Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/8564#discussion_r41465812
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala ---
@@ -316,13 +322,27 @@ class LinearRegressionModel private[ml] (
*/
// TODO: decide on a good name before exposing to public API
private[regression] def evaluate(dataset: DataFrame):
LinearRegressionSummary = {
- val t = udf { features: Vector => predict(features) }
- val predictionAndObservations = dataset
- .select(col($(labelCol)),
t(col($(featuresCol))).as($(predictionCol)))
+ // Handle possible missing or invalid prediction columns
+ val (summaryModel, predictionColName) =
findSummaryModelAndPredictionCol()
+ new LinearRegressionSummary(summaryModel.transform(dataset),
predictionColName, $(labelCol))
+ }
- new LinearRegressionSummary(predictionAndObservations,
$(predictionCol), $(labelCol))
+ /**
+ * If the prediction column is set returns the current model and
prediction column,
+ * otherwise generates a new column and sets it as the prediction column
on a new copy
+ * of the current model.
+ */
+ private[regression] def findSummaryModelAndPredictionCol():
(LinearRegressionModel, String) = {
+ $(predictionCol) match {
+ case "" => {
--- End diff --
style: remove unnecessary braces
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
