Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
6,027 Commits 32 Branches 59 Tags
9dd8d70f0e00a214585f145a85c0c21ce6f132f1
Commit Graph
6027 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Jiaming Yuan 021f8bf28b Fix pylint. (#7498) 2021-12-07 13:23:30 +08:00
Jiaming Yuan eee527d264 Add approx partitioner. (#7467) 2021-11-27 15:22:06 +08:00
Jiaming Yuan 85cbd32c5a Add range-based slicing to tensor view. (#7453) 2021-11-27 13:42:36 +08:00
danmarinescu 6f38f5affa Updated CMake version requirement in build.rst (#7487) 
The documentation states that to build from source you need CMake 3.13 or higher. However, according to https://github.com/dmlc/xgboost/blob/master/CMakeLists.txt#L1 CMake 3.14 or higher is required.
 2021-11-27 09:58:01 +08:00
Jiaming Yuan 557ffc4bf5 Reduce base margin to 2 dim for now. (#7455) 2021-11-27 00:46:13 +08:00
Jiaming Yuan bf7bb575b4 Test CPU histogram with cat data. (#7465) 2021-11-27 00:43:28 +08:00
Bobby Wang 24be04e848 [jvm-packages] Add DeviceQuantileDMatrix to Scala binding (#7459) 2021-11-24 20:23:18 +08:00
Philip Hyunsu Cho 619c450a49 [CI] Add missing step extract_branch (#7479) 2021-11-24 17:35:59 +08:00
Jiaming Yuan 820e1c01ef Fix macos package upload. (#7475) 
* Split up the tests.
 2021-11-24 03:43:49 +08:00
Jiaming Yuan 488f12a996 Fix github macos package upload. (#7474) 2021-11-24 00:29:11 +08:00
Jiaming Yuan c024c42dce Modernize XGBoost Python document. (#7468) 
* Use sphinx gallery to integrate examples.
* Remove mock objects.
* Add dask doc inventory.
 2021-11-23 23:24:52 +08:00
Philip Hyunsu Cho 96a9848c9e [CI] Fix continuous delivery pipeline for MacOS (#7472) 2021-11-23 22:22:08 +08:00
Jiaming Yuan b124a27f57 Support scipy sparse in dask. (#7457) 2021-11-23 16:45:36 +08:00
Jiaming Yuan 5262e933f7 Remove unnecessary constexpr. (#7466) 2021-11-23 16:42:08 +08:00
Philip Hyunsu Cho 0c67685e43 [CI] Add a helper script to aid Maven release (#7470) 
* [CI] Add a helper script to aid Maven release

* Move script to dev/ [skip ci]

* Update command [skip ci]
 2021-11-23 00:11:07 -08:00
Harvey 0552ca8021 Fix typo (#7469) 2021-11-23 08:58:45 +08:00
Jiaming Yuan 176110a22d Support external memory in CPU histogram building. (#7372) 2021-11-23 01:13:33 +08:00
Jiaming Yuan d33854af1b [Breaking] Accept multi-dim meta info. (#7405) 
This PR changes base_margin into a 3-dim array, with one of them being reserved for multi-target classification. Also, a breaking change is made for binary serialization due to extra dimension along with a fix for saving the feature weights. Lastly, it unifies the prediction initialization between CPU and GPU. After this PR, the meta info setter in Python will be based on array interface.
 2021-11-18 23:02:54 +08:00
Jiaming Yuan 9fb4338964 Add test for eta and mitigate float error. (#7446) 
* Add eta test.
* Don't skip test.
 2021-11-18 20:42:48 +08:00
Bobby Wang 7cfb310eb4 Rework transform (#7440) 
extract the common part of transform code from XGBoostClassifier
and XGBoostRegressor
 2021-11-18 15:48:57 +08:00
Philip Hyunsu Cho 2adf222fb2 [CI] CI cost saving (#7407) 
* [CI] Drop CUDA 10.1; Require 11.0

* Change NCCL version

* Use CUDA 10.1 for clang-tidy, for now

* Remove JDK 11 and 12

* Fix NCCL version

* Don't require 11.0 just yet, until clang-tidy is fixed

* Skip MultiClassesSerializationTest.GpuHist
 2021-11-17 21:02:20 -08:00
Jiaming Yuan b0015fda96 Fix R CRAN failures. (#7404) 
* Remove hist builder dtor.

* Initialize values.

* Tolerance.

* Remove the use of nthread in col maker.
 2021-11-16 10:51:12 +08:00
Jiaming Yuan 55ee272ea8 Extend array interface to handle ndarray. (#7434) 
* Extend array interface to handle ndarray.

