[SPARK-7429] [ML] Params cleanups

Params.setDefault taking a set of ParamPairs should be annotated with varargs. I thought it would not work before, but it apparently does. CrossValidator.transform should call transformSchema since the underlying Model might be a PipelineModel CC: mengxr Author: Joseph K. Bradley <[email protected]> Closes apache#5960 from jkbradley/params-cleanups and squashes the following commits: 118b158 [Joseph K. Bradley] Params.setDefault taking a set of ParamPairs should be annotated with varargs. I thought it would not work before, but it apparently does. CrossValidator.transform should call transformSchema since the underlying Model might be a PipelineModel (cherry picked from commit 4f87e95) Signed-off-by: Xiangrui Meng <[email protected]>
jkbradley · May 7, 2015 · 91ce131 · 91ce131
1 parent a038c51
commit 91ce131
Show file tree

Hide file tree

Showing 3 changed files with 4 additions and 4 deletions.
diff --git a/mllib/src/main/scala/org/apache/spark/ml/param/params.scala b/mllib/src/main/scala/org/apache/spark/ml/param/params.scala
@@ -366,13 +366,11 @@ trait Params extends Identifiable with Serializable {
   /**
    * Sets default values for a list of params.
    *
-   * Note: Java developers should use the single-parameter [[setDefault()]].
-   *       Annotating this with varargs causes compilation failures.
-   *
    * @param paramPairs  a list of param pairs that specify params and their default values to set
    *                    respectively. Make sure that the params are initialized before this method
    *                    gets called.
    */
+  @varargs
   protected final def setDefault(paramPairs: ParamPair[_]*): this.type = {
     paramPairs.foreach { p =>
       setDefault(p.param.asInstanceOf[Param[Any]], p.value)

diff --git a/mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala b/mllib/src/main/scala/org/apache/spark/ml/tuning/CrossValidator.scala
@@ -105,7 +105,7 @@ class CrossValidator extends Estimator[CrossValidatorModel] with CrossValidatorP
 
   override def fit(dataset: DataFrame): CrossValidatorModel = {
     val schema = dataset.schema
-    transformSchema(dataset.schema, logging = true)
+    transformSchema(schema, logging = true)
     val sqlCtx = dataset.sqlContext
     val est = $(estimator)
     val eval = $(evaluator)
@@ -159,6 +159,7 @@ class CrossValidatorModel private[ml] (
   }
 
   override def transform(dataset: DataFrame): DataFrame = {
+    transformSchema(dataset.schema, logging = true)
     bestModel.transform(dataset)
   }
 

diff --git a/mllib/src/test/java/org/apache/spark/ml/param/JavaTestParams.java b/mllib/src/test/java/org/apache/spark/ml/param/JavaTestParams.java
@@ -59,5 +59,6 @@ public JavaTestParams() {
       ParamValidators.inArray(validStrings));
     setDefault(myIntParam, 1);
     setDefault(myDoubleParam, 0.5);
+    setDefault(myIntParam.w(1), myDoubleParam.w(0.5));
   }
 }