[SPARK-10470] [ML] ml.IsotonicRegressionModel.copy should set parent

Copied model must have the same parent, but ml.IsotonicRegressionModel.copy did not set parent.
Here fix it and add test case.

Author: Yanbo Liang <ybliang8@gmail.com>

Closes #8637 from yanboliang/spark-10470.

mllib/src/main/scala/org/apache/spark/ml/regression/IsotonicRegression.scala

@@ -203,7 +203,7 @@ class IsotonicRegressionModel private[ml] (
   def predictions: Vector = Vectors.dense(oldModel.predictions)
 
   override def copy(extra: ParamMap): IsotonicRegressionModel = {
-    copyValues(new IsotonicRegressionModel(uid, oldModel), extra)
+    copyValues(new IsotonicRegressionModel(uid, oldModel), extra).setParent(parent)
   }
 
   override def transform(dataset: DataFrame): DataFrame = {

mllib/src/test/scala/org/apache/spark/ml/regression/IsotonicRegressionSuite.scala

@@ -19,6 +19,7 @@ package org.apache.spark.ml.regression
 
 import org.apache.spark.SparkFunSuite
 import org.apache.spark.ml.param.ParamsSuite
+import org.apache.spark.ml.util.MLTestingUtils
 import org.apache.spark.mllib.linalg.Vectors
 import org.apache.spark.mllib.util.MLlibTestSparkContext
 import org.apache.spark.sql.{DataFrame, Row}
@@ -89,6 +90,10 @@ class IsotonicRegressionSuite extends SparkFunSuite with MLlibTestSparkContext {
     assert(ir.getFeatureIndex === 0)
 
     val model = ir.fit(dataset)
+
+    // copied model must have the same parent.
+    MLTestingUtils.checkCopy(model)
+
     model.transform(dataset)
       .select("label", "features", "prediction", "weight")
       .collect()