Class

net.sansa_stack.ml.spark.clustering.utils

DataProcessing

Related Doc: package utils

Permalink

class DataProcessing extends Serializable

load TomTom dataset

Linear Supertypes
Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. DataProcessing
  2. Serializable
  3. Serializable
  4. AnyRef
  5. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new DataProcessing(spark: SparkSession, conf: Config)

    Permalink

    spark

    SparkSession

    conf

    Configuration

Value Members

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

    Permalink
    Definition Classes
    AnyRef → Any

  2. final def ##(): Int

    Permalink
    Definition Classes
    AnyRef → Any

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

    Permalink
    Definition Classes
    AnyRef → Any

  4. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any

  5. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  6. val conf: Config

    Permalink

    Configuration

  7. val dataRDD: RDD[Triple]

    Permalink

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

    Permalink
    Definition Classes
    AnyRef

  9. def equals(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  10. def filterCoordinates(poiCoordinates: RDD[(Long, CoordinatePOI)], lo_min: Double, lo_max: Double, la_min: Double, la_max: Double): RDD[(Long, CoordinatePOI)]

    Permalink

    poiCoordinates

    super set of poi with coordinates

    lo_min

    min longitude

    lo_max

    max longitude

    la_min

    min latitude

    la_max

    max latitude

    returns

    pois within certain coordinates

  11. def finalize(): Unit

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )

  12. def getCategoryId(poiCoordinates: RDD[(Long, CoordinatePOI)], poiFlatCategoryId: RDD[(Long, Long)]): RDD[(Long, Set[Long])]

    Permalink

    get (poi_unique, poi_category_id_set)

    get (poi_unique, poi_category_id_set)

    poiCoordinates

    (poi_unique, Coordinate)

    poiFlatCategoryId

    (poi, category_id)

  13. def getCategoryValues: RDD[(Long, Categories)]

    Permalink

    get (category_id, Categories)

    get (category_id, Categories)

    returns

    RDD with category values for category id

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

    Permalink
    Definition Classes
    AnyRef → Any

  15. def getPOICategories(poiCoordinates: RDD[(Long, CoordinatePOI)], poiFlatCategoryId: RDD[(Long, Long)], poiCategoryValueSet: RDD[(Long, Categories)]): RDD[(Long, Categories)]

    Permalink

    get (poi_unique, Categories)

    get (poi_unique, Categories)

    poiCoordinates

    (poi_unique, Coordinate)

    poiFlatCategoryId

    (poi, category_id)

    poiCategoryValueSet

    (category_id, Categories)

    returns

    (poi, Categories)

  16. def getPOICoordinates(lo_min: Double, lo_max: Double, la_min: Double, la_max: Double): RDD[(Long, CoordinatePOI)]

    Permalink

    load data filter on geo-coordinates

    load data filter on geo-coordinates

    lo_min

    min longitude

    lo_max

    max longitude

    la_min

    min latitude

    la_max

    max latitude

  17. def getPOICoordinates: RDD[(Long, CoordinatePOI)]

    Permalink

    get coordinate for all poi

  18. def getPOIFlatCategoryId: RDD[(Long, Long)]

    Permalink

    returns

    (poi, category_id)

  19. def getYelpCategories(mergedRDD: RDD[Triple]): RDD[(Long, (Categories, Double))]

    Permalink

  20. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any

  21. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any

  22. def loadNTriple(tripleFilePath: String): RDD[Triple]

    Permalink

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

    Permalink
    Definition Classes
    AnyRef

  24. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef

  25. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef

  26. var poiCategories: RDD[(Long, Categories)]

    Permalink

  27. var poiCategoryId: RDD[(Long, Set[Long])]

    Permalink

  28. var poiCategoryValueSet: RDD[(Long, Categories)]

    Permalink

  29. var poiCoordinates: RDD[(Long, CoordinatePOI)]

    Permalink

  30. var poiFlatCategoryId: RDD[(Long, Long)]

    Permalink

  31. val poiYelpCategories: RDD[(Long, (Categories, Double))]

    Permalink

  32. var pois: RDD[Poi]

    Permalink

  33. val spark: SparkSession

    Permalink

    SparkSession

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

    Permalink
    Definition Classes
    AnyRef

  35. def toString(): String

    Permalink
    Definition Classes
    AnyRef → Any

  36. final def wait(): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

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

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

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

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped