Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/597#discussion_r12334839
--- Diff:
examples/src/main/scala/org/apache/spark/examples/mllib/MovieLensALS.scala ---
@@ -121,11 +135,17 @@ object MovieLensALS {
}
/** Compute RMSE (Root Mean Squared Error). */
- def computeRmse(model: MatrixFactorizationModel, data: RDD[Rating], n:
Long) = {
+ def computeRmse(model: MatrixFactorizationModel, data: RDD[Rating],
params: Params) = {
val predictions: RDD[Rating] = model.predict(data.map(x => (x.user,
x.product)))
- val predictionsAndRatings = predictions.map(x => ((x.user, x.product),
x.rating))
- .join(data.map(x => ((x.user, x.product), x.rating)))
- .values
- math.sqrt(predictionsAndRatings.map(x => (x._1 - x._2) * (x._1 -
x._2)).reduce(_ + _) / n)
+ val predictionsAndRatings = if (params.implicitPrefs) {
+ predictions.map(x => (
+ (x.user, x.product),
+ if (x.rating > 1.0) 1.0 else if (x.rating < 0.0) 0.0 else x.rating
+ )).join(data.map(x => ((x.user, x.product), x.rating)))
--- End diff --
Put `join` after `if ... else ...` because both branches use the same join.
---
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.
---
