github.com/dmlc/xgboost commits | Ecosyste.ms: OpenCollective

Fix incorrect device in multi-GPU algorithm (#4161)

c8c472f39aa08d5b8f180076a429f09317451cc7 authored over 5 years ago by Rory Mitchell <[email protected]>

more correct way to build node stats in distributed fast hist (#4140)

* add back train method but mark as deprecated

* add back train method but mark as deprecated...

1dac5e24108890c946c5a4673f0d1fa4d6125943 authored over 5 years ago by Nan Zhu <[email protected]>

Accept numpy array view. (#4147)

* Accept array view (slice) in metainfo.

a985a99cf0dacb26a5d734835473d492d3c2a0df authored over 5 years ago by Jiaming Yuan <[email protected]>

Upgrade rabit. (#4159)

0ff84d950ed78df9941ccbaec3ac08e15159f81a authored over 5 years ago by Jiaming Yuan <[email protected]>

Fix ssize_t definition. (#80)

* Fix linter.

1cc34f01db56d28e8e80847cf0fc5e3ecf8bb67b authored over 5 years ago by Jiaming Yuan <[email protected]>

Fix typo in demo (#4156)

60f05352c51956613e3319461180405c82a09266 authored over 5 years ago by Kenichi Nagahara <[email protected]>

Prevent empty quantiles in fast hist (#4155)

* Prevent empty quantiles

* Revise and improve unit tests for quantile hist

* Remove unnec...

549c8d6ae998a5aa4578102a517e4b4def8761c9 authored over 5 years ago by Philip Hyunsu Cho <[email protected]>

Fix gpu_hist apply_split test. (#4158)

e1240413c90ee64621895bd4717103da3bf60244 authored over 5 years ago by Jiaming Yuan <[email protected]>

Fix cpplint. (#4157)

* Add comment after #endif.
* Add missing headers.

2e618af743091644395b2be066633951651b9827 authored over 5 years ago by Jiaming Yuan <[email protected]>

Fix for windows compilation (#4139)

71a604fae3970ff0422f45617f57d85027cdddce authored over 5 years ago by Rory Mitchell <[email protected]>

Remove dmlc logging. (#78)

* Remove dmlc logging header.

* Fix lint.

0101a4719ce9c368584716250e732849d9c56700 authored over 5 years ago by Jiaming Yuan <[email protected]>

Fix empty subspan. (#4151)

* Silent the death tests.

1fe874e58aae2e17be46fb9177407e245b844d11 authored over 5 years ago by Jiaming Yuan <[email protected]>

Update datatable usage (#4123)

ff2d4c99fa89695ffe3b72c678aafd2a12d68adb authored over 5 years ago by Pasha Stetsenko <[email protected]>

Try fixing mingw build error when using CMake. (#77)

* Try fixing mingw build error when using CMake.

* Check __MINGW32__ .

* Fix linter.

05941a5f965007eba8441d962fadce6466688d9b authored over 5 years ago by Jiaming Yuan <[email protected]>

Make `HistCutMatrix::Init' be aware of groups. (#4115)

* Add checks for group size.
* Simple docs.
* Search group index during hist cut matrix init...

754fe8142b295c95798b2cfb2031aa0875b69f19 authored over 5 years ago by Jiaming Yuan <[email protected]>

Fix broken R test: Install Homebrew GCC (#4142)

* Fix broken R test: Install Homebrew GCC

Missing GCC Fortran causes installation failure of ...

