Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Mark next release as 1.7 instead of 2.0 (#8281)

Browse Source
This commit is contained in:
Jiaming Yuan
2022-09-28 14:33:37 +08:00
committed by GitHub
parent 6d1452074a
commit f835368bcf
19 changed files with 38 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
doc/jvm/xgboost4j_spark_tutorial.rst
View File

@@ -347,7 +347,7 @@ and then loading the model in another session:
.. note::
Besides dumping the model to raw format, users are able to dump the model to be json or ubj format from ``version 2.0.0+``.
Besides dumping the model to raw format, users are able to dump the model to be json or ubj format from ``version 1.7.0+``.
.. code-block:: scala
@@ -362,7 +362,7 @@ Interact with Other Bindings of XGBoost
After we train a model with XGBoost4j-Spark on massive dataset, sometimes we want to do model serving
in single machine or integrate it with other single node libraries for further processing.
After saving the model, we can load this model with single node Python XGBoost directly from ``version 2.0.0+``.
After saving the model, we can load this model with single node Python XGBoost directly from ``version 1.7.0+``.
.. code-block:: scala
@@ -375,7 +375,7 @@ After saving the model, we can load this model with single node Python XGBoost d
bst = xgb.Booster({'nthread': 4})
bst.load_model("/tmp/xgbClassificationModel/data/XGBoostClassificationModel")
Before ``version 2.0.0``, XGBoost4j-Spark needs to export model to local manually by:
Before ``version 1.7.0``, XGBoost4j-Spark needs to export model to local manually by:
.. code-block:: scala

7
doc/parameter.rst
View File

@@ -237,7 +237,7 @@ These parameters are only used for training with categorical data. See
.. versionadded:: 1.6
.. note:: This parameter is experimental. ``exact`` tree method is not supported yet.
.. note:: This parameter is experimental. ``exact`` tree method is not yet supported.
- A threshold for deciding whether XGBoost should use one-hot encoding based split for
categorical data. When number of categories is lesser than the threshold then one-hot
@@ -247,10 +247,9 @@ These parameters are only used for training with categorical data. See
* ``max_cat_threshold``
.. versionadded:: 2.0
.. versionadded:: 1.7.0
.. note:: This parameter is experimental. ``exact`` and ``gpu_hist`` tree methods are
not supported yet.
.. note:: This parameter is experimental. ``exact`` tree method is not yet supported.
- Maximum number of categories considered for each split. Used only by partition-based
splits for preventing over-fitting.

2
doc/tutorials/dask.rst
View File

@@ -508,7 +508,7 @@ dask config is used:
IPv6 Support
************
.. versionadded:: 2.0.0
.. versionadded:: 1.7.0
XGBoost has initial IPv6 support for the dask interface on Linux. Due to most of the
cluster support for IPv6 is partial (dual stack instead of IPv6 only), we require

4
doc/tutorials/spark_estimator.rst
View File

@@ -1,8 +1,8 @@
###############################
Using XGBoost PySpark Estimator
###############################
Starting from version 2.0, xgboost supports pyspark estimator APIs.
The feature is still experimental and not yet ready for production use.
Starting from version 1.7.0, xgboost supports pyspark estimator APIs. The feature is
still experimental and not yet ready for production use.
*****************
SparkXGBRegressor