srowen commented on a change in pull request #26124: [SPARK-29224][ML]Implement Factorization Machines as a ml-pipeline component URL: https://github.com/apache/spark/pull/26124#discussion_r356151927
########## File path: mllib/src/main/scala/org/apache/spark/ml/regression/FMRegressor.scala ########## @@ -0,0 +1,839 @@ +/* + * 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 scala.util.Random + +import breeze.linalg.{axpy => brzAxpy, norm => brzNorm, Vector => BV} +import breeze.numerics.{sqrt => brzSqrt} +import org.apache.hadoop.fs.Path + +import org.apache.spark.annotation.Since +import org.apache.spark.internal.Logging +import org.apache.spark.ml.{PredictionModel, Predictor, PredictorParams} +import org.apache.spark.ml.linalg._ +import org.apache.spark.ml.linalg.BLAS._ +import org.apache.spark.ml.param._ +import org.apache.spark.ml.param.shared._ +import org.apache.spark.ml.regression.FactorizationMachines._ +import org.apache.spark.ml.util._ +import org.apache.spark.ml.util.Instrumentation.instrumented +import org.apache.spark.mllib.{linalg => OldLinalg} +import org.apache.spark.mllib.linalg.{Vector => OldVector, Vectors => OldVectors} +import org.apache.spark.mllib.linalg.VectorImplicits._ +import org.apache.spark.mllib.optimization.{Gradient, GradientDescent, SquaredL2Updater, Updater} +import org.apache.spark.mllib.util.MLUtils +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.{Dataset, Row} +import org.apache.spark.sql.functions.col +import org.apache.spark.storage.StorageLevel + +/** + * Params for Factorization Machines + */ +private[ml] trait FactorizationMachinesParams + extends PredictorParams + with HasMaxIter with HasStepSize with HasTol with HasSolver with HasSeed { + + /** + * Param for dimensionality of the factors (>= 0) + * @group param + */ + @Since("3.0.0") + final val factorSize: IntParam = new IntParam(this, "factorSize", + "Dimensionality of the factor vectors, " + + "which are used to get pairwise interactions between variables", + ParamValidators.gt(0)) + + /** @group getParam */ + @Since("3.0.0") + final def getFactorSize: Int = $(factorSize) + + /** + * Param for whether to fit global bias term + * @group param + */ + @Since("3.0.0") + final val fitBias: BooleanParam = new BooleanParam(this, "fitBias", Review comment: How about calling this intercept and using HasIntercept? ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
