Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/245#discussion_r11014277
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/optimization/Gradient.scala ---
@@ -57,7 +68,22 @@ class LogisticGradient extends Gradient {
math.log(1 + math.exp(margin)) - margin
}
- (gradient, loss)
+ (Vectors.fromBreeze(gradient), loss)
+ }
+
+ override def compute(data: Vector, label: Double, weights: Vector,
gradientAddTo: Vector): Double = {
+ val brzData = data.toBreeze
+ val brzWeights = weights.toBreeze
+ val margin: Double = -1.0 * brzWeights.dot(brzData)
+ val gradientMultiplier = (1.0 / (1.0 + math.exp(margin))) - label
+
+ brzAxpy(gradientMultiplier, brzData, gradientAddTo.toBreeze)
--- End diff --
breeze uses implicits a lot. Scala do not look for second degree implicit
conversions.
---
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.
---
