Github user sethah commented on a diff in the pull request: https://github.com/apache/spark/pull/11136#discussion_r52403617 --- Diff: mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala --- @@ -0,0 +1,472 @@ +/* + * 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.regression + +import breeze.stats.distributions.{Gaussian => GD} + +import org.apache.spark.Logging +import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.ml.PredictorParams +import org.apache.spark.ml.feature.Instance +import org.apache.spark.ml.optim._ +import org.apache.spark.ml.param._ +import org.apache.spark.ml.param.shared._ +import org.apache.spark.ml.util.Identifiable +import org.apache.spark.mllib.linalg.{BLAS, Vector} +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.{DataFrame, Row} +import org.apache.spark.sql.functions._ + +/** + * Params for Generalized Linear Regression. + */ +private[regression] trait GeneralizedLinearRegressionParams extends PredictorParams + with HasFitIntercept with HasMaxIter with HasTol with HasRegParam with HasWeightCol + with HasSolver with Logging { + + /** + * Param for the name of family which is a description of the error distribution + * to be used in the model. + * Supported options: "gaussian", "binomial", "poisson" and "gamma". + * @group param + */ + @Since("2.0.0") + final val family: Param[String] = new Param(this, "family", + "the name of family which is a description of the error distribution to be used in the model", + ParamValidators.inArray[String](GeneralizedLinearRegression.supportedFamilies.toArray)) + + /** @group getParam */ + @Since("2.0.0") + def getFamily: String = $(family) + + /** + * Param for the name of the model link function. + * Supported options: "identity", "log", "inverse", "logit", "probit", "cloglog" and "sqrt". + * @group param + */ + @Since("2.0.0") + final val link: Param[String] = new Param(this, "link", "the name of the model link function", + ParamValidators.inArray[String](GeneralizedLinearRegression.supportedLinks.toArray)) + + /** @group getParam */ + @Since("2.0.0") + def getLink: String = $(link) + + @Since("2.0.0") + override def validateParams(): Unit = { + require(GeneralizedLinearRegression.supportedFamilyLinkPairs.contains($(family) -> $(link)), --- End diff -- This line causes a `NoSuchElementException` when you call `fit` without setting a `Link` function. IMO if you set a `Family` for the Estimator, and that family has a default `Link`, then you shouldn't have to explicitly set the `Link` function. In the setter for `Family`, can we check `if !isSet(link)` and set link to the default link?
--- 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