Ecosyste.ms: OpenCollective
An open API service for software projects hosted on Open Collective.
github.com/dmlc/xgboost
Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow
https://github.com/dmlc/xgboost
e2d8a994134d25be8318f3e6316a144230c41e5e authored over 3 years ago by Jiaming Yuan <[email protected]>
The [general documentation](https://xgboost.readthedocs.io/en/latest/parameter.html#parameters...
4e00737c60592b05d74d8f9da08ec6e5f2c7f0f4 authored over 3 years ago by ReeceGoding <[email protected]>* Fix sampling.
4f75f514ce48936e654c6baddccb7fb864e16af2 authored over 3 years ago by Jiaming Yuan <[email protected]>This is part of https://github.com/dmlc/xgboost/pull/6747 .
1a73a2851143bb8a8a5b9fb307cfa059d3fed578 authored over 3 years ago by Jiaming Yuan <[email protected]>* [dask] Use `distributed.MultiLock`
This enables training multiple models in parallel.
* ...
325bc93e1662ba26fe4c58bfe0ba073527ce34f6 authored over 3 years ago by Jiaming Yuan <[email protected]>* Another implementation of predicting by indices
* Fixed omp parallel_for variable type
*...
19a2c54265618d70d1a6e2a8be1ef4e258a30720 authored over 3 years ago by Igor Rukhovich <[email protected]>* Ensure RMM is 0.18 or later
* Add use_rmm flag to global configuration
* Modify XGBCachi...
366f3cb9d8b215c06877069e95262998ad105f44 authored over 3 years ago by Philip Hyunsu Cho <[email protected]>e4894111baf957a6a7b077add146a4af90a37514 authored over 3 years ago by Philip Hyunsu Cho <[email protected]>
* [jvm-packages] fix early stopping doesn't work even without custom_eval setting
* remove de...
49c22c23b4763fa974e5ac6d2f4b5fe2af187da2 authored over 3 years ago by Bobby Wang <[email protected]>5ae7f9944bc63aaade45e894697a7031123bc7df authored over 3 years ago by Philip Hyunsu Cho <[email protected]>
f20074e8265fdd0fc80a3d78b2a8dd98bf33ab02 authored over 3 years ago by Jiaming Yuan <[email protected]>
* Expose more methods in cvpack and packed booster.
* Fix cv context in deprecated callbacks.
...
9c8523432acdce35ffd6a6935f336f587680dddc authored over 3 years ago by kangsheng89 <[email protected]>
1fa6793a4efdf0d41b012fcdf8b3931530464e51 authored over 3 years ago by Roffild <[email protected]>
* Save feature info in booster in JSON model.
* [breaking] Remove automatic feature name genera...
Co-authored-by: fis <[email protected]>
b6167cd2ff2284d69af82601d863e0e69b849abf authored over 3 years ago by capybara <[email protected]>9b530e5697545ae384297889bf86b5568f520f4f authored over 3 years ago by Louis Desreumaux <[email protected]>
c375173dcae9c857ea859c08422235e0cebfa084 authored over 3 years ago by Jiaming Yuan <[email protected]>
* Add ability to load booster direct from byte array
* fix compiler error
* move InputStre...
17913713b554d820a8ce94226d854b4a5f1d8bbc authored over 3 years ago by Honza Sterba <[email protected]>* Use inplace predict for sklearn when possible.
872e559b91f6f201a4f690a024398412c128a976 authored over 3 years ago by Jiaming Yuan <[email protected]>Replaces "dowm" with "down" on parameter n_jobs
25077564abbb16a0523dcda009696f702dbbe500 authored over 3 years ago by Benjamin Lehmann <[email protected]>bdedaab8d1ab55f69f940c40f11baf38cd665c29 authored over 3 years ago by Jiaming Yuan <[email protected]>
Co-authored-by: Shvets Kirill <[email protected]>
9f15b9e322ac505189394ff840bda3f52a7abb1f authored over 3 years ago by ShvetsKS <[email protected]>dc97b5f19f99c17b1277981d96ea87fbed176fcb authored over 3 years ago by James Lamb <[email protected]>
4c5d2608e0bd179bfc5a8e9b3132e6651f841256 authored over 3 years ago by Roffild <[email protected]>
Co-authored-by: Shvets Kirill <[email protected]>
9a0399e8981b2279d921fe2312f7ab1b880fd3c3 authored over 3 years ago by ShvetsKS <[email protected]>Skip `copy_tree` when existing build is found.
