[jvm-packages] Fix wrong method name setAllowZeroForMissingValue. (#5740)

* Allow non-zero for missing value when training.

* Fix wrong method names.

* Add a unit test

* Move the getter/setter unit test to MissingValueHandlingSuite

Co-authored-by: Hyunsu Cho <chohyu01@cs.washington.edu>

jvm-packages/xgboost4j-spark/src/main/scala/ml/dmlc/xgboost4j/scala/spark/XGBoostClassifier.scala

@@ -141,6 +141,11 @@ class XGBoostClassifier (
 
   def setCustomEval(value: EvalTrait): this.type = set(customEval, value)
 
+  def setAllowNonZeroForMissing(value: Boolean): this.type = set(
+    allowNonZeroForMissing,
+    value
+  )
+
   def setSinglePrecisionHistogram(value: Boolean): this.type =
     set(singlePrecisionHistogram, value)
 
@@ -248,7 +253,7 @@ class XGBoostClassificationModel private[ml](
 
   def setMissing(value: Float): this.type = set(missing, value)
 
-  def setAllowZeroForMissingValue(value: Boolean): this.type = set(
+  def setAllowNonZeroForMissing(value: Boolean): this.type = set(
     allowNonZeroForMissing,
     value
   )

jvm-packages/xgboost4j-spark/src/main/scala/ml/dmlc/xgboost4j/scala/spark/XGBoostRegressor.scala

@@ -145,6 +145,11 @@ class XGBoostRegressor (
 
   def setCustomEval(value: EvalTrait): this.type = set(customEval, value)
 
+  def setAllowNonZeroForMissing(value: Boolean): this.type = set(
+    allowNonZeroForMissing,
+    value
+  )
+
   def setSinglePrecisionHistogram(value: Boolean): this.type =
     set(singlePrecisionHistogram, value)
 
@@ -244,7 +249,7 @@ class XGBoostRegressionModel private[ml] (
 
   def setMissing(value: Float): this.type = set(missing, value)
 
-  def setAllowZeroForMissingValue(value: Boolean): this.type = set(
+  def setAllowNonZeroForMissing(value: Boolean): this.type = set(
     allowNonZeroForMissing,
     value
   )