SparkMethods

Value Members

1. final def !=(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

2. final def ##(): Int

   

   Definition Classes

   AnyRef → Any

3. final def ==(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

4. def aggregateTotal(aggregateRegion: Dataset[Region], variants: Dataset[Variant])(implicit sparkSession: SparkSession): Dataset[GeneCounts]

   

   Aggregate on genes (or other features inside the bed file)

5. def allCombination(variants: Dataset[Variant], broadcasts: Broadcast[Broadcasts], regions: Dataset[IndexedRegions], outputDir: File)(implicit sparkSession: SparkSession): List[Future[Unit]]

   

6. final def asInstanceOf[T0]: T0

   

   Definition Classes

   Any

7. def checkExistsOutput(outputDir: File): Unit

   

8. def clone(): AnyRef

   

   Attributes

   protected[java.lang]

   Definition Classes

   AnyRef

   Annotations

   @throws( ... )

9. def createAggregateFamilies(aggregateRegion: Dataset[Region], variants: Dataset[Variant], broadcasts: Broadcast[Broadcasts])(implicit sparkSession: SparkSession): Dataset[GeneFamilyCounts]

   

   Aggregate on families and genes (or other features inside the bed file)

10. def createAggregateRegions(aggregationFile: Option[File], dict: SAMSequenceDictionary)(implicit sparkSession: SparkSession): Option[Dataset[Region]]

    

    Create aggregate regions as dataset if this is given on the commandline

11. def createCombinations(regionsRdd: Dataset[IndexedRegions], broadcasts: Broadcast[Broadcasts])(implicit sparkSession: SparkSession): Dataset[Combination]

    

    This created a list of combinations rdds

12. def createVariantCombinations(variants: Dataset[Variant], regionsRdd: Dataset[IndexedRegions], broadcasts: Broadcast[Broadcasts])(implicit sparkSession: SparkSession): Dataset[VariantCombination]

    

    Created all posible combinations of variants

13. def distanceFilter(v1: Variant, v2: Variant, maxDistance: Option[Long]): Boolean

    

    This returns false is the variants are to far a way

14. def distanceFilter(list1: List[Region], list2: List[Region], maxDistance: Option[Long]): Boolean

    

    This filters region combinations when maxDistance is set

15. final def eq(arg0: AnyRef): Boolean

    

    Definition Classes

    AnyRef

16. def equals(arg0: Any): Boolean

    

    Definition Classes

    AnyRef → Any

17. def familyAggregation(variants: Dataset[Variant], broadcasts: Broadcast[Broadcasts], aggregateRegions: Option[Dataset[Region]], outputDir: File)(implicit sparkSession: SparkSession): Option[Future[Unit]]

    

18. def familyCombinations(variants: Dataset[Variant], broadcasts: Broadcast[Broadcasts], familyId: Int, regions: Dataset[IndexedRegions], outputDir: File)(implicit sparkSession: SparkSession): Future[Unit]

    

19. def filterAllVariantCombinations(combinations: Dataset[VariantCombination], broadcasts: Broadcast[Broadcasts])(implicit sparkSession: SparkSession): Dataset[VariantCombination]

    

    Filter combinations

20. def finalize(): Unit

    

    Attributes

    protected[java.lang]

    Definition Classes

    AnyRef

    Annotations

    @throws( classOf[java.lang.Throwable] )

21. def generateRegions(cmdArgs: Args, dict: SAMSequenceDictionary): List[List[Region]]

    

    creates regions to analyse

22. final def getClass(): Class[_]

    

    Definition Classes

    AnyRef → Any

23. def hashCode(): Int

    

    Definition Classes

    AnyRef → Any

24. final def isInstanceOf[T0]: Boolean

    

    Definition Classes

    Any

25. def logger: Logger

    

    Definition Classes

    Logging

26. def main(cmdArgs: Args): Unit

    

27. final def ne(arg0: AnyRef): Boolean

    

    Definition Classes

    AnyRef

28. final def notify(): Unit

    

    Definition Classes

    AnyRef

29. final def notifyAll(): Unit

    

    Definition Classes

    AnyRef

30. def outputAggregation(outputDir: File): File

    

31. def outputFamilyGenes(outputDir: File): File

    

32. def outputFamilyPairs(outputDir: File, familyName: String): File

    

33. def outputPairs(outputDir: File): File

    

34. def outputVariants(outputDir: File): File

    

35. def pairedAnnotationFilter(combination: VariantCombination, pairFilters: List[AnnotationFilter]): Boolean

    

    This filters if 1 of the 2 variants returns true

36. def regionsDataset(broadcasts: Broadcast[Broadcasts])(implicit sparkSession: SparkSession): Dataset[IndexedRegions]

    

    Create regions as dataset

37. def singleAnnotationFilter(v: Variant, broadcasts: Broadcasts): Boolean

    

    This filters by looking only at a single variants, this reduces the number of combinations, this step is only there to improve performance

38. final def synchronized[T0](arg0: ⇒ T0): T0

    

    Definition Classes

    AnyRef

39. def toString(): String

    

    Definition Classes

    AnyRef → Any

40. def variantsDataSet(regionsRdd: Dataset[IndexedRegions], broadcasts: Broadcast[Broadcasts])(implicit sparkSession: SparkSession): Dataset[Variant]

    

    This reads all regions and makes a Variant dataset

41. final def wait(): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

42. final def wait(arg0: Long, arg1: Int): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

43. final def wait(arg0: Long): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

44. def writeStatsFile(outputDir: File, singleFilterTotal: Long, totalPairs: Long): Unit

    

    Writing a stats file