37ddfd7d6e448185fc15b320b44785d06ab62577 authored over 5 years ago by Philip Hyunsu Cho <[email protected]>

[jvm-packages] add `verbosity` param (#4138)

d506a8bc633fea3c8d535c70a5c11047122f07b5 authored over 5 years ago by Rong Ou <[email protected]>

Separate Depthwidth and Lossguide growing policy in fast histogram (#4102)

* add back train method but mark as deprecated

* add back train method but mark as deprecated...

c18a3660faea9d9351ffc6a01ee1d8f50559d9bf authored over 5 years ago by Nan Zhu <[email protected]>

reformat benchmark_tree.py to get rid of lint errors (#4126)

3be1b9ae30015950ddc072499b4092ae97dff786 authored over 5 years ago by Rong Ou <[email protected]>

[jvm-packages] fix simple logic error :) (#4128)

@CodingCat

9b917cda4ff61f0512cdba1c53bc8e55258a5d4a authored over 5 years ago by Rong Ou <[email protected]>

Update Python docstring for ranking functions (#4121)

* Update Python docstring for ranking functions

* Fix formatting

99a290489cb8e7109ff4f8f1161f098185097b25 authored over 5 years ago by Philip Hyunsu Cho <[email protected]>

[jvm-packages] force use per-group weights in spark layer (#4118)

3320a5219204cb8ff6a83c0c20fcaeece9cdbf32 authored over 5 years ago by Nan Zhu <[email protected]>

Add link to InfoWorld 2019 award (#4116)

ba584e5e9f9ae3d38f44f5837a4ffb6a85427188 authored over 5 years ago by Yuan (Terry) Tang <[email protected]>

[jvm-packages] minor fix of params (#4114)

2a9b085bc8d75b85bfd1d9877c52837c37651af9 authored over 5 years ago by Rong Ou <[email protected]>

Use nccl group calls to prevent from dead lock. (#4113)

* launch all reduce sequentially.
* Fix gpu_exact test memory leak.

f8ca2960fc3829dd0ff71bf0980f7b27efb6f281 authored over 5 years ago by Jiaming Yuan <[email protected]>

[jvm-packages] better fix for shutdown applications (#4108)

* intentionally failed task

* throw exception

* more

* stop sparkcontext directly

* ...

05243642bb64a2865d35cc853058e7986cf5686e authored over 5 years ago by Nan Zhu <[email protected]>

Clean up training code. (#3825)

* Remove GHistRow, GHistEntry, GHistIndexRow.
* Remove kSimpleStats.
* Remove CheckInfo, SetLe...

017c97b8ce62935429c797b085bf46c63b2be617 authored over 5 years ago by Jiaming Yuan <[email protected]>

[jvm-packages] fix return type of setEvalSets (#4105)

325b16bccdc0e863e6c85063e601c601d65a0320 authored over 5 years ago by Nan Zhu <[email protected]>

Distributed Fast Histogram Algorithm (#4011)

* add back train method but mark as deprecated

* add back train method but mark as deprecated...

ae3bb9c2d55f4d1e21df0ad0fcf936044aae783a authored over 5 years ago by Nan Zhu <[email protected]>

Perform clang-tidy on both cpp and cuda source. (#4034)

* Basic script for using compilation database.

* Add `GENERATE_COMPILATION_DATABASE' to CMake...

8905df4a182eba7e97bcbcec0d37e06c47f4de60 authored over 5 years ago by Jiaming Yuan <[email protected]>

Prevent training without setting up caches. (#4066)

* Prevent training without setting up caches.

* Add warning for internal functions.
* Check ...

1088dff42c28d7f7b4009fefab64da6e5e5161b3 authored over 5 years ago by Jiaming Yuan <[email protected]>

Speed up Jenkins by not compiling CMake (#4099)

7a652a8c646a6e6492ca637613b24b81486a1f37 authored over 5 years ago by Philip Hyunsu Cho <[email protected]>

enable xgb_model in scklearn XGBClassifier and test. (#4092)

* Enable xgb_model parameter in XGClassifier scikit-learn API

https://github.com/dmlc/xgboost...

59f868bc60a6ba8816aa38a2c2eb87bb6c468632 authored over 5 years ago by tmitanitky <[email protected]>

[jvm-packages] adding logs for parameters (#4091)

0d0ce32908b4081e9fe85212177af6ae01564f4d authored over 5 years ago by Nan Zhu <[email protected]>

Add Jenkins status badge (#4090)

a60e224484236fee24afcd2a92fca888180da914 authored over 5 years ago by Philip Hyunsu Cho <[email protected]>

fix doc about max_depth (#4078)

* fix doc

* Update doc/parameter.rst

Co-Authored-By: CodingCat <[email protected]...

e0094d996e47e16df3a493b85a927a23985b5356 authored over 5 years ago by Nan Zhu <[email protected]>

Fix failing Travis CI on Mac (#4086)

* Fix failing Travis CI on Mac

Use Homebrew Addon + latest Mac image

* Use long command fo...

a1c35cadf00ca926b9658b9ea6160e84f95cdff5 authored over 5 years ago by Philip Hyunsu Cho <[email protected]>

Check booster for dart in feature importance. (#4073)

* Check booster for dart in feature importance.

4fac9874e0abcf864a9ca00f66ccb65bcdd86696 authored over 5 years ago by Jiaming Yuan <[email protected]>

Correct JVM CMake GPU flag. (#4071)

301cef463826d24837d4f17c742b6c9e4502dbe4 authored over 5 years ago by Jiaming Yuan <[email protected]>

Require leaf statistics when expanding tree (#4015)

* Cache left and right gradient sums

* Require leaf statistics when expanding tree

1fc37e47497239a7bc52e0e9949004c891fe36b6 authored almost 6 years ago by Rory Mitchell <[email protected]>

Fixed single-GPU tests. (#4053)

- ./testxgboost (without filters) failed if run on a multi-GPU machine because
the memory was...

0f8af85f642fe65a9b655fe93cc2f94ecfafeccc authored almost 6 years ago by Andy Adinets <[email protected]>

Performance optimizations for Intel CPUs (#3957)

* Initial performance optimizations for xgboost

* remove includes

* revert float->double
...

5f151c5cf3bae00b69fd0bc923126c61c6abd26c authored almost 6 years ago by Egor Smirnov <[email protected]>

[jvm-packages] Performance consideration and Alignment input parameter of repartition function (#4049)

dade7c3aff1044f83339fd1393f78501c2fd5841 authored almost 6 years ago by KyleLi1985 <[email protected]>

[BLOCKING] fix the issue with infrequent feature (#4045)

* fix the issue with infrequent feature

* handle exception

* use only 2 workers

* addre...

773ddbcfcb3abe2115a419b186f45f18473d995e authored almost 6 years ago by Nan Zhu <[email protected]>

[jvm-packages] fix safe execution (#4046)

e290ec9a804d3c3df7c0e62af5fd81f608225cfb authored almost 6 years ago by Nan Zhu <[email protected]>

Avoid generating NaNs in UnwoundPathSum (#3943)

* Avoid generating NaNs in UnwoundPathSum.

Kudos to Jakub Zakrzewski for tracking down the bu...

6a569b8cd950ba64db8cb1168912cce60e394934 authored almost 6 years ago by Kodi Arfer <[email protected]>

Fix sparse page segfault. (#4040)

* Remove usage of raw pointers in SparsePageSource.

55bc149efb069f15ea0c8bdfdfb38022d5ec6266 authored almost 6 years ago by Jiaming Yuan <[email protected]>

[jvm-packages] Updates to Java Booster to support other feature importance measures (#3801)

* Updates to Booster to support other feature importances

* Add returns for Java methods

*...

431c850c03edd97a126707d2f04f251838392fe9 authored almost 6 years ago by Shayak Banerjee <[email protected]>

Use Span in gpu coordinate. (#4029)

* Use Span in gpu coordinate.

* Use Span in device code.
* Fix shard size calculation.
- ...

1f022929f414d9dda7f984d88cafa2ec3887031e authored almost 6 years ago by Jiaming Yuan <[email protected]>

[jvm-packages] fix the scalability issue of prediction (#4033)

f368d0de2b6d60cdba67fed8291e7a3ce402850d authored almost 6 years ago by Nan Zhu <[email protected]>

fix typos (#4027)

15fe2f1e7cb1db4236429879faed59a4bac308b1 authored almost 6 years ago by Tatsuhito KATO <[email protected]>

Fix ignoring dart in updater configuration. (#4024)

* Fix ignoring dart in updater configuration.

be948df23ff3402b38a76dc8a2fee9172c63be6d authored almost 6 years ago by Jiaming Yuan <[email protected]>

Use Span in GPU exact updater. (#4020)

* Use Span in GPU exact updater.

* Add a small test.

9897b5042f563150513b0aebfc33a8e1ccb96987 authored almost 6 years ago by Jiaming Yuan <[email protected]>

Document num_parallel_tree. (#4022)

77352529256dafc425e026b0c6b7791a7ba84753 authored almost 6 years ago by Jiaming Yuan <[email protected]>

Merge duplicated linear updater parameters. (#4013)

* Merge duplicated linear updater parameters.

* Split up coordinate descent parameter.

85939c6a6ea630c213852f485b13f70d47820c72 authored almost 6 years ago by Jiaming Yuan <[email protected]>

Reduce tree expand boilerplate code (#4008)

f75a21af25d1752648d78d8efae33b6cb1a7fac9 authored almost 6 years ago by Rory Mitchell <[email protected]>

Combine TreeModel and RegTree (#3995)

84c99f86f46b1ff901b9416233ae5eb172c18755 authored almost 6 years ago by Rory Mitchell <[email protected]>

[jvm-packages]support multiple validation datasets in Spark (#3910)

* add back train method but mark as deprecated

* add back train method but mark as deprecated...

c055a3260988b63d61dbec088e8f8d6af2d34e9c authored almost 6 years ago by Nan Zhu <[email protected]>

Fix and optimize logger (#4002)

* Fix logging switch statement.

* Remove debug_verbose_ in AllReducer.

* Don't construct t...

c8c7b9649cb84f7e3dfc5dfa7a9f1fe813b4d8d2 authored almost 6 years ago by Jiaming Yuan <[email protected]>

Update CONTRIBUTORS.md (#3999)

a2dc92959816d6d7cd44501db1dfcdfed737cb01 authored almost 6 years ago by Sam Wilkinson <[email protected]>

Column sampling at individual nodes (splits). (#3971)

* Column sampling at individual nodes (splits).

* Documented colsample_bynode parameter.

-...

42bf90eb8fbcda2fac494c43bc326c7ca1d254d0 authored almost 6 years ago by Andy Adinets <[email protected]>

Unify logging facilities. (#3982)

* Unify logging facilities.

* Enhance `ConsoleLogger` to handle different verbosity.
* Overr...

e0a279114ee184d5e0012265ddc320bee84319ef authored almost 6 years ago by Jiaming Yuan <[email protected]>

Deprecation warning for lists passed into DMatrix (#3970)

* Ensure lists cannot be passed into DMatrix

The documentation does not include lists as an a...

fd722d60cdc06a3fd49c3284ae86e71e38cbe798 authored almost 6 years ago by Sam Wilkinson <[email protected]>

scikit-learn api section documentation correction (#3967)

* update description of early stopping rounds

the description of early stopping round was qui...

53f695acf2afe897abbaf2b3b77aad269da1161d authored almost 6 years ago by lyxthe <[email protected]>

Remove leaf vector, add tree serialisation test, fix Windows tests (#3989)

3d81c48d3fa9a2a2ceb0d7388d3ac1436af7d8ee authored almost 6 years ago by Rory Mitchell <[email protected]>

Fix CRAN check warnings/notes (#3988)

* fix

* reorder declaration to match initialization

84a3af8dc00dbc587d55892a55b418d362e24ff5 authored almost 6 years ago by Tong He <[email protected]>

Initialized AllReducer counters to 0. (#3987)

4be5edaf92ab3f9c181eee12c4afac0a29c965b2 authored almost 6 years ago by Andy Adinets <[email protected]>

Single precision histograms on GPU (#3965)

* Allow single precision histogram summation in gpu_hist

* Add python test, reduce run-time o...

93f9ce9ef9d88a9cf8ded989c2fb83b37b3f0cd0 authored almost 6 years ago by Rory Mitchell <[email protected]>

Use int instead of char in CLI config parser (#3976)

9af6b689d6c96d0326ddfc1c95ef849970dc7b1d authored almost 6 years ago by Philip Hyunsu Cho <[email protected]>

Fix typo in Feature Interaction Constraints tutorial (#3975)

4f26053b09737e191a7993285aed022be67a322a authored almost 6 years ago by Philip Hyunsu Cho <[email protected]>

Porting elementwise metrics to GPU. (#3952)

* Port elementwise metrics to GPU.

* All elementwise metrics are converted to static polymorp...

48dddfd635b0fa6575b9934334254533e5d8708d authored almost 6 years ago by Jiaming Yuan <[email protected]>

GPU performance logging/improvements (#3945)

- Improved GPU performance logging

- Only use one execute shards function

- Revert perform...

a9d684db185b1e5ee5a0dd64b646b58da28e6b05 authored almost 6 years ago by Rory Mitchell <[email protected]>

Disable retries in Jenkins CI, since we're now using On-Demand instances instead of Spot (#3948)

c5f92df4754b91c6c5871621d3ecd5f3a704df45 authored almost 6 years ago by Philip Hyunsu Cho <[email protected]>

Fix #3894: Allow loading pickles without self.booster attributes (redux) (#3944)

c5130e487a3746089d2183dca799159c3d4bf941 authored almost 6 years ago by Philip Hyunsu Cho <[email protected]>

[jvm-packages]Fix early stopping condition (#3928)

* add back train method but mark as deprecated

* add back train method but mark as deprecated...

9c4ff50e83b23ad460d5130deb24ad673c8fe666 authored almost 6 years ago by Nan Zhu <[email protected]>

[jvm-packages] Fix vector size of 'rawPredictionCol' in XGBoostClassificationModel (#3932)

* Fix vector size of 'rawPredictionCol' in XGBoostClassificationModel

* Fix UT

42cac4a30b80bddebda59345819f39a0aa178203 authored almost 6 years ago by Huafeng Wang <[email protected]>

Fix #3894: Allow loading pickles without self.booster attributes (#3938)

The addition of self.booster attribute broke backward compatibility.

f9302a56fbdabb28d071ed9e402ca75e03673b4d authored almost 6 years ago by Philip Hyunsu Cho <[email protected]>

Add AUC-PR to list of metrics to maximize for early stopping (#3936)

7d3149a21f9fbdc416bd09e28305d016651012c6 authored almost 6 years ago by Philip Hyunsu Cho <[email protected]>

[jvm-packages] Fix #3898: use correct group ID for maven-site-plugin (#3937)

86aac98e54b831d04197be6cd7c8ccb67ecbd3d6 authored almost 6 years ago by Philip Hyunsu Cho <[email protected]>

Address #3933: document limitation of DMLC CSV parser + recommend Pandas (#3934)

e9ab4a1c6cbfac828440f9e37bd95d26e8446622 authored almost 6 years ago by Philip Hyunsu Cho <[email protected]>

[jvm-packages] update version to 0.82-SNAPSHOT (#3920)

* add back train method but mark as deprecated

* add back train method but mark as deprecated...

dc2bfbfde144ada58c6992f0315e27064a5f8ea6 authored almost 6 years ago by Nan Zhu <[email protected]>

Fix link in binary classification demo README.md (#3918) (#3919)

7ebe8dcf5b5026eab02b62d2bed7435563bcae97 authored almost 6 years ago by Prabakaran Kumaresshan <[email protected]>

Use consistent type for sharding GPU data in GPU coordinate updater (#3917)

* Use consistent type for sharding GPU data in GPU coordinate updater

* Use fast integer ceil...

