Skip to content
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

Jump to bottom

Check array length + clues + fix fill geo location vectorizer values #132

Merged
merged 3 commits into from
Sep 13, 2018
Merged

Check array length + clues + fix fill geo location vectorizer values #132

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
948f641
Check array length + clues
tovbinm Sep 13, 2018
94b6d6d
fill in missing geo location values
tovbinm Sep 13, 2018
cb7af90
Merge branch 'master' into mt/better-asserts
tovbinm Sep 13, 2018
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
5 changes: 4 additions & 1 deletion core/src/main/scala/com/salesforce/op/stages/impl/feature/GeolocationVectorizer.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,7 +139,10 @@ final class GeolocationVectorizerModel private[op]
def transformFn: Seq[Geolocation] => OPVector = row => {
val replaced =
if (!trackNulls) {
row.zip(fillValues).flatMap { case (r, m) => if (r.isEmpty) m else r.value }
row.zip(fillValues).flatMap { case (r, m) =>
val meanToUse: Seq[Double] = if (m.isEmpty) RepresentationOfEmpty else m
if (r.isEmpty) meanToUse else r.value
}
}
else {
row.zip(fillValues).flatMap { case (r, m) =>
Expand Down
18 changes: 13 additions & 5 deletions core/src/test/scala/com/salesforce/op/stages/impl/feature/AttributeAsserts.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,19 +37,27 @@ import org.scalatest.{Assertion, Matchers}

trait AttributeAsserts {
self: Matchers =>

/**
* Assert if attributes are nominal or not
*
* @param schema
* @param schema field schema with attributes attached
* @param expectedNominal Expected array of booleans. True if the field is nominal, false if not.
* @param output the output OPVector associated with the column
*/
final def assertNominal(schema: StructField, expectedNominal: Array[Boolean], output: Array[OPVector]): Assertion = {
val attributes = AttributeGroup.fromStructField(schema).attributes
for {
x <- output
(x, i) <- output.zipWithIndex
_ = withClue(s"Output vector $i and expectedNominal arrays are not of the same length:") {
x.value.size shouldBe expectedNominal.length
}
(value, nominal) <- x.value.toArray.zip(expectedNominal)
} if (nominal) value should (be (0.0) or be (1.0))
attributes.map(_.map(_.isNominal).toSeq) shouldBe Some(expectedNominal.toSeq)
} if (nominal) value should (be(0.0) or be(1.0))

val attributes = AttributeGroup.fromStructField(schema).attributes
withClue("Field attributes were not set or not as expected:") {
attributes.map(_.map(_.isNominal).toSeq) shouldBe Some(expectedNominal.toSeq)
}
}

}
6 changes: 3 additions & 3 deletions features/src/main/scala/com/salesforce/op/aggregators/Geolocation.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,9 +78,9 @@ case object GeolocationMidpoint

trait GeolocationFunctions {

val Zero: Array[Double] = Array.fill[Double](4)(0.0)
val Zero: Array[Double] = new Array[Double](4)

def isNone(data: Array[Double]): Boolean = data(3) == 0
def isNone(data: Array[Double]): Boolean = data(3) == 0.0

/**
* Prepare method to be used in the MonoidAggregator for Geolocation objects
Expand All @@ -93,7 +93,7 @@ trait GeolocationFunctions {
if (input.isEmpty) Zero
else {
val g = input.toGeoPoint
val d = input.accuracy.rangeInUnits / 2
val d = input.accuracy.rangeInUnits / 2.0
Array[Double](
g.x, g.y, g.z,
1.0,
Expand Down
4 changes: 2 additions & 2 deletions features/src/main/scala/com/salesforce/op/features/types/Geolocation.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -97,8 +97,8 @@ object Geolocation {
private[types] def geolocationData(
lat: Double,
lon: Double,
accuracy: GeolocationAccuracy): Seq[Double] =
geolocationData(lat, lon, accuracy.value)
accuracy: GeolocationAccuracy
): Seq[Double] = geolocationData(lat, lon, accuracy.value)

private[types] def geolocationData(
lat: Double,
Expand Down