Github user hhbyyh commented on a diff in the pull request:
https://github.com/apache/spark/pull/19020#discussion_r147323528
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala ---
@@ -69,25 +70,103 @@ private[regression] trait LinearRegressionParams
extends PredictorParams
"The solver algorithm for optimization. Supported options: " +
s"${supportedSolvers.mkString(", ")}. (Default auto)",
ParamValidators.inArray[String](supportedSolvers))
+
+ /**
+ * The loss function to be optimized.
+ * Supported options: "squaredError" and "huber".
+ * Default: "squaredError"
+ *
+ * @group param
+ */
+ @Since("2.3.0")
+ final override val loss: Param[String] = new Param[String](this, "loss",
"The loss function to" +
+ s" be optimized. Supported options: ${supportedLosses.mkString(", ")}.
(Default squaredError)",
+ ParamValidators.inArray[String](supportedLosses))
+
+ /**
+ * The shape parameter to control the amount of robustness. Must be >
1.0.
+ * At larger values of epsilon, the huber criterion becomes more similar
to least squares
+ * regression; for small values of epsilon, the criterion is more
similar to L1 regression.
+ * Default is 1.35 to get as much robustness as possible while retaining
+ * 95% statistical efficiency for normally distributed data.
+ * Only valid when "loss" is "huber".
+ *
+ * @group expertParam
+ */
+ @Since("2.3.0")
+ final val epsilon = new DoubleParam(this, "epsilon", "The shape
parameter to control the " +
+ "amount of robustness. Must be > 1.0.", ParamValidators.gt(1.0))
+
+ /** @group getExpertParam */
+ @Since("2.3.0")
+ def getEpsilon: Double = $(epsilon)
+
+ override protected def validateAndTransformSchema(
+ schema: StructType,
+ fitting: Boolean,
+ featuresDataType: DataType): StructType = {
+ if ($(loss) == Huber) {
--- End diff --
minor: && fitting == true?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
