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

Skip writing empty stages & skip loading stages without uid-s #282

Merged
merged 2 commits into from
Apr 12, 2019
Merged

Skip writing empty stages & skip loading stages without uid-s #282

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1602869
As precation - skip stages without uid-s
tovbinm Apr 12, 2019
0ba2a49
write non empty stages
tovbinm Apr 12, 2019
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
19 changes: 10 additions & 9 deletions core/src/main/scala/com/salesforce/op/OpWorkflowModelReader.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,12 +30,11 @@

package com.salesforce.op

import com.salesforce.op.OpWorkflowModelReadWriteShared.FieldNames
import com.salesforce.op.OpWorkflowModelReadWriteShared.FieldNames._
import com.salesforce.op.features.{FeatureJsonHelper, OPFeature, TransientFeature}
import com.salesforce.op.filters.{FeatureDistribution, RawFeatureFilterResults}
import com.salesforce.op.stages.OpPipelineStageReadWriteShared._
import com.salesforce.op.stages.{OpPipelineStageReader, _}
import com.salesforce.op.stages._
import org.apache.spark.ml.util.MLReader
import org.json4s.JsonAST.{JArray, JNothing, JValue}
import org.json4s.jackson.JsonMethods.parse
Expand Down Expand Up @@ -133,14 +132,16 @@ class OpWorkflowModelReader(val workflowOpt: Option[OpWorkflow]) extends MLReade

private def loadStages(workflow: OpWorkflow, json: JValue, path: String): Seq[OPStage] = {
val stagesJs = (json \ Stages.entryName).extract[JArray].arr
val recoveredStages = stagesJs.map(j => {
val stageUid = (j \ FieldNames.Uid.entryName).extract[String]
val originalStage = workflow.stages.find(_.uid == stageUid)
originalStage match {
case Some(os) => new OpPipelineStageReader(os).loadFromJson(j, path = path).asInstanceOf[OPStage]
case None => throw new RuntimeException(s"Workflow does not contain a stage with uid: $stageUid")
val recoveredStages = stagesJs.flatMap { j =>
val stageUidOpt = (j \ Uid.entryName).extractOpt[String]
stageUidOpt.map { stageUid =>
val originalStage = workflow.stages.find(_.uid == stageUid)
originalStage match {
case Some(os) => new OpPipelineStageReader(os).loadFromJson(j, path = path).asInstanceOf[OPStage]
case None => throw new RuntimeException(s"Workflow does not contain a stage with uid: $stageUid")
}
}
})
}
val generators = workflow.rawFeatures.map(_.originStage)
generators ++ recoveredStages
}
Expand Down
4 changes: 3 additions & 1 deletion core/src/main/scala/com/salesforce/op/OpWorkflowModelWriter.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,7 +99,9 @@ class OpWorkflowModelWriter(val model: OpWorkflowModel) extends MLWriter {
*/
private def stagesJArray(path: String): JArray = {
val stages: Seq[OpPipelineStageBase] = model.stages
val stagesJson: Seq[JObject] = stages.map(_.write.asInstanceOf[OpPipelineStageWriter].writeToJson(path))
val stagesJson: Seq[JObject] = stages
.map(_.write.asInstanceOf[OpPipelineStageWriter].writeToJson(path))
.filter(_.children.nonEmpty)
JArray(stagesJson.toList)
}

Expand Down