CVS log for pkgsrc/math/py-xgboost/Makefile

Up to [cvs.NetBSD.org] / pkgsrc / math / py-xgboost

Request diff between arbitrary revisions

Keyword substitution: kv
Default branch: MAIN

py-xgboost: mark as broken on SunOS

NotImplementedError: System SunOS not supported

py-xgboost: updated to 2.1.4

2.1.4

The 2.1.4 patch release incorporates the following fixes on top of the 2.1.3 release:

XGBoost is now compatible with scikit-learn 1.6
Build wheels with CUDA 12.8 and enable Blackwell support
Adapt to RMM 25.02 logger changes

py-xgboost: updated to 2.1.3

2.1.3

[pyspark] Support large model size
Fix rng for the column sampler
Handle cudf.pandas proxy objects properly

2.1.2

Clean up and modernize release-artifacts.py
Fix ellpack categorical feature with missing values.
Fix unbiased ltr with training continuation.
Fix potential race in feature constraint.
Fix boolean array for arrow-backed DF.
Ensure that pip check does not fail due to a bad platform tag
Check cub errors
Limit the maximum number of threads.
Fixes for large size clusters.
POSIX compliant poll.h and mmap

*: clean-up after python38 removal

py-xgboost: updated to 2.1.1

The 2.1.1 patch release make the following bug fixes:

[Dask] Disable broadcast in the scatter call so that predict function won't hang
[Dask] Handle empty partitions correctly
Fix federated learning for the encrypted GRPC backend
Fix a race condition in column splitter
Gracefully handle cases where system files like /sys/fs/cgroup/cpu.max are not readable by the user
Fix build and C++ tests for FreeBSD
Clarify the requirement Pandas 1.2+
More robust endianness detection in R package build

In addition, it contains several enhancements:

Publish JVM packages targeting Linux ARM64
Publish a CPU-only wheel under name xgboost-cpu
Support building with CUDA Toolkit 12.5 and latest CCCL

py-xgboost: insists on gcc 8.1+

py-xgboost: remove unused REPLACE_; spotted by @wiz

py-xgboost: updated to 2.0.3

2.0.3

[backport][sklearn] Fix loading model attributes.
[backport][py] Use the first found native library.
[backport] [CI] Upload libxgboost4j.dylib (M1) to S3 bucket
[jvm-packages] Fix POM for xgboost-jvm metapackage

*: remove more references to Python 3.7

*: restrict py-numpy users to 3.9+ in preparation for update

py-xgboost: updated to 1.7.6

1.7.6 Patch Release

Bug Fixes

Fix distributed training with mixed dense and sparse partitions.
Fix monotone constraints on CPU with large trees.
[spark] Make the spark model have the same UID as its estimator
Optimize prediction with QuantileDMatrix.

Document

Improve doxygen
Update the cuDF pip index URL.

Maintenance

Fix tests with pandas 2.0.

py-xgboost: added version 1.7.5

XGBoost is an optimized distributed gradient boosting library designed to be
highly efficient, flexible and portable. It implements machine learning
algorithms under the Gradient Boosting framework. XGBoost provides a parallel
tree boosting (also known as GBDT, GBM) that solve many data science problems
in a fast and accurate way. The same code runs on major distributed environment
(Kubernetes, Hadoop, SGE, Dask, Spark, PySpark) and can solve problems beyond
billions of examples.