The `ArrayInterface` class is extended to support multi-dim array inputs. Previously this
class handles only 2-dim (vector is also matrix).  This PR specifies the expected
dimension at compile-time and the array interface can perform various checks automatically
for input data. Also, adapters like CSR are more rigorous about their input.  Lastly, row
vector and column vector are handled without intervention from the caller.
 2021-11-16 09:52:15 +08:00
Jiaming Yuan e27f543deb Set use_logger in tracker to false. (#7438) 2021-11-16 05:12:42 +08:00
Jiaming Yuan d4274bc556 Fix typo. (#7433) 2021-11-15 01:28:11 +08:00
Jiaming Yuan a7057fa64c Implement typed storage for tensor. (#7429) 
* Add `Tensor` class.
* Add elementwise kernel for CPU and GPU.
* Add unravel index.
* Move some computation to compile time.
 2021-11-14 18:53:13 +08:00
Kian Meng Ang d27a11ff87 Fix typos in python package (#7432) 2021-11-14 17:20:19 +08:00
Jiaming Yuan 8cc75f1576 Cleanup Python tests. (#7426) 2021-11-14 15:47:05 +08:00
Jiaming Yuan 38ca96c9fc [CI] Install igraph as binary. (#7417) 2021-11-12 19:04:28 +08:00
Jiaming Yuan 46726ec176 Expose build info (#7399) 2021-11-12 18:22:46 +08:00
Jiaming Yuan 937fa282b5 Extract string view. (#7416) 
* Add equality operators.
* Return a view in substr.
* Add proper iterator types.
 2021-11-12 18:22:30 +08:00
Jiaming Yuan ca6f980932 Check number of trees in inplace predict. (#7409) 2021-11-12 18:20:23 +08:00
Jiaming Yuan 97d7582457 Delay breaking changes to 1.6. (#7420) 
The patch is too big to be backported.
 2021-11-12 16:46:03 +08:00
Bobby Wang cb685607b2 [jvm-packages] Rework the train pipeline (#7401) 
1. Add PreXGBoost to build RDD[Watches] from Dataset
2. Feed RDD[Watches] built from PreXGBoost to XGBoost to train
 2021-11-10 17:51:38 +08:00
Jiaming Yuan 8df0a252b7 [doc] Update document for GPU. [skip ci] (#7403) 
* Remove outdated workaround and description.
 2021-11-09 02:05:55 +08:00
Jiaming Yuan d7d1b6e3a6 CPU evaluation for cat data. (#7393) 
* Implementation for one hot based.
* Implementation for partition based. (LightGBM)
 2021-11-06 14:41:35 +08:00
Jiaming Yuan 6ede12412c Update dmlc-core and use data iter for GPU sampling tests. (#7398) 
* Update dmlc-core.
* New parquet parser in dmlc-core.
* Use data iter for GPU sampling tests.
 2021-11-06 05:12:49 +08:00
Jiaming Yuan c968217ca8 [R] Fix global feature importance and predict with 1 sample. (#7394) 
* [R] Fix global feature importance.

* Add implementation for tree index.  The parameter is not documented in C API since we
should work on porting the model slicing to R instead of supporting more use of tree
index.

* Fix the difference between "gain" and "total_gain".

* debug.

* Fix prediction.
 2021-11-05 10:07:00 +08:00
Jiaming Yuan 48aff0eabd [doc][jvm-packages] Update information about Python tracker. [skip ci] (#7396) 2021-11-05 05:55:13 +08:00
Jiaming Yuan b06040b6d0 Implement a general array view. (#7365) 
* Replace existing matrix and vector view.

This is to prepare for handling higher dimension data and prediction when we support multi-target models.
 2021-11-05 04:16:11 +08:00
Jiaming Yuan 232144ca09 Add note about CRAN release [skip ci] (#7395) 2021-11-05 00:34:14 +08:00
Jiaming Yuan 4100827971 Pass infomation about objective to tree methods. (#7385) 
* Define the `ObjInfo` and pass it down to every tree updater.
 2021-11-04 01:52:44 +08:00
Jiaming Yuan ccdabe4512 Support building gradient index with cat data. (#7371) 2021-11-03 22:37:37 +08:00
Jiaming Yuan 57a4b4ff64 Handle OMP_THREAD_LIMIT. (#7390) 2021-11-03 15:44:38 +08:00
Jiaming Yuan e6ab594e14 Change shebang used in CLI demo. (#7389) 
Change from system Python to environment python3.  For Ubuntu 20.04, only `python3` is
available and there's no `python`.  So at least `python3` is consistent with Python
virtual env, Ubuntu and anaconda.
 2021-11-02 22:11:19 +08:00
Jiaming Yuan a55d43ccfd Add test for invalid categorical data values. (#7380) 
* Add test for invalid categorical data values.

* Add check during sketching.
 2021-11-02 18:00:52 +08:00
Jiaming Yuan c74df31bf9 Cleanup the train function. (#7377) 
* Move attribute setter to callback.
* Remove the internal train function.
* Remove unnecessary initialization.
 2021-11-02 18:00:26 +08:00
Jiaming Yuan 154b15060e Move callbacks from fit to __init__. (#7375) 2021-11-02 17:51:42 +08:00
Jiaming Yuan 32e673d8c4 Support building with CTK11.5. (#7379) 
* Support building with CTK11.5.

* Require system cub installation for CTK11.4+.
* Check thrust version for segmented sort.
 2021-11-02 16:22:26 +08:00
Jiaming Yuan a13321148a Support multi-class with base margin. (#7381) 
This is already partially supported but never properly tested. So the only possible way to use it is calling `numpy.ndarray.flatten` with `base_margin` before passing it into XGBoost. This PR adds proper support
for most of the data types along with tests.
 2021-11-02 13:38:00 +08:00