Skip to content

[SPARK-2477][MLlib] Using appendBias for adding intercept in GeneralizedLinearAlgorithm #1410

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

[SPARK-2477][MLlib] Using appendBias for adding intercept in GeneralizedLinearAlgorithm #1410

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 5 additions & 16 deletions mllib/src/main/scala/org/apache/spark/mllib/regression/GeneralizedLinearAlgorithm.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,13 +17,12 @@

package org.apache.spark.mllib.regression

import breeze.linalg.{DenseVector => BDV, SparseVector => BSV}

import org.apache.spark.annotation.DeveloperApi
import org.apache.spark.{Logging, SparkException}
import org.apache.spark.rdd.RDD
import org.apache.spark.mllib.optimization._
import org.apache.spark.mllib.linalg.{Vectors, Vector}
import org.apache.spark.mllib.util.MLUtils._

/**
* :: DeveloperApi ::
Expand Down Expand Up @@ -124,16 +123,6 @@ abstract class GeneralizedLinearAlgorithm[M <: GeneralizedLinearModel]
run(input, initialWeights)
}

/** Prepends one to the input vector. */
private def prependOne(vector: Vector): Vector = {
val vector1 = vector.toBreeze match {
case dv: BDV[Double] => BDV.vertcat(BDV.ones[Double](1), dv)
case sv: BSV[Double] => BSV.vertcat(new BSV[Double](Array(0), Array(1.0), 1), sv)
case v: Any => throw new IllegalArgumentException("Do not support vector type " + v.getClass)
}
Vectors.fromBreeze(vector1)
}

/**
* Run the algorithm with the configured parameters on an input RDD
* of LabeledPoint entries starting from the initial weights provided.
Expand All @@ -147,23 +136,23 @@ abstract class GeneralizedLinearAlgorithm[M <: GeneralizedLinearModel]

// Prepend an extra variable consisting of all 1.0's for the intercept.
val data = if (addIntercept) {
input.map(labeledPoint => (labeledPoint.label, prependOne(labeledPoint.features)))
input.map(labeledPoint => (labeledPoint.label, appendBias(labeledPoint.features)))
} else {
input.map(labeledPoint => (labeledPoint.label, labeledPoint.features))
}

val initialWeightsWithIntercept = if (addIntercept) {
prependOne(initialWeights)
appendBias(initialWeights)
} else {
initialWeights
}

val weightsWithIntercept = optimizer.optimize(data, initialWeightsWithIntercept)

val intercept = if (addIntercept) weightsWithIntercept(0) else 0.0
val intercept = if (addIntercept) weightsWithIntercept(weightsWithIntercept.size - 1) else 0.0
val weights =
if (addIntercept) {
Vectors.dense(weightsWithIntercept.toArray.slice(1, weightsWithIntercept.size))
Vectors.dense(weightsWithIntercept.toArray.slice(0, weightsWithIntercept.size - 1))
} else {
weightsWithIntercept
}
Expand Down