Improve error message when number of examples is less than arity of h…

…igh-arity categorical feature
apache · Jul 30, 2015 · b8f6cdb · b8f6cdb
1 parent ed3cb1d
commit b8f6cdb
Showing 1 changed file with 6 additions and 2 deletions.
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/tree/impl/DecisionTreeMetadata.scala b/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]()