9b267a435e0aa1dfdff211d1a5b668538c51cd35 authored over 3 years ago by Ali <[email protected]>* Use normal predictor for dart booster.
* Implement `inplace_predict` for dart.
* Enable `d...
The cache stores outdated packages with wrong linkage. Right now there's no way to clear the ca...
dbf7e9d3cbc0adc1c8cea5f1002fcc01fc6e121b authored over 3 years ago by Jiaming Yuan <[email protected]>
* Add tag for versions.
* use autoclass in sphinx build.
Made some class methods to be private...
5d48d40d9a06022d3112922c263ab8b92c106033 authored over 3 years ago by Jiaming Yuan <[email protected]>
* Stop printing out message.
* Remove R specialization.
The printed message is not really ...
218a5fb6dda9c639750103f51aaa0d1f25010d0c authored over 3 years ago by Jiaming Yuan <[email protected]>* Add a new API function for predicting on `DMatrix`. This function aligns
with rest of the ...
* Use __array_interface__ for creating DMatrix from CSR.
* Add configuration.
1e949110da07332d60468494ff185f5854c87500 authored over 3 years ago by Jiaming Yuan <[email protected]>
a4101de67872e94a4b00b45de4e7afb193020f3a authored over 3 years ago by Jiaming Yuan <[email protected]>
72892cc80d2b656d0d911381ee29a32904308fb4 authored over 3 years ago by Jiaming Yuan <[email protected]>
9d62b145910de4a581d08eb83370c8e7c9b8749c authored over 3 years ago by Jiaming Yuan <[email protected]>
* Accept array interface for csr and array.
* Accept an optional proxy dmatrix for metainfo...
This PR changes predict and inplace_predict to accept a Future of model, to avoid sending models...
87ab1ad607f9c15e643a089b0832afeebf0cc7d2 authored over 3 years ago by Jiaming Yuan <[email protected]>a9ec0ea6da84672fb52d2163babe95ec05f95f6f authored over 3 years ago by Jiaming Yuan <[email protected]>
* [dask] Use a 1 line sample to infer output shape.
This is for inferring shape with direct p...
d8ec7aad5a9a3eb580c55680aee8ad1a975cba20 authored over 3 years ago by Jiaming Yuan <[email protected]>c3c8e66fc9d285c265b07d78fb6866770a65347b authored over 3 years ago by Jiaming Yuan <[email protected]>
0f2ed21a9d93635d6bb95c775c3132f31c3bab0c authored over 3 years ago by Philip Hyunsu Cho <[email protected]>
d167892c7e2d5976764cf478e6cbd37863131fe1 authored over 3 years ago by Jiaming Yuan <[email protected]>
0ad6e18a2a804389c77fa4d6977c1e2df4c4a098 authored over 3 years ago by Philip Hyunsu Cho <[email protected]>
* Add ARM64 test to Jenkins pipeline
* Check for bundled libgomp
* Use a separate test sui...
55ee2bd77f3ff319ccb27d7d1c2780f938aefc34 authored over 3 years ago by Philip Hyunsu Cho <[email protected]>1b70a323a7fafff07abe9fa9305532dc16806589 authored over 3 years ago by Jiaming Yuan <[email protected]>
bc08e0c9d10cab1164e75a0cc903e6c73f78105f authored over 3 years ago by Jiaming Yuan <[email protected]>
8968ca7c0a3cb24208fca9c6f645b26a2f114c7b authored over 3 years ago by Jiaming Yuan <[email protected]>
* Move x86 linux and osx sdist test to action.
* Add Windows.
d19a0ddacf8e88da2653a1c3a69f6628e17b0600 authored over 3 years ago by Jiaming Yuan <[email protected]>* Add base margin to evaluation datasets.
* Unify the code base for evaluation matrices.
4bf23c239139aaa90b6bd0e3d36c7c2168c516ce authored over 3 years ago by Jiaming Yuan <[email protected]>
This PR ensures all DMatrix types have a common interface.
* Fix logic in avoiding duplicated...
8942c9805426862a3d01519048aba087adbf99f7 authored over 3 years ago by Jiaming Yuan <[email protected]>561809200a4f12f6ab84fd04aa8ae0467b46d37a authored over 3 years ago by Jiaming Yuan <[email protected]>
* [java] extending the library loader to use both OS and CPU architecture.
* Simplifying crea...
fec66d033ab1683db967b99975d9c43f9baaecbf authored over 3 years ago by Adam Pocock <[email protected]>a275f4026728ed14fbc70da142ef7a4a1d3de04d authored over 3 years ago by Jiaming Yuan <[email protected]>
7bc56fa0eda6984197152ed4aa98d2fc9e9e8cc8 authored over 3 years ago by Jiaming Yuan <[email protected]>
26982f9fcebf63c46081f3266d2f8f283e7a6171 authored over 3 years ago by Jiaming Yuan <[email protected]>
* Fix `long_description_content_type`.
f0fd7629ae14c040586bdd72a00c0e20b85dee01 authored over 3 years ago by Jiaming Yuan <[email protected]>
there is possibility that onJobStart of TaskFailedListener won't be called, if
the job is submi...
f8bb678c67f9166329fb691f235653efb5f53447 authored over 3 years ago by Jiaming Yuan <[email protected]>
The old (before fix) best_ntree_limit ignores the num_class parameters, which is incorrect. In...
d6d72de339e3172143b1923a780c1674f4248fcd authored over 3 years ago by Jiaming Yuan <[email protected]>d132933550dde9526da72d2bf72b12b83f11fad8 authored almost 4 years ago by Jiaming Yuan <[email protected]>
d356b7a07146bd7aa9586c33d7ec4fc2675c044f authored almost 4 years ago by Jiaming Yuan <[email protected]>
89a00a5866e5d73c79d878e0207db1545bc7dffe authored almost 4 years ago by Jiaming Yuan <[email protected]>
* Fix attributes not being restored.
* Rename all `data` to `X`. [breaking]
Co-authored-by: Kirill Shvets <[email protected]>
7f4d3a91b9053e9b486a6bc84b93029510d180c6 authored almost 4 years ago by ShvetsKS <[email protected]>03cd087da180b7dff21bd8ef34997bf747016025 authored almost 4 years ago by Jiaming Yuan <[email protected]>
* Remove duplicated code, which fixes typo `evals_result` -> `evals_result_`.
c709f2aaaf5553af71cde010c6b11a23b441d436 authored almost 4 years ago by Jiaming Yuan <[email protected]>f2f7dd87b860ed1d4fcdfb1ba1339a327c6c39d5 authored almost 4 years ago by Jiaming Yuan <[email protected]>
78f2cd83d70f3eed831390642cb228a83f98518d authored almost 4 years ago by Jiaming Yuan <[email protected]>
* Initial support for distributed LTR using dask.
* Support `qid` in libxgboost.
* Refactor ...
96d3d32265c9f73c709d503ce3c9007c18cc0878 authored almost 4 years ago by Jiaming Yuan <[email protected]>
7c9dcbedbc15094d1eb387c55df8129c727139b9 authored almost 4 years ago by Jiaming Yuan <[email protected]>
* Use `_estimator_type`.
For more info, see: https://scikit-learn.org/stable/developers/devel...
f5ff90cd87c0ba77dec21ea528f1b5683b1b8ff0 authored almost 4 years ago by Jiaming Yuan <[email protected]>* Add system header.
* Remove use of TR1 on Solaris
Co-authored-by: Hyunsu Cho <chohyu01@c...
8747885a8bc2d9dcaa8bb2e7e019198b174e26b7 authored almost 4 years ago by Jiaming Yuan <[email protected]>* Update dmlc-core submodule and conform to new API
* Remove unsupported parameter from metho...
b2246ae7eff090bd1431f3854c99a8ca12782a98 authored almost 4 years ago by TP Boudreau <[email protected]>
* For sklearn:
- Handles user defined objective function.
