[SPARK-17141][ML] MinMaxScaler should remain NaN value.

## What changes were proposed in this pull request?
In the existing code, ```MinMaxScaler``` handle ```NaN``` value indeterminately.
* If a column has identity value, that is ```max == min```, ```MinMaxScalerModel``` transformation will output ```0.5``` for all rows even the original value is ```NaN```.
* Otherwise, it will remain ```NaN``` after transformation.

I think we should unify the behavior by remaining ```NaN``` value at any condition, since we don't know how to transform a ```NaN``` value. In Python sklearn, it will throw exception when there is ```NaN``` in the dataset.

## How was this patch tested?
Unit tests.

Author: Yanbo Liang <ybliang8@gmail.com>

Closes #14716 from yanboliang/spark-17141.

1 files changed, 4 insertions, 2 deletions

diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala
index 9f3d2ca6db..28cbe1cb01 100644
--- a/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala
+++ b/mllib/src/main/scala/org/apache/spark/ml/feature/MinMaxScaler.scala
@@ -186,8 +186,10 @@ class MinMaxScalerModel private[ml] (
       val size = values.length
       var i = 0
       while (i < size) {
-        val raw = if (originalRange(i) != 0) (values(i) - minArray(i)) / originalRange(i) else 0.5
-        values(i) = raw * scale + $(min)
+        if (!values(i).isNaN) {
+          val raw = if (originalRange(i) != 0) (values(i) - minArray(i)) / originalRange(i) else 0.5
+          values(i) = raw * scale + $(min)
+        }
         i += 1
       }
       Vectors.dense(values)