Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/6115#discussion_r30284079
--- Diff:
examples/src/main/scala/org/apache/spark/examples/ml/OneVsRestExample.scala ---
@@ -0,0 +1,169 @@
+/*
+ * 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.examples.ml
+
+import java.util.concurrent.TimeUnit.{NANOSECONDS => NANO}
+
+import scopt.OptionParser
+
+import org.apache.spark.{SparkContext, SparkConf}
+import org.apache.spark.examples.mllib.AbstractParams
+import org.apache.spark.ml.classification.{OneVsRest, LogisticRegression}
+import org.apache.spark.ml.util.MetadataUtils
+import org.apache.spark.mllib.evaluation.MulticlassMetrics
+import org.apache.spark.mllib.regression.LabeledPoint
+import org.apache.spark.mllib.util.MLUtils
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.SQLContext
+
+/**
+ * An example runner for Multiclass to Binary Reduction with One Vs Rest.
+ * The example uses Logistic Regression as the base classifier. All
parameters that
+ * can be specified on the base classifier can be passed in to the runner
options.
+ * Run with
+ * {{{
+ * ./bin/run-example ml.OneVsRestExample [options]
+ * }}}
+ * For local mode, run
+ * {{{
+ * ./bin/spark-submit --class
org.apache.spark.examples.ml.OneVsRestExample --driver-memory 1g
+ * [examples JAR path] [options]
+ * }}}
+ * If you use it as a template to create your own app, please use
`spark-submit` to submit your app.
+ */
+object OneVsRestExample {
+
+ case class Params private[ml] (input: String = null,
+ testInput: Option[String] = None,
+ maxIter: Int = 100,
+ tol: Double = 1E-6,
+ fitIntercept: Boolean = true,
+ regParam: Option[Double] = None,
+ elasticNetParam: Option[Double] = None,
+ fracTest: Double = 0.2) extends AbstractParams[Params]
+
+ def main(args: Array[String]) {
+ val defaultParams = Params()
+
+ val parser = new OptionParser[Params]("OneVsRest Example") {
+ head("OneVsRest Example: multiclass to binary reduction using
OneVsRest")
+ arg[String]("<input>")
+ .text("input path to labeled examples")
+ .required()
+ .action((x, c) => c.copy(input = x))
+ opt[Double]("fracTest")
+ .text(s"fraction of data to hold out for testing. If given option
testInput, " +
+ s"this option is ignored. default: ${defaultParams.fracTest}")
+ .action((x, c) => c.copy(fracTest = x))
+ opt[String]("testInput")
+ .text("input path to test dataset. If given, option fracTest is
ignored")
+ .action((x,c) => c.copy(testInput = Some(x)))
+ opt[Int]("maxIter")
+ .text(s"maximum number of iterations. default:
${defaultParams.maxIter}")
+ .action((x, c) => c.copy(maxIter = x))
+ opt[Double]("tol")
+ .text(s"the convergence tolerance of iterations. default:
${defaultParams.tol}")
+ .action((x, c) => c.copy(tol = x))
+ opt[Double]("regParam")
+ .text(s"the regularization parameter")
--- End diff --
for logistic regression (same in Java example)
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
