Github user dbtsai commented on a diff in the pull request: https://github.com/apache/spark/pull/14834#discussion_r78101327 --- Diff: mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala --- @@ -311,8 +348,25 @@ class LogisticRegression @Since("1.2.0") ( val histogram = labelSummarizer.histogram val numInvalid = labelSummarizer.countInvalid - val numClasses = histogram.length val numFeatures = summarizer.mean.size + val numFeaturesPlusIntercept = if (getFitIntercept) numFeatures + 1 else numFeatures + + val numClasses = MetadataUtils.getNumClasses(dataset.schema($(labelCol))) match { + case Some(n: Int) => + require(n >= histogram.length, s"Specified number of classes $n was " + + s"less than the number of unique labels ${histogram.length}.") + n + case None => histogram.length + } + val isBinaryClassification = numClasses == 1 || numClasses == 2 + val isMultinomial = ($(family) == "auto" && !isBinaryClassification) || + ($(family) == "multinomial") + val numCoefficientSets = if (isMultinomial) numClasses else 1 + --- End diff -- maybe it's easier to read ```scala val (isBinomial, isMultinomial) = { $(family) match { case "binomial" => require(numClasses == 1 || numClasses == 2, s"Binomial family only supports 1 or 2 " + + s"outcome classes but found $numClasses.") (true, false) case "multinomial" => (false, true) case "auto": => .... case _: throw new IllegalArgExpcetion("Unsupported family") } } ```
--- 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