diff options
author | Xiangrui Meng <meng@databricks.com> | 2016-06-23 08:26:17 -0700 |
---|---|---|
committer | Xiangrui Meng <meng@databricks.com> | 2016-06-23 08:26:17 -0700 |
commit | 65d1f0f716f50dd14b5dfe1e7fac772f1b4d2be0 (patch) | |
tree | 87587e2631e1e029baf5f7b83e19fe186b121f83 | |
parent | 5bf2889bfcfd776e7ee1369443a0474421a800bd (diff) | |
download | spark-65d1f0f716f50dd14b5dfe1e7fac772f1b4d2be0.tar.gz spark-65d1f0f716f50dd14b5dfe1e7fac772f1b4d2be0.tar.bz2 spark-65d1f0f716f50dd14b5dfe1e7fac772f1b4d2be0.zip |
[SPARK-16154][MLLIB] Update spark.ml and spark.mllib package docs
## What changes were proposed in this pull request?
Since we decided to switch spark.mllib package into maintenance mode in 2.0, it would be nice to update the package docs to reflect this change.
## How was this patch tested?
Manually checked generated APIs.
Author: Xiangrui Meng <meng@databricks.com>
Closes #13859 from mengxr/SPARK-16154.
5 files changed, 72 insertions, 9 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/ml/package-info.java b/mllib/src/main/scala/org/apache/spark/ml/package-info.java index 9a40f5dd69..cb97382207 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/package-info.java +++ b/mllib/src/main/scala/org/apache/spark/ml/package-info.java @@ -16,10 +16,7 @@ */ /** - * Spark ML is a component that adds a new set of machine learning APIs to let users quickly - * assemble and configure practical machine learning pipelines. + * DataFrame-based machine learning APIs to let users quickly assemble and configure practical + * machine learning pipelines. */ -@Experimental package org.apache.spark.ml; - -import org.apache.spark.annotation.Experimental; diff --git a/mllib/src/main/scala/org/apache/spark/ml/package.scala b/mllib/src/main/scala/org/apache/spark/ml/package.scala index 5cc328b4a9..a445c675e4 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/package.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/package.scala @@ -18,8 +18,8 @@ package org.apache.spark /** - * Spark ML is a component that adds a new set of machine learning APIs to let users quickly - * assemble and configure practical machine learning pipelines. + * DataFrame-based machine learning APIs to let users quickly assemble and configure practical + * machine learning pipelines. * * @groupname param Parameters * @groupdesc param A list of (hyper-)parameter keys this algorithm can take. Users can set and get diff --git a/mllib/src/main/scala/org/apache/spark/mllib/JavaPackage.java b/mllib/src/main/scala/org/apache/spark/mllib/JavaPackage.java new file mode 100644 index 0000000000..22e34524aa --- /dev/null +++ b/mllib/src/main/scala/org/apache/spark/mllib/JavaPackage.java @@ -0,0 +1,31 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.mllib; + +import org.apache.spark.annotation.AlphaComponent; + +/** + * A dummy class as a workaround to show the package doc of <code>spark.mllib</code> in generated + * Java API docs. + * @see <a href="http://bugs.java.com/bugdatabase/view_bug.do?bug_id=4492654" target="_blank"> + * JDK-4492654</a> + */ +@AlphaComponent +public class JavaPackage { + private JavaPackage() {} +} diff --git a/mllib/src/main/scala/org/apache/spark/mllib/package-info.java b/mllib/src/main/scala/org/apache/spark/mllib/package-info.java index 5962efa96b..72b71b7cd9 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/package-info.java +++ b/mllib/src/main/scala/org/apache/spark/mllib/package-info.java @@ -16,6 +16,26 @@ */ /** - * Spark's machine learning library. + * RDD-based machine learning APIs (in maintenance mode). + * + * The <code>spark.mllib</code> package is in maintenance mode as of the Spark 2.0.0 release to + * encourage migration to the DataFrame-based APIs under the <code>spark.ml</code> package. + * While in maintenance mode, + * <ul> + * <li> + * no new features in the RDD-based <code>spark.mllib</code> package will be accepted, unless + * they block implementing new features in the DataFrame-based <code>spark.ml</code> package; + * </li> + * <li> + * bug fixes in the RDD-based APIs will still be accepted. + * </li> + * </ul> + * + * The developers will continue adding more features to the DataFrame-based APIs in the 2.x series + * to reach feature parity with the RDD-based APIs. + * And once we reach feature parity, this package will be deprecated. + * + * @see <a href="https://issues.apache.org/jira/browse/SPARK-4591" target="_blank">SPARK-4591</a> to + * track the progress of feature parity */ package org.apache.spark.mllib; diff --git a/mllib/src/main/scala/org/apache/spark/mllib/package.scala b/mllib/src/main/scala/org/apache/spark/mllib/package.scala index 5c2b2160c0..9810b6f668 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/package.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/package.scala @@ -18,6 +18,21 @@ package org.apache.spark /** - * Spark's machine learning library. + * RDD-based machine learning APIs (in maintenance mode). + * + * The `spark.mllib` package is in maintenance mode as of the Spark 2.0.0 release to encourage + * migration to the DataFrame-based APIs under the [[org.apache.spark.ml]] package. + * While in maintenance mode, + * + * - no new features in the RDD-based `spark.mllib` package will be accepted, unless they block + * implementing new features in the DataFrame-based `spark.ml` package; + * - bug fixes in the RDD-based APIs will still be accepted. + * + * The developers will continue adding more features to the DataFrame-based APIs in the 2.x series + * to reach feature parity with the RDD-based APIs. + * And once we reach feature parity, this package will be deprecated. + * + * @see [[https://issues.apache.org/jira/browse/SPARK-4591 SPARK-4591]] to track the progress of + * feature parity */ package object mllib |