[GitHub] [spark] zhengruifeng commented on a change in pull request #26124: [SPARK-29224][ML]Implement Factorization Machines as a ml-pipeline component

[GitBox <gi...@apache.org>]

zhengruifeng 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_r337443915
 
 

 ##########
 File path: mllib/src/main/scala/org/apache/spark/ml/regression/FactorizationMachines.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.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, Updater}
+import org.apache.spark.mllib.regression.{LabeledPoint => OldLabeledPoint}
+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[regression] trait FactorizationMachinesParams
+  extends PredictorParams
+  with HasMaxIter with HasStepSize with HasTol with HasSolver with HasLoss {
+
+  import FactorizationMachines._
+
+  /**
+   * Param for dimensionality of the factors (>= 0)
+   * @group param
+   */
+  @Since("3.0.0")
+  final val numFactors: IntParam = new IntParam(this, "numFactors",
+    "dimensionality of the factorization")
+
+  /** @group getParam */
+  @Since("3.0.0")
+  final def getNumFactors: Int = $(numFactors)
+
+  /**
+   * Param for whether to fit global bias term
+   * @group param
+   */
+  @Since("3.0.0")
+  final val fitBias: BooleanParam = new BooleanParam(this, "fitBias",
+    "whether to fit global bias term")
+
+  /** @group getParam */
+  @Since("3.0.0")
+  final def getFitBias: Boolean = $(fitBias)
+
+  /**
+   * Param for whether to fit linear term (aka 1-way term)
+   * @group param
+   */
+  @Since("3.0.0")
+  final val fitLinear: BooleanParam = new BooleanParam(this, "fitLinear",
+    "whether to fit linear term (aka 1-way term)")
+
+  /** @group getParam */
+  @Since("3.0.0")
+  final def getFitLinear: Boolean = $(fitLinear)
+
+  /**
+   * Param for L2 regularization parameter (>= 0)
+   * @group param
+   */
+  @Since("3.0.0")
+  final val regParam: DoubleParam = new DoubleParam(this, "regParam",
+    "regularization for L2")
+
+  /** @group getParam */
+  @Since("3.0.0")
+  final def getRegParam: Double = $(regParam)
+
+  /**
+   * Param for mini-batch fraction, must be in range (0, 1]
+   * @group param
+   */
+  @Since("3.0.0")
+  final val miniBatchFraction: DoubleParam = new DoubleParam(this, "miniBatchFraction",
+    "mini-batch fraction")
+
+  /** @group getParam */
+  @Since("3.0.0")
+  final def getMiniBatchFraction: Double = $(miniBatchFraction)
+
+  /**
+   * Param for standard deviation of initial coefficients
+   * @group param
+   */
+  @Since("3.0.0")
+  final val initStd: DoubleParam = new DoubleParam(this, "initStd",
+    "standard deviation of initial coefficients")
+
+  /** @group getParam */
+  @Since("3.0.0")
+  final def getInitStd: Double = $(initStd)
+
+  /**
+   * The solver algorithm for optimization.
+   * Supported options: "gd", "adamW".
+   * Default: "adamW"
+   *
+   * @group param
+   */
+  @Since("3.0.0")
+  final override val solver: Param[String] = new Param[String](this, "solver",
+    "The solver algorithm for optimization. Supported options: " +
+      s"${supportedSolvers.mkString(", ")}. (Default adamW)",
+    ParamValidators.inArray[String](supportedSolvers))
+
+  /**
+   * The loss function to be optimized.
+   * Supported options: "logisticLoss" and "squaredError".
+   * Default: "logisticLoss"
+   *
+   * @group param
+   */
+  @Since("3.0.0")
+  final override val loss: Param[String] = new Param[String](this, "loss", "The loss function to" +
+    s" be optimized. Supported options: ${supportedLosses.mkString(", ")}. (Default logisticLoss)",
+    ParamValidators.inArray[String](supportedLosses))
 
 Review comment:
   for a log-loss, should we put it into `ml.classification`? 

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org