Github user etrain commented on a diff in the pull request: https://github.com/apache/spark/pull/3637#discussion_r22691031 --- Diff: examples/src/main/scala/org/apache/spark/examples/ml/DeveloperApiExample.scala --- @@ -0,0 +1,195 @@ +/* + * 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 org.apache.spark.{SparkConf, SparkContext} +import org.apache.spark.SparkContext._ +import org.apache.spark.ml.classification.{Classifier, ClassifierParams, ClassificationModel} +import org.apache.spark.ml.param.{Params, IntParam, ParamMap} +import org.apache.spark.mllib.linalg.{BLAS, Vector, Vectors, VectorUDT} +import org.apache.spark.mllib.regression.LabeledPoint +import org.apache.spark.sql.{DataType, SchemaRDD, Row, SQLContext} + +/** + * A simple example demonstrating how to write your own learning algorithm using Estimator, + * Transformer, and other abstractions. + * This mimics [[org.apache.spark.ml.classification.LogisticRegression]]. + * Run with + * {{{ + * bin/run-example ml.DeveloperApiExample + * }}} + */ +object DeveloperApiExample { + + def main(args: Array[String]) { + val conf = new SparkConf().setAppName("DeveloperApiExample") + val sc = new SparkContext(conf) + val sqlContext = new SQLContext(sc) + import sqlContext._ + + // Prepare training data. + val training = sparkContext.parallelize(Seq( + LabeledPoint(1.0, Vectors.dense(0.0, 1.1, 0.1)), + LabeledPoint(0.0, Vectors.dense(2.0, 1.0, -1.0)), + LabeledPoint(0.0, Vectors.dense(2.0, 1.3, 1.0)), + LabeledPoint(1.0, Vectors.dense(0.0, 1.2, -0.5)))) + + // Create a LogisticRegression instance. This instance is an Estimator. + val lr = new MyLogisticRegression() + // Print out the parameters, documentation, and any default values. + println("MyLogisticRegression parameters:\n" + lr.explainParams() + "\n") + + // We may set parameters using setter methods. + lr.setMaxIter(10) + + // Learn a LogisticRegression model. This uses the parameters stored in lr. + val model = lr.fit(training) + + // Prepare test data. + val test = sparkContext.parallelize(Seq( + LabeledPoint(1.0, Vectors.dense(-1.0, 1.5, 1.3)), + LabeledPoint(0.0, Vectors.dense(3.0, 2.0, -0.1)), + LabeledPoint(1.0, Vectors.dense(0.0, 2.2, -1.5)))) + + // Make predictions on test data. + val sumPredictions: Double = model.transform(test) + .select('features, 'label, 'prediction) + .collect() + .map { case Row(features: Vector, label: Double, prediction: Double) => + prediction + }.sum + assert(sumPredictions == 0.0, + "MyLogisticRegression predicted something other than 0, even though all weights are 0!") + } +} + +/** + * Example of defining a parameter trait for a user-defined type of [[Classifier]]. + * + * NOTE: This is private since it is an example. In practice, you may not want it to be private. + */ +private trait MyLogisticRegressionParams extends ClassifierParams { + + /** param for max number of iterations */ + val maxIter: IntParam = new IntParam(this, "maxIter", "max number of iterations") + def getMaxIter: Int = get(maxIter) --- End diff -- I'm a little confused here - do I understand correctly that you need to specify a getter by convention? Or is this just showing that you *can* specify a getter?
--- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org