Skip to content

[Spark-7983] [MLlib] Add require for one-based indices in loadLibSVMFile #6538

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 7 commits into from
Closed

[Spark-7983] [MLlib] Add require for one-based indices in loadLibSVMFile #6538

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
5bd1f9a
add require for one-based in loadLIBSVM
hhbyyh May 31, 2015
9956365
add ut for 0-based loadlibsvm exception
hhbyyh May 31, 2015
6e4f8ca
add check for ascending order
hhbyyh Jun 1, 2015
20a2811
use require
hhbyyh Jun 2, 2015
96460f1
merge conflict
hhbyyh Jun 3, 2015
4310710
merge conflict
hhbyyh Jun 3, 2015
79d9c11
optimization as respond to comments
hhbyyh Jun 3, 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
12 changes: 12 additions & 0 deletions mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,6 +82,18 @@ object MLUtils {
val value = indexAndValue(1).toDouble
(index, value)
}.unzip

// check if indices are one-based and in ascending order
var previous = -1
var i = 0
val indicesLength = indices.length
while (i < indicesLength) {
val current = indices(i)
require(current > previous, "indices should be one-based and in ascending order" )
previous = current
i += 1
}

(label, indices.toArray, values.toArray)
}

Expand Down
35 changes: 35 additions & 0 deletions mllib/src/test/scala/org/apache/spark/mllib/util/MLUtilsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@ import breeze.linalg.{squaredDistance => breezeSquaredDistance}
import com.google.common.base.Charsets
import com.google.common.io.Files

import org.apache.spark.SparkException
import org.apache.spark.SparkFunSuite
import org.apache.spark.mllib.linalg.{DenseVector, SparseVector, Vectors}
import org.apache.spark.mllib.regression.LabeledPoint
Expand Down Expand Up @@ -108,6 +109,40 @@ class MLUtilsSuite extends SparkFunSuite with MLlibTestSparkContext {
Utils.deleteRecursively(tempDir)
}

test("loadLibSVMFile throws IllegalArgumentException when indices is zero-based") {
val lines =
"""
|0
|0 0:4.0 4:5.0 6:6.0
""".stripMargin
val tempDir = Utils.createTempDir()
val file = new File(tempDir.getPath, "part-00000")
Files.write(lines, file, Charsets.US_ASCII)
val path = tempDir.toURI.toString

intercept[SparkException] {
loadLibSVMFile(sc, path).collect()
}
Utils.deleteRecursively(tempDir)
}

test("loadLibSVMFile throws IllegalArgumentException when indices is not in ascending order") {
val lines =
"""
|0
|0 3:4.0 2:5.0 6:6.0
""".stripMargin
val tempDir = Utils.createTempDir()
val file = new File(tempDir.getPath, "part-00000")
Files.write(lines, file, Charsets.US_ASCII)
val path = tempDir.toURI.toString

intercept[SparkException] {
loadLibSVMFile(sc, path).collect()
}
Utils.deleteRecursively(tempDir)
}

test("saveAsLibSVMFile") {
val examples = sc.parallelize(Seq(
LabeledPoint(1.1, Vectors.sparse(3, Seq((0, 1.23), (2, 4.56)))),
Expand Down