Github user crackcell commented on a diff in the pull request: https://github.com/apache/spark/pull/17123#discussion_r103955065 --- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/Bucketizer.scala --- @@ -171,23 +176,23 @@ object Bucketizer extends DefaultParamsReadable[Bucketizer] { * Binary searching in several buckets to place each data point. * @param splits array of split points * @param feature data point - * @param keepInvalid NaN flag. - * Set "true" to make an extra bucket for NaN values; - * Set "false" to report an error for NaN values + * @param keepInvalid NaN/NULL flag. + * Set "true" to make an extra bucket for NaN/NULL values; + * Set "false" to report an error for NaN/NULL values * @return bucket for each data point * @throws SparkException if a feature is < splits.head or > splits.last */ private[feature] def binarySearchForBuckets( splits: Array[Double], - feature: Double, + feature: java.lang.Double, keepInvalid: Boolean): Double = { - if (feature.isNaN) { + if (feature == null || feature.isNaN) { if (keepInvalid) { splits.length - 1 } else { - throw new SparkException("Bucketizer encountered NaN value. To handle or skip NaNs," + - " try setting Bucketizer.handleInvalid.") + throw new SparkException("Bucketizer encountered NaN/NULL values. " + + "To handle or skip NaNs/NULLs, try setting Bucketizer.handleInvalid.") } } else if (feature == splits.last) { --- End diff -- My fault! I'll do it now!
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org