[SPARK-9720] [ML] Identifiable types need UID in toString methods

A few Identifiable types did override their toString method but without using the parent implementation. As a consequence, the uid was not present anymore in the toString result. It is the default behaviour.

This patch is a quick fix. The question of enforcement is still up.

No tests have been written to verify the toString method behaviour. That would be long to do because all types should be tested and not only those which have a regression now.

It is possible to enforce the condition using the compiler by making the toString method final but that would introduce unwanted potential API breaking changes (see jira).

Author: Bertrand Dechoux <BertrandDechoux@users.noreply.github.com>

Closes #8062 from BertrandDechoux/SPARK-9720.

8 files changed, 9 insertions, 9 deletions

diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala
index 0a75d5d222..b8eb49f9bd 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/DecisionTreeClassifier.scala
@@ -146,7 +146,7 @@ final class DecisionTreeClassificationModel private[ml] (
   }
 
   override def toString: String = {
-    s"DecisionTreeClassificationModel of depth $depth with $numNodes nodes"
+    s"DecisionTreeClassificationModel (uid=$uid) of depth $depth with $numNodes nodes"
   }
 
   /** (private[ml]) Convert to a model in the old API */
diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala
index 3073a2a61c..ad8683648b 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/GBTClassifier.scala
@@ -200,7 +200,7 @@ final class GBTClassificationModel(
   }
 
   override def toString: String = {
-    s"GBTClassificationModel with $numTrees trees"
+    s"GBTClassificationModel (uid=$uid) with $numTrees trees"
   }
 
   /** (private[ml]) Convert to a model in the old API */
diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala
index 69cb88a7e6..082ea1ffad 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/NaiveBayes.scala
@@ -198,7 +198,7 @@ class NaiveBayesModel private[ml] (
   }
 
   override def toString: String = {
-    s"NaiveBayesModel with ${pi.size} classes"
+    s"NaiveBayesModel (uid=$uid) with ${pi.size} classes"
   }
 
 }
diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala
index 11a6d72468..a6ebee1bb1 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/classification/RandomForestClassifier.scala
@@ -193,7 +193,7 @@ final class RandomForestClassificationModel private[ml] (
   }
 
   override def toString: String = {
-    s"RandomForestClassificationModel with $numTrees trees"
+    s"RandomForestClassificationModel (uid=$uid) with $numTrees trees"
   }
 
   /**
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala
index a7fa504442..dcd6fe3c40 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/RFormula.scala
@@ -129,7 +129,7 @@ class RFormula(override val uid: String) extends Estimator[RFormulaModel] with R
 
   override def copy(extra: ParamMap): RFormula = defaultCopy(extra)
 
-  override def toString: String = s"RFormula(${get(formula)})"
+  override def toString: String = s"RFormula(${get(formula)}) (uid=$uid)"
 }
 
 /**
@@ -171,7 +171,7 @@ class RFormulaModel private[feature](
   override def copy(extra: ParamMap): RFormulaModel = copyValues(
     new RFormulaModel(uid, resolvedFormula, pipelineModel))
 
-  override def toString: String = s"RFormulaModel(${resolvedFormula})"
+  override def toString: String = s"RFormulaModel(${resolvedFormula}) (uid=$uid)"
 
   private def transformLabel(dataset: DataFrame): DataFrame = {
     val labelName = resolvedFormula.label
diff --git a/mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala b/mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala
index a2bcd67401..d9a244bea2 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/regression/DecisionTreeRegressor.scala
@@ -118,7 +118,7 @@ final class DecisionTreeRegressionModel private[ml] (
   }
 
   override def toString: String = {
-    s"DecisionTreeRegressionModel of depth $depth with $numNodes nodes"
+    s"DecisionTreeRegressionModel (uid=$uid) of depth $depth with $numNodes nodes"
   }
 
   /** Convert to a model in the old API */
diff --git a/mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala b/mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala
index b66e61f37d..d841ecb9e5 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/regression/GBTRegressor.scala
@@ -189,7 +189,7 @@ final class GBTRegressionModel(
   }
 
   override def toString: String = {
-    s"GBTRegressionModel with $numTrees trees"
+    s"GBTRegressionModel (uid=$uid) with $numTrees trees"
   }
 
   /** (private[ml]) Convert to a model in the old API */
diff --git a/mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala b/mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala
index 2f36da371f..ddb7214416 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/regression/RandomForestRegressor.scala
@@ -155,7 +155,7 @@ final class RandomForestRegressionModel private[ml] (
   }
 
   override def toString: String = {
-    s"RandomForestRegressionModel with $numTrees trees"
+    s"RandomForestRegressionModel (uid=$uid) with $numTrees trees"
   }
 
   /**