- Handles `softmax`.
* For da...
60cfd14349a3ed4593de276525fba068adcaea53 authored almost 4 years ago by Jiaming Yuan <[email protected]>516a93d25c3b6899558700430ffc99a29ea21e1a authored almost 4 years ago by Jiaming Yuan <[email protected]>
195a41cef172d9cbb833ff7a032da59584e65354 authored almost 4 years ago by James Lamb <[email protected]>
2b049b32e94d3d24bd57803ebd70be6dbe7646d4 authored almost 4 years ago by Jiaming Yuan <[email protected]>
* Calling XGBModel.fit() should clear the Booster by default
* Document the behavior of fit()...
fa139922649db7a99d7690e3b9cdcaa4f23199ac authored almost 4 years ago by Philip Hyunsu Cho <[email protected]>5e9e525223075923c3c403ebd68db2c2da6e0569 authored almost 4 years ago by Jiaming Yuan <[email protected]>
8ad22bf4e7971baaf4c5f4b525dcd7c767bb5c6b authored almost 4 years ago by James Lamb <[email protected]>
* Add validate_features.
* Show type hints in doc.
Co-authored-by: Hyunsu Cho <chohyu01@cs...
de8fd852a565c5557a4e27d1991f3ecb300e7244 authored almost 4 years ago by Jiaming Yuan <[email protected]>
New Scikit-Learn version uses keyword argument, and `X` is the predefined
keyword.
* Use pip...
610ee632ccceafd266f1dea8c8ebfed051f044a1 authored almost 4 years ago by Jiaming Yuan <[email protected]>cb207a355d1ff530b5f9a7dcb8677dc19999e270 authored almost 4 years ago by Jiaming Yuan <[email protected]>
For the `gamma-nloglik` eval metric, small positive values in the labels are causing `NaN`'s in ...
2231940d1d08f5aca23cf53d922642996a098d44 authored almost 4 years ago by Gorkem Ozkaya <[email protected]>95cbfad990866fe28488a28dbc339b64ec642e08 authored almost 4 years ago by MBSMachineLearning <[email protected]>
fbb980d9d3bc3bd2a2a5510279277e05e7c7467e authored almost 4 years ago by Philip Hyunsu Cho <[email protected]>
cd0821500cbecf8b7afaa2382448e0470081ddca authored almost 4 years ago by Philip Hyunsu Cho <[email protected]>
380f6f4ab89840678758ee4a978ea72232bbe1d4 authored almost 4 years ago by Philip Hyunsu Cho <[email protected]>
* Implement early stopping with training continuation.
* Add new C API for obtaining boosted ...
ca3da55de47bfe693b50dd9000c4c84a1cc90180 authored almost 4 years ago by Jiaming Yuan <[email protected]>* Lazy import cuDF
* Lazy import Dask
Co-authored-by: PSEUDOTENSOR / Jonathan McKinney <ps...
125b3c0f2d09d8ac42958b806a2c431aea338108 authored almost 4 years ago by Philip Hyunsu Cho <[email protected]>* Enable loading model from <1.0.0 trained with objective='binary:logitraw'
* Add binary:logi...
ad1a52770938b9d7c6eb03b95ca77dba83c63e28 authored almost 4 years ago by Philip Hyunsu Cho <[email protected]>* [CI] Upgrade cuDF and RMM to 0.18 nightlies
* Modify RMM plugin to be compatible with RMM 0...
bf6cfe3b99884ff4ba1cd2c5d5451fe634426405 authored almost 4 years ago by Philip Hyunsu Cho <[email protected]>d8d684538c6312efe5ca1b03ad4b572bda671583 authored almost 4 years ago by Jiaming Yuan <[email protected]>
c5876277a87ea20ab717b3834032621e904b24c1 authored almost 4 years ago by Jiaming Yuan <[email protected]>
0e97d97d50708ff9c8cfac9d7e33534eb37a8f08 authored almost 4 years ago by Jiaming Yuan <[email protected]>