GitLab

* add warnings for override parameters of Dataset

* fix pep8

* add feature_penalty

* refactor

* add R's code

* Update basic.py

* Update basic.py

* fix parameter bug

* Update lgb.Dataset.R

* fix a bug

* fixed minor typos in documentation

* fixed typo in gpu_tree_learner.cpp

* Update .gitignore

* Added links to the libraries used.

* Fixing the header

* Fixes

* ot -> to

* Correcting lgb.prepare output comment

* updated Roxygen files

* Fix multiclass custom objective demo

* Use option not to boost from average instead of setting init score explicitly

* Reference #1846 when turning off boost_from_average

* Add trailing whitespace

* removed comparison warning

* fixed spacing

* removed brew hotfix and deprecated sudo option on Travis

* removed brew hotfix on Azure

File: [LightGBM//src/io/dataset.cpp]
Function: [138:FastFeatureBundling(...)]

Reserving vectors where we already know the size to save on reallocation costs.

Also removed a variable that was unnecessary.

When loading a binary file, take feature penalty and monotone constraints from config if given there. (#1881)

* When loading a binary file, take feature penalty from config if given there.

* When loading a binary file, take feature penalty from config if given there.

* Fix crash when num_features != num_total_features and feature_contri is given.

* Apply the same logic to monotone_types_.

* Fix indentation

* fixed xcode version

* fixed brew on Travis

* fixed brew on Azure Pipelines

add boost header files compute/ into build_r.R to enable GPU compilation

* added get_data method

* hotfix

* added warning for other data types

* reworked according to review comments

* minor addition to FAQ

* added test

* [python] fix creating train_set in fit

https://github.com/Microsoft/LightGBM/blob/cc99f0d36ae929eb02b22a072823ab7c6d3155ab/python-package/lightgbm/sklearn.py#L519
may False even if valid_data[0] is X and valid_data[1] is y actually, because `check_X_y` might return copy of X and y.
https://scikit-learn.org/0.20/modules/generated/sklearn.utils.check_X_y.html

cf. https://github.com/Microsoft/LightGBM/pull/451

* use assertIn

* fix RF's bugs

* fix tests

* rollback num_iterations

* fix a bug and reduce memory costs

* reduce memory cost

Init has been updated to allow for feature_fraction == 1.0f but the change has not been copyed in the ResetConfig function.

* disabled early stopping in dart mode

* check dart mode during the init phase of early_stop callback

* [CPP] disable early stopping in dart

* fix compile error

* added download artifacts badge

* hotfix

* store badge images locally

* explicitly set the order

* add free booster in lgb.cv

* change to reset_data

* updated external repos section in README

* added SHAP

[ci][docs] updated temp fix for warning written to stderr, fixed conda permissions and updated bench link (#1849)

* Update .appveyor.yml

* updated bench link (404)

* fixed conda permission error on Azure

* use stable container

* Update Dockerfile

* Update Dockerfile

* chmod conda folder

[ci][python] fall back to producing one wheel for macOS and drop support of OSX 10.6 and 10.7 (#1826)