Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/15593#discussion_r87518789
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -1486,57 +1504,65 @@ private class LogisticAggregator(
var marginOfLabel = 0.0
var maxMargin = Double.NegativeInfinity
- val margins = Array.tabulate(numClasses) { i =>
- var margin = 0.0
- features.foreachActive { (index, value) =>
- if (localFeaturesStd(index) != 0.0 && value != 0.0) {
- margin += localCoefficients(i * numFeaturesPlusIntercept +
index) *
- value / localFeaturesStd(index)
- }
+ val margins = new Array[Double](numClasses)
+ features.foreachActive { (index, value) =>
+ val stdValue = value / localFeaturesStd(index)
+ var j = 0
+ while (j < numClasses) {
+ margins(j) += localCoefficients(index * numClasses + j) * stdValue
+ j += 1
}
-
+ }
+ var i = 0
+ while (i < numClasses) {
if (fitIntercept) {
- margin += localCoefficients(i * numFeaturesPlusIntercept +
numFeatures)
+ margins(i) += localCoefficients(numClasses * numFeatures + i)
}
- if (i == label.toInt) marginOfLabel = margin
- if (margin > maxMargin) {
- maxMargin = margin
+ if (i == label.toInt) marginOfLabel = margins(i)
+ if (margins(i) > maxMargin) {
+ maxMargin = margins(i)
}
- margin
+ i += 1
}
/**
* When maxMargin > 0, the original formula could cause overflow.
* We address this by subtracting maxMargin from all the margins, so
it's guaranteed
* that all of the new margins will be smaller than zero to prevent
arithmetic overflow.
*/
+ val multipliers = new Array[Double](numClasses)
val sum = {
var temp = 0.0
- if (maxMargin > 0) {
- for (i <- 0 until numClasses) {
- margins(i) -= maxMargin
- temp += math.exp(margins(i))
- }
- } else {
- for (i <- 0 until numClasses) {
- temp += math.exp(margins(i))
- }
+ var i = 0
+ while (i < numClasses) {
+ if (maxMargin > 0) margins(i) -= maxMargin
+ val exp = math.exp(margins(i))
+ temp += exp
+ multipliers(i) = exp
+ i += 1
}
temp
}
- for (i <- 0 until numClasses) {
- val multiplier = math.exp(margins(i)) / sum - {
- if (label == i) 1.0 else 0.0
- }
- features.foreachActive { (index, value) =>
- if (localFeaturesStd(index) != 0.0 && value != 0.0) {
- localGradientArray(i * numFeaturesPlusIntercept + index) +=
- weight * multiplier * value / localFeaturesStd(index)
+ margins.indices.foreach { i =>
+ multipliers(i) = multipliers(i) / sum - (if (label == i) 1.0 else
0.0)
+ }
+ features.foreachActive { (index, value) =>
+ if (localFeaturesStd(index) != 0.0 && value != 0.0) {
+ val stdValue = value / localFeaturesStd(index)
+ var j = 0
+ while (j < numClasses) {
+ localGradientArray(index * numClasses + j) +=
+ weight * multipliers(j) * stdValue
+ j += 1
}
}
- if (fitIntercept) {
- localGradientArray(i * numFeaturesPlusIntercept + numFeatures) +=
weight * multiplier
+ }
+ if (fitIntercept) {
+ var i = 0
+ while (i < numClasses) {
+ localGradientArray(numFeatures * numClasses + i) += weight *
multipliers(i)
+ i += 1
}
}
--- End diff --
You can make `def gradient: Vector` returning `Matrix`, and for MLOR, the
implementation can be col major matrix so when we use `foreachActive` we don't
need to worry about the underlying implementation.
---
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
