Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/11136#discussion_r54524989
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/regression/GeneralizedLinearRegression.scala
---
@@ -0,0 +1,577 @@
+/*
+ * 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, SparkException}
+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 GeneralizedLinearRegressionBase 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".
+ * Default is "gaussian".
+ * @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. Supported options: gaussian(default), binomial, poisson and
gamma.",
+
ParamValidators.inArray[String](GeneralizedLinearRegression.supportedFamilyNames.toArray))
+
+ /** @group getParam */
+ @Since("2.0.0")
+ def getFamily: String = $(family)
+
+ /**
+ * Param for the name of link function which provides the relationship
+ * between the linear predictor and the mean of the distribution
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
link function " +
+ "which provides the relationship between the linear predictor and the
mean of the " +
+ "distribution function. Supported options: identity, log, inverse,
logit, probit, " +
+ "cloglog and sqrt.",
+
ParamValidators.inArray[String](GeneralizedLinearRegression.supportedLinkNames.toArray))
+
+ /** @group getParam */
+ @Since("2.0.0")
+ def getLink: String = $(link)
+
+ import GeneralizedLinearRegression._
+
+ @Since("2.0.0")
+ override def validateParams(): Unit = {
+ if ($(solver) == "irls") {
+ setDefault(maxIter -> 25)
+ }
+ if (isDefined(link)) {
+ require(supportedFamilyAndLinkPairs.contains(
+ Family.fromName($(family)) -> Link.fromName($(link))),
"Generalized Linear Regression " +
+ s"with ${$(family)} family does not support ${$(link)} link
function.")
+ }
+ }
+}
+
+/**
+ * :: Experimental ::
+ *
+ * Fit a Generalized Linear Model
([[https://en.wikipedia.org/wiki/Generalized_linear_model]])
+ * specified by giving a symbolic description of the linear predictor
(link function) and
+ * a description of the error distribution (family).
+ * It supports "gaussian", "binomial", "poisson" and "gamma" as family.
+ * Valid link functions for each family is listed below. The first link
function of each family
+ * is the default one.
+ * - "gaussian" -> "identity", "log", "inverse"
+ * - "binomial" -> "logit", "probit", "cloglog"
+ * - "poisson" -> "log", "identity", "sqrt"
+ * - "gamma" -> "inverse", "identity", "log"
+ */
+@Experimental
+@Since("2.0.0")
+class GeneralizedLinearRegression @Since("2.0.0") (@Since("2.0.0")
override val uid: String)
+ extends Regressor[Vector, GeneralizedLinearRegression,
GeneralizedLinearRegressionModel]
+ with GeneralizedLinearRegressionBase with Logging {
+
+ import GeneralizedLinearRegression._
+
+ @Since("2.0.0")
+ def this() = this(Identifiable.randomUID("glm"))
+
+ /**
+ * Sets the value of param [[family]].
+ * Default is "gaussian".
+ * @group setParam
+ */
+ @Since("2.0.0")
+ def setFamily(value: String): this.type = set(family, value)
+ setDefault(family -> Gaussian.name)
+
+ /**
+ * Sets the value of param [[link]].
+ * @group setParam
+ */
+ @Since("2.0.0")
+ def setLink(value: String): this.type = set(link, value)
+
+ /**
+ * Sets if we should fit the intercept.
+ * Default is true.
+ * @group setParam
+ */
+ @Since("2.0.0")
+ def setFitIntercept(value: Boolean): this.type = set(fitIntercept, value)
+
+ /**
+ * Sets the maximum number of iterations.
+ * Default is 25 if the solver algorithm is "irls".
+ * @group setParam
+ */
+ @Since("2.0.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+
+ /**
+ * Sets the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is 1E-6.
+ * @group setParam
+ */
+ @Since("2.0.0")
+ def setTol(value: Double): this.type = set(tol, value)
+ setDefault(tol -> 1E-6)
+
+ /**
+ * Sets the regularization parameter.
+ * Default is 0.0.
+ * @group setParam
+ */
+ @Since("2.0.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Sets the value of param [[weightCol]].
+ * If this is not set or empty, we treat all instance weights as 1.0.
+ * Default is empty, so all instances have weight one.
+ * @group setParam
+ */
+ @Since("2.0.0")
+ def setWeightCol(value: String): this.type = set(weightCol, value)
+ setDefault(weightCol -> "")
+
+ /**
+ * Sets the solver algorithm used for optimization.
+ * Currently only support "irls" which is also the default solver.
+ * @group setParam
+ */
+ @Since("2.0.0")
+ def setSolver(value: String): this.type = set(solver, value)
+ setDefault(solver -> "irls")
+
+ override protected def train(dataset: DataFrame):
GeneralizedLinearRegressionModel = {
+ val familyObj = Family.fromName($(family))
+ val linkObj = if (isDefined(link)) {
+ Link.fromName($(link))
+ } else {
+ familyObj.defaultLink
+ }
+ val familyAndLink = new FamilyAndLink(familyObj, linkObj)
+
+ val numFeatures = dataset.select(col($(featuresCol))).limit(1)
+ .map { case Row(features: Vector) =>
+ features.size
+ }.first()
+ if (numFeatures > WeightedLeastSquares.MAX_NUM_FEATURES) {
+ val msg = "Currently, GeneralizedLinearRegression only supports
number of features" +
+ s" <= ${WeightedLeastSquares.MAX_NUM_FEATURES}. Found $numFeatures
in the input dataset."
+ throw new SparkException(msg)
+ }
+
+ val w = if ($(weightCol).isEmpty) lit(1.0) else col($(weightCol))
+ val instances: RDD[Instance] = dataset.select(col($(labelCol)), w,
col($(featuresCol)))
+ .map { case Row(label: Double, weight: Double, features: Vector) =>
--- End diff --
`.rdd.map` instead of `.map`. This is caused by recent DataFrame API
changes.
---
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
