Skip to content

[SPARK-9312] [ML] Added max confidence factor to OneVsRestModel #7652

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 8 commits into from
Closed

[SPARK-9312] [ML] Added max confidence factor to OneVsRestModel #7652

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
f4e2089
Added predictive probability to OneVsRestModel and LogisticRegression…
badriub Jul 24, 2015
8bfd54c
SPARK-9312: Adding confidence factor to OneVsRest Model
badriub Jul 29, 2015
c4a3c29
SPARK-9312: Undoing changes for the LogisticRegression related to
badriub Jul 29, 2015
d758972
Correcting indentation
badriub Jul 29, 2015
095774f
Implementing review comments
badriub Jul 29, 2015
e3e858f
Merge branch 'master' of https://github.com/badriub/spark.git
badriub Aug 12, 2015
a18dab6
Import order corrected
badriub Aug 12, 2015
3950a5b
Missed fixing a doc earlier
badriub Aug 12, 2015
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
16 changes: 12 additions & 4 deletions mllib/src/main/scala/org/apache/spark/ml/classification/OneVsRest.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,18 +24,19 @@ import scala.language.existentials
import org.apache.spark.annotation.Experimental
import org.apache.spark.ml._
import org.apache.spark.ml.attribute._
import org.apache.spark.ml.param.shared.HasRawPredictionCol
import org.apache.spark.ml.param.{Param, ParamMap}
import org.apache.spark.ml.util.{Identifiable, MetadataUtils}
import org.apache.spark.mllib.linalg.Vector
import org.apache.spark.sql.{DataFrame, Row}
import org.apache.spark.sql.functions._
import org.apache.spark.sql.types._
import org.apache.spark.sql.{DataFrame, Row}
import org.apache.spark.storage.StorageLevel

/**
* Params for [[OneVsRest]].
*/
private[ml] trait OneVsRestParams extends PredictorParams {
private[ml] trait OneVsRestParams extends ClassifierParams {

// scalastyle:off structural.type
type ClassifierType = Classifier[F, E, M] forSome {
Expand Down Expand Up @@ -127,10 +128,16 @@ final class OneVsRestModel private[ml] (
predictions.maxBy(_._2)._1.toDouble
}

// output label and label metadata as prediction
// output the highest confidence as rawPredictionCol
val probabilityUDF = udf { (predictions: Map[Int, Double]) =>
Copy link
Member

@jkbradley jkbradley Jul 31, 2015

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is outputting a Double, but it should return a Vector with one value for each class label. Actually, the output value should be the accCol converted to a Vector.

Copy link
Author

@badriub badriub Aug 12, 2015

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sorry for the delayed response. I've made some small changes as per your recommendations. WRT this point, I'm not sure I follow. As far as I understand, I need to return the highest confidence factor(which will be Double) corresponding to the model used with OVR.

predictions.maxBy(_._2)._2.toDouble
}

// output label, confidence factor and label metadata as prediction
aggregatedDataset
.withColumn($(predictionCol), labelUDF(col(accColName)).as($(predictionCol), labelMetadata))
.drop(accColName)
.withColumn($(rawPredictionCol), probabilityUDF(col(accColName)).as($(rawPredictionCol),
labelMetadata)).drop(accColName)
}
Copy link
Author

@badriub badriub Jul 29, 2015

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Adding the max confidence factor as output column.


override def copy(extra: ParamMap): OneVsRestModel = {
Expand Down Expand Up @@ -220,4 +227,5 @@ final class OneVsRest(override val uid: String)
}
copied
}

}
3 changes: 2 additions & 1 deletion mllib/src/test/scala/org/apache/spark/ml/classification/OneVsRestSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,7 +110,8 @@ class OneVsRestSuite extends SparkFunSuite with MLlibTestSparkContext {
val ovr = new OneVsRest()
.setClassifier(logReg)
val output = ovr.fit(dataset).transform(dataset)
assert(output.schema.fieldNames.toSet === Set("label", "features", "prediction"))
assert(output.schema.fieldNames.toSet === Set("label", "features", "prediction",
"rawPrediction"))
}

test("OneVsRest.copy and OneVsRestModel.copy") {
Expand Down