diff options
author | Xiangrui Meng <meng@databricks.com> | 2016-06-21 15:46:14 -0700 |
---|---|---|
committer | Reynold Xin <rxin@databricks.com> | 2016-06-21 15:46:14 -0700 |
commit | f4e8c31adf45af05751e0d77aefb5cacc58375ee (patch) | |
tree | 4a19c7f6c5a08f19c0c671f9c90074c538271106 /mllib/src | |
parent | dbfdae4e41a900de01b48639d6554d32edbb2e0b (diff) | |
download | spark-f4e8c31adf45af05751e0d77aefb5cacc58375ee.tar.gz spark-f4e8c31adf45af05751e0d77aefb5cacc58375ee.tar.bz2 spark-f4e8c31adf45af05751e0d77aefb5cacc58375ee.zip |
[SPARK-16117][MLLIB] hide LibSVMFileFormat and move its doc to LibSVMDataSource
## What changes were proposed in this pull request?
LibSVMFileFormat implements data source for LIBSVM format. However, users do not really need to call its APIs to use it. So we should hide it in the public API docs. The main issue is that we still need to put the documentation and example code somewhere. The proposal it to have a dummy class to hold the documentation, as a workaround to https://issues.scala-lang.org/browse/SI-8124.
## How was this patch tested?
Manually checked the generated API doc and tested loading LIBSVM data.
Author: Xiangrui Meng <meng@databricks.com>
Closes #13819 from mengxr/SPARK-16117.
Diffstat (limited to 'mllib/src')
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/ml/source/libsvm/LibSVMDataSource.scala | 56 | ||||
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/ml/source/libsvm/LibSVMRelation.scala | 41 |
2 files changed, 59 insertions, 38 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/ml/source/libsvm/LibSVMDataSource.scala b/mllib/src/main/scala/org/apache/spark/ml/source/libsvm/LibSVMDataSource.scala new file mode 100644 index 0000000000..73d813064d --- /dev/null +++ b/mllib/src/main/scala/org/apache/spark/ml/source/libsvm/LibSVMDataSource.scala @@ -0,0 +1,56 @@ +/* + * 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.ml.source.libsvm + +import org.apache.spark.ml.linalg.Vector +import org.apache.spark.sql.{DataFrame, DataFrameReader} + +/** + * `libsvm` package implements Spark SQL data source API for loading LIBSVM data as [[DataFrame]]. + * The loaded [[DataFrame]] has two columns: `label` containing labels stored as doubles and + * `features` containing feature vectors stored as [[Vector]]s. + * + * To use LIBSVM data source, you need to set "libsvm" as the format in [[DataFrameReader]] and + * optionally specify options, for example: + * {{{ + * // Scala + * val df = spark.read.format("libsvm") + * .option("numFeatures", "780") + * .load("data/mllib/sample_libsvm_data.txt") + * + * // Java + * Dataset<Row> df = spark.read().format("libsvm") + * .option("numFeatures, "780") + * .load("data/mllib/sample_libsvm_data.txt"); + * }}} + * + * LIBSVM data source supports the following options: + * - "numFeatures": number of features. + * If unspecified or nonpositive, the number of features will be determined automatically at the + * cost of one additional pass. + * This is also useful when the dataset is already split into multiple files and you want to load + * them separately, because some features may not present in certain files, which leads to + * inconsistent feature dimensions. + * - "vectorType": feature vector type, "sparse" (default) or "dense". + * + * Note that this class is public for documentation purpose. Please don't use this class directly. + * Rather, use the data source API as illustrated above. + * + * @see [[https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/ LIBSVM datasets]] + */ +class LibSVMDataSource private() {} diff --git a/mllib/src/main/scala/org/apache/spark/ml/source/libsvm/LibSVMRelation.scala b/mllib/src/main/scala/org/apache/spark/ml/source/libsvm/LibSVMRelation.scala index 4988dd66f8..034223e115 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/source/libsvm/LibSVMRelation.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/source/libsvm/LibSVMRelation.scala @@ -25,11 +25,10 @@ import org.apache.hadoop.io.{NullWritable, Text} import org.apache.hadoop.mapreduce.{Job, RecordWriter, TaskAttemptContext} import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat -import org.apache.spark.annotation.Since import org.apache.spark.ml.feature.LabeledPoint import org.apache.spark.ml.linalg.{Vector, Vectors, VectorUDT} import org.apache.spark.mllib.util.MLUtils -import org.apache.spark.sql.{DataFrame, DataFrameReader, Row, SparkSession} +import org.apache.spark.sql.{Row, SparkSession} import org.apache.spark.sql.catalyst.InternalRow import org.apache.spark.sql.catalyst.encoders.RowEncoder import org.apache.spark.sql.catalyst.expressions.AttributeReference @@ -77,44 +76,10 @@ private[libsvm] class LibSVMOutputWriter( } } -/** - * `libsvm` package implements Spark SQL data source API for loading LIBSVM data as [[DataFrame]]. - * The loaded [[DataFrame]] has two columns: `label` containing labels stored as doubles and - * `features` containing feature vectors stored as [[Vector]]s. - * - * To use LIBSVM data source, you need to set "libsvm" as the format in [[DataFrameReader]] and - * optionally specify options, for example: - * {{{ - * // Scala - * val df = spark.read.format("libsvm") - * .option("numFeatures", "780") - * .load("data/mllib/sample_libsvm_data.txt") - * - * // Java - * Dataset<Row> df = spark.read().format("libsvm") - * .option("numFeatures, "780") - * .load("data/mllib/sample_libsvm_data.txt"); - * }}} - * - * LIBSVM data source supports the following options: - * - "numFeatures": number of features. - * If unspecified or nonpositive, the number of features will be determined automatically at the - * cost of one additional pass. - * This is also useful when the dataset is already split into multiple files and you want to load - * them separately, because some features may not present in certain files, which leads to - * inconsistent feature dimensions. - * - "vectorType": feature vector type, "sparse" (default) or "dense". - * - * @see [[https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/ LIBSVM datasets]] - * - * Note that this class is public for documentation purpose. Please don't use this class directly. - * Rather, use the data source API as illustrated above. - */ +/** @see [[LibSVMDataSource]] for public documentation. */ // If this is moved or renamed, please update DataSource's backwardCompatibilityMap. -@Since("1.6.0") -class LibSVMFileFormat extends TextBasedFileFormat with DataSourceRegister { +private[libsvm] class LibSVMFileFormat extends TextBasedFileFormat with DataSourceRegister { - @Since("1.6.0") override def shortName(): String = "libsvm" override def toString: String = "LibSVM" |