[SPARK-9077] [MLLIB] Improve error message for decision trees when nu…

…mExamples < maxCategoriesPerFeature

Improve error message when number of examples is less than arity of high-arity categorical feature

CC jkbradley is this about what you had in mind? I know it's a starter, but was on my list to close out in the short term.

Author: Sean Owen <sowen@cloudera.com>

Closes apache#7800 from srowen/SPARK-9077 and squashes the following commits:

b8f6cdb [Sean Owen] Improve error message when number of examples is less than arity of high-arity categorical feature

mllib/src/main/scala/org/apache/spark/mllib/tree/impl/DecisionTreeMetadata.scala

@@ -128,9 +128,13 @@ private[spark] object DecisionTreeMetadata extends Logging {
     // based on the number of training examples.
     if (strategy.categoricalFeaturesInfo.nonEmpty) {
       val maxCategoriesPerFeature = strategy.categoricalFeaturesInfo.values.max
+      val maxCategory =
+        strategy.categoricalFeaturesInfo.find(_._2 == maxCategoriesPerFeature).get._1
       require(maxCategoriesPerFeature <= maxPossibleBins,
-        s"DecisionTree requires maxBins (= $maxPossibleBins) >= max categories " +
-          s"in categorical features (= $maxCategoriesPerFeature)")
+        s"DecisionTree requires maxBins (= $maxPossibleBins) to be at least as large as the " +
+        s"number of values in each categorical feature, but categorical feature $maxCategory " +
+        s"has $maxCategoriesPerFeature values. Considering remove this and other categorical " +
+        "features with a large number of values, or add more training examples.")
     }
 
     val unorderedFeatures = new mutable.HashSet[Int]()