973fc8b1ff082586dc415951c81fd7913a9bfdf7 authored almost 6 years ago by Philip Hyunsu Cho <[email protected]>

Address deprecation of Python ABC. (#3909)

93f63324e62c9e04269d17bc6505137a18dcc900 authored almost 6 years ago by Jiaming Yuan <[email protected]>

[jvm-packages][refactor] refactor XGBoost.scala (spark) (#3904)

* add back train method but mark as deprecated

* add back train method but mark as deprecated...

aa48b7e9033a4d78bf4f336960f62f63212d5530 authored almost 6 years ago by Nan Zhu <[email protected]>

Add parameter to make node type configurable in plot tree (#3859)

* add parameters 'conditionNodeParams' and 'leafNodeParams' to function `to_graphviz` enable to ...

0cd326c1bc369f1ed395f5fa59cc512166ca6ef0 authored almost 6 years ago by Joey Gao <[email protected]>

Update dmlc-core submodule (#3907)

3a150742c73bbe702b3d27fd975a5ccfab19348a authored almost 6 years ago by Philip Hyunsu Cho <[email protected]>

Fix Typo in learner.cc (#3902)

0a0d4239d32cc90e48fb95be0b122164582c9d96 authored almost 6 years ago by theycallhimavi <[email protected]>

Add back python2 tests for Travis light weight tests. (#3901)

fe999bf968e173e79b89b786f59a6fe496d99151 authored almost 6 years ago by Jiaming Yuan <[email protected]>

Refactor Python tests. (#3897)

* Deprecate nose tests.
* Format python tests.

2ea0f887c182f37b0dc88ff8daca6663416b76be authored almost 6 years ago by Jiaming Yuan <[email protected]>

Enforce naming style in Python lint (#3896)

c76d993681d8486decc43d4bd4b81d86762ed434 authored almost 6 years ago by Philip Hyunsu Cho <[email protected]>

Update dmlc-core submodule (#3891)

a2a8954659810de0a1a3849d124a270feec4a773 authored almost 6 years ago by Philip Hyunsu Cho <[email protected]>

Improve update position function for gpu_hist (#3895)

7af0946ac18020b756fd22015563b23eb487f7a7 authored almost 6 years ago by Rory Mitchell <[email protected]>

use gain for sklearn feature_importances_ (#3876)

* use gain for sklearn feature_importances_

`gain` is a better feature importance criteria th...

143475b27ba195604fe584bf175c6185320724b4 authored almost 6 years ago by Dr. Kashif Rasul <[email protected]>

Minor refactor of split evaluation in gpu_hist (#3889)

* Refactor evaluate split into shard

* Use span in evaluate split

* Update google tests

926eb651fe97ae521e7fd045ff8446136cf3f873 authored almost 6 years ago by Rory Mitchell <[email protected]>

Enable running objectives with 0 GPU. (#3878)

* Enable running objectives with 0 GPU.

* Enable 0 GPU for objectives.
* Add doc for GPU obj...

daf77ca7b70b3d85666d3376c22bca33b8139f07 authored almost 6 years ago by Jiaming Yuan <[email protected]>

Fix gpu coordinate running on multi-gpu. (#3893)

97984f4890e1b6357d8f98d121f2050220852998 authored almost 6 years ago by Jiaming Yuan <[email protected]>

Update README.md (#3872)

SparkWithDataFrame was not there anymore. So replace with SparkMLlibPipeline.scala

0ddb8a7661013c75674704872c22273415268dbd authored almost 6 years ago by ajing <[email protected]>

Fix a typo in the R-package documentation: max.deph -> max.depth (#3890)

Signed-off-by: Jiacheng Xu <[email protected]>

d810e6dec91c84d6cf469403f6efb8663199eacd authored almost 6 years ago by Jiacheng Xu <[email protected]>

Remove unnecessary warning when 'gblinear' is selected (#3888)

be0bb7dd908ba910f73ee33095df915df6a0c138 authored almost 6 years ago by Philip Hyunsu Cho <[email protected]>