Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/8564#discussion_r39679838
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/regression/LinearRegression.scala ---
@@ -298,11 +298,7 @@ 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)))
-
- new LinearRegressionSummary(predictionAndObservations,
$(predictionCol), $(labelCol))
+ new LinearRegressionSummary(transform(dataset), $(predictionCol),
$(labelCol))
--- End diff --
I had recommended switching to transform, but I just realized that a user
could potentially disable the output columns we need. In that case, I'm really
not sure what we should do. I guess I'd say:
* Easy option: Check to make sure predictionCol is defined and not the
empty string, and throw an exception if not.
* Nicer option: If predictionCol is disabled (empty string), then generate
a column name like "prediction_[randomNumber]", copy the model with this new
predictionCol set, and use it for the summary.
Either is OK with me, but it'd be cool if you have time to do the nicer
option. : )
---
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]
