekit94-08@mail.ru>

* Change iteration to avoid potential overflow, add bindings to R and Python and a basic test

* Adjust test values

* Consider const correctness and multithreading protection

* Update test values

* Update test values

* Add test to check that model is exactly the same in all platforms

* Try to parse the model to get the expected values

* Try to parse the model to get the expected values

* Fix implementation, num_leaves can be lower than the leaf_value_ size

* Do not check for num_leaves to be smaller than actual size and get back to test with hardcoded value

* Change test order

* Add gpu_use_dp option in test

* Remove helper test method

* Update src/c_api.cpp
Co-Authored-By: default avatarNikita Titov <nekit94-08@mail.ru>

* Update src/io/tree.cpp
Co-Authored-By: default avatarNikita Titov <nekit94-08@mail.ru>

* Update src/io/tree.cpp
Co-Authored-By: default avatarNikita Titov <nekit94-08@mail.ru>

* Update tests/python_package_test/test_basic.py
Co-Authored-By: default avatarNikita Titov <nekit94-08@mail.ru>

* Remoove imports
Co-authored-by: default avatarNikita Titov <nekit94-08@mail.ru>
      18e7de4f