GitLab

* Add parameter max_bin_by_feature.

* Fix minor bug.

* Fix minor bug.

* Fix calculation of header size for writing binary file.

* Fix style issues.

* Fix python style issue.

* Fix test and python style issue.

* Update .appveyor.yml

* Update .vsts-ci.yml

* Update setup.sh

* Update test.py

* Update test_consistency.py

* Update test_basic.py

* Update test_sklearn.py

* Update test_sklearn.py

* Update test_engine.py

* more replacements

* add balanced bagging

* refine code

* fix format

* clarify usage only for binary application

* add "download" badge

* Update README.rst

* Update README.md

* replaced issue badge with releases downloads badge

* Update README.md

* mojave install r openmp fix

* if not gcc/g++ env

* add comment

* fix

* consider max_depth for histogram_pool_size

* Update serial_tree_learner.cpp

* Update config.cpp

* Update serial_tree_learner.cpp

* fixed class_weight

* fixed lint

* added test

* hotfix

* Update sklearn.py

* Update parameter_generator.py

Replace "Traninig" with "Training"

* fix unsorted eval_at

* Update config.cpp

* fixed and enhanced format of C API

* fixed description of dataset creation functions

* Callback for NA handling

* lgb.Booster default score => NA

* lgb.cv default best score => NA

* Fix back callback

* lgb.train with booster check at the end

manual tests done: 
* With early stopping + with validation set
* With early stopping + without validation set
* Without early stopping + with validation set
* Without early stopping + without validation set

And with multiple metrics / validation sets.

* lgb.cv with booster check at the end

manual tests done: 
* With early stopping + with validation set
* With early stopping + without validation set
* Without early stopping + with validation set
* Without early stopping + without validation set

And with multiple metrics / validation sets.

[python] fixed picklability of sklearn models with custom obj and updated docstings for custom obj (#2191)

* refactored joblib test

* fixed picklability of sklearn models with custom obj and updated docstings for custom obj

* pickled model should be able to predict without refitting

* Implement top-k multiclass error metric. Add new parameter top_k_threshold.

* Add test for multiclass metrics

* Make test less sensitive to avoid floating-point issues.

* Change tabs to spaces.

* Fix problem with test in Python 2. Refactor to use np.testing. Decrease number of training rounds so loss is larger and easier to compare.

* Move multiclass tests into test_engine.py

* Change parameter name from top_k_threshold to multi_error_top_k.

* Fix top-k error metric to handle case where scores are equal. Update tests and docs.

* Change name of top-k metric to multi_error@k.

* Change tabs to spaces.

* Fix formatting.

* Fix minor issues in docs.

* [ci] for autogenerating docs

* resolved comments

* resolved comments 2

* update to 36c89134

`num_round` is redundant here because it will be overrideen by `num_trees` in the `param` dictionary.

* first metric only in earlystopping for cli

* code clean

* added note about CLI only usage

* removed note about CLI only usage

* migrate Dockerfile

* switch tag back

* PR #1879

* Update docs with parameter_generator.py

* Update wrapper doc for sklearn

* added GitHub Release task

* add connection name

* test

* added triggers for tags

* hotfixes

* added ability to pass first_metric_only in params

* simplified tests

* fixed test

* fixed punctuation

* compile SWIG artifact on Windows

* compile SWIG artifact on Windows

* combined swig and sdist jobs for Linux

* added conditions for artifacts publishing

* added SWIG artifact compilation on macOS

* hotfix

* test: switch compilers

* harsh workaround for OpenMP library conflict

* switch compilers back

* consistent order of tasks in condition

* dummy commit to trigger CI and fix CLA

* test: AppleClang on Travis

* updated fix for OpenMP multiple instances

* updated docs

* switch compiler back

* Update setup.sh

* Update test.sh

* Update setup.sh

* test: gcc on Azure

* Update test.sh

* Update setup.sh

* Update test.sh

* switch compiler back on Azure