forked from apache/spark
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[SPARK-19456][SPARKR] Add LinearSVC R API
## What changes were proposed in this pull request? Linear SVM classifier is newly added into ML and python API has been added. This JIRA is to add R side API. Marked as WIP, as I am designing unit tests. ## How was this patch tested? Please review http://spark.apache.org/contributing.html before opening a pull request. Author: [email protected] <[email protected]> Closes apache#16800 from wangmiao1981/svc.
- Loading branch information
1 parent
7c9cec4
commit 3f6abff
Showing
7 changed files
with
341 additions
and
4 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
151 changes: 151 additions & 0 deletions
151
mllib/src/main/scala/org/apache/spark/ml/r/LinearSVCWrapper.scala
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,151 @@ | ||
| /* | ||
| * 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.r | ||
|
|
||
| import org.apache.hadoop.fs.Path | ||
| import org.json4s._ | ||
| import org.json4s.JsonDSL._ | ||
| import org.json4s.jackson.JsonMethods._ | ||
|
|
||
| import org.apache.spark.ml.{Pipeline, PipelineModel} | ||
| import org.apache.spark.ml.classification.{LinearSVC, LinearSVCModel} | ||
| import org.apache.spark.ml.feature.{IndexToString, RFormula} | ||
| import org.apache.spark.ml.r.RWrapperUtils._ | ||
| import org.apache.spark.ml.util._ | ||
| import org.apache.spark.sql.{DataFrame, Dataset} | ||
|
|
||
| private[r] class LinearSVCWrapper private ( | ||
| val pipeline: PipelineModel, | ||
| val features: Array[String], | ||
| val labels: Array[String]) extends MLWritable { | ||
| import LinearSVCWrapper._ | ||
|
|
||
| private val svcModel: LinearSVCModel = | ||
| pipeline.stages(1).asInstanceOf[LinearSVCModel] | ||
|
|
||
| lazy val coefficients: Array[Double] = svcModel.coefficients.toArray | ||
|
|
||
| lazy val intercept: Double = svcModel.intercept | ||
|
|
||
| lazy val numClasses: Int = svcModel.numClasses | ||
|
|
||
| lazy val numFeatures: Int = svcModel.numFeatures | ||
|
|
||
| def transform(dataset: Dataset[_]): DataFrame = { | ||
| pipeline.transform(dataset) | ||
| .drop(PREDICTED_LABEL_INDEX_COL) | ||
| .drop(svcModel.getFeaturesCol) | ||
| .drop(svcModel.getLabelCol) | ||
| } | ||
|
|
||
| override def write: MLWriter = new LinearSVCWrapper.LinearSVCWrapperWriter(this) | ||
| } | ||
|
|
||
| private[r] object LinearSVCWrapper | ||
| extends MLReadable[LinearSVCWrapper] { | ||
|
|
||
| val PREDICTED_LABEL_INDEX_COL = "pred_label_idx" | ||
| val PREDICTED_LABEL_COL = "prediction" | ||
|
|
||
| def fit( | ||
| data: DataFrame, | ||
| formula: String, | ||
| regParam: Double, | ||
| maxIter: Int, | ||
| tol: Double, | ||
| standardization: Boolean, | ||
| threshold: Double, | ||
| weightCol: String, | ||
| aggregationDepth: Int | ||
| ): LinearSVCWrapper = { | ||
|
|
||
| val rFormula = new RFormula() | ||
| .setFormula(formula) | ||
| .setForceIndexLabel(true) | ||
| checkDataColumns(rFormula, data) | ||
| val rFormulaModel = rFormula.fit(data) | ||
|
|
||
| val fitIntercept = rFormula.hasIntercept | ||
|
|
||
| // get labels and feature names from output schema | ||
| val (features, labels) = getFeaturesAndLabels(rFormulaModel, data) | ||
|
|
||
| // assemble and fit the pipeline | ||
| val svc = new LinearSVC() | ||
| .setRegParam(regParam) | ||
| .setMaxIter(maxIter) | ||
| .setTol(tol) | ||
| .setFitIntercept(fitIntercept) | ||
| .setStandardization(standardization) | ||
| .setFeaturesCol(rFormula.getFeaturesCol) | ||
| .setLabelCol(rFormula.getLabelCol) | ||
| .setPredictionCol(PREDICTED_LABEL_INDEX_COL) | ||
| .setThreshold(threshold) | ||
| .setAggregationDepth(aggregationDepth) | ||
|
|
||
| if (weightCol != null) svc.setWeightCol(weightCol) | ||
|
|
||
| val idxToStr = new IndexToString() | ||
| .setInputCol(PREDICTED_LABEL_INDEX_COL) | ||
| .setOutputCol(PREDICTED_LABEL_COL) | ||
| .setLabels(labels) | ||
|
|
||
| val pipeline = new Pipeline() | ||
| .setStages(Array(rFormulaModel, svc, idxToStr)) | ||
| .fit(data) | ||
|
|
||
| new LinearSVCWrapper(pipeline, features, labels) | ||
| } | ||
|
|
||
| override def read: MLReader[LinearSVCWrapper] = new LinearSVCWrapperReader | ||
|
|
||
| override def load(path: String): LinearSVCWrapper = super.load(path) | ||
|
|
||
| class LinearSVCWrapperWriter(instance: LinearSVCWrapper) extends MLWriter { | ||
|
|
||
| override protected def saveImpl(path: String): Unit = { | ||
| val rMetadataPath = new Path(path, "rMetadata").toString | ||
| val pipelinePath = new Path(path, "pipeline").toString | ||
|
|
||
| val rMetadata = ("class" -> instance.getClass.getName) ~ | ||
| ("features" -> instance.features.toSeq) ~ | ||
| ("labels" -> instance.labels.toSeq) | ||
| val rMetadataJson: String = compact(render(rMetadata)) | ||
| sc.parallelize(Seq(rMetadataJson), 1).saveAsTextFile(rMetadataPath) | ||
|
|
||
| instance.pipeline.save(pipelinePath) | ||
| } | ||
| } | ||
|
|
||
| class LinearSVCWrapperReader extends MLReader[LinearSVCWrapper] { | ||
|
|
||
| override def load(path: String): LinearSVCWrapper = { | ||
| implicit val format = DefaultFormats | ||
| val rMetadataPath = new Path(path, "rMetadata").toString | ||
| val pipelinePath = new Path(path, "pipeline").toString | ||
|
|
||
| val rMetadataStr = sc.textFile(rMetadataPath, 1).first() | ||
| val rMetadata = parse(rMetadataStr) | ||
| val features = (rMetadata \ "features").extract[Array[String]] | ||
| val labels = (rMetadata \ "labels").extract[Array[String]] | ||
|
|
||
| val pipeline = PipelineModel.load(pipelinePath) | ||
| new LinearSVCWrapper(pipeline, features, labels) | ||
| } | ||
| } | ||
| } |
Oops, something went wrong.