org.apache.spark.h2o

H2OSchemaUtils

object H2OSchemaUtils

Utilities for working with Spark SQL component.

Linear Supertypes
AnyRef, Any
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. H2OSchemaUtils
  2. AnyRef
  3. Any
  1. Hide All
  2. Show all
Learn more about member selection
Visibility
  1. Public
  2. All

Value Members

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

    Definition Classes
    AnyRef
  2. final def !=(arg0: Any): Boolean

    Definition Classes
    Any
  3. final def ##(): Int

    Definition Classes
    AnyRef → Any
  4. final def ==(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef
  5. final def ==(arg0: Any): Boolean

    Definition Classes
    Any
  6. val ARRAY_TYPE: Byte

  7. val NORMAL_TYPE: Byte

  8. val VEC_TYPE: Byte

  9. final def asInstanceOf[T0]: T0

    Definition Classes
    Any
  10. def clone(): AnyRef

    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  11. def collectArrayLikeTypes(fields: Seq[StructField], path: Seq[Int] = Seq()): Seq[Seq[Int]]

  12. def collectStringTypesIndx(fields: Seq[StructField], path: Seq[Int] = Seq()): Seq[Seq[Int]]

    Collect all StringType indexes in give list representing schema

  13. def collectTypeIndx(fields: Seq[StructField], path: Seq[Int] = Seq()): Seq[Seq[Int]]

  14. def collectVectorLikeTypes(fields: Seq[StructField], path: Seq[Int] = Seq()): Seq[Seq[Int]]

  15. def createSchema(f: DataFrame): StructType

  16. def dataTypeToVecType(dt: DataType, d: Array[String]): Byte

    Method translating SQL types into Sparkling Water types

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

    Definition Classes
    AnyRef
  18. def equals(arg0: Any): Boolean

    Definition Classes
    AnyRef → Any
  19. def expandedSchema(sc: SparkContext, srdd: SchemaRDD): Seq[(Seq[Int], StructField, Byte)]

    Returns expanded schema

    Returns expanded schema

    • schema is represented as list of types and its position inside row
    • all arrays are expanded into columns based on the longest one
    • all vectors are expanded into columns
    sc

    actual Spark context

    srdd

    schema-based RDD

    returns

    list of types with their positions

  20. def finalize(): Unit

    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  21. def flatSchema(s: StructType, typeName: Option[String] = None, nullable: Boolean = false): Seq[StructField]

    Return flattenized type - recursively transforms StrucType into Seq of encapsulated types.

  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. final def ne(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef
  26. final def notify(): Unit

    Definition Classes
    AnyRef
  27. final def notifyAll(): Unit

    Definition Classes
    AnyRef
  28. def numericVecTypeToDataType(v: Vec): DataType

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

    Definition Classes
    AnyRef
  30. def toString(): String

    Definition Classes
    AnyRef → Any
  31. def vecTypeToDataType(v: Vec): DataType

    Return catalyst structural type for given H2O vector.

    Return catalyst structural type for given H2O vector.

    The mapping of type is flat, if type is unrecognized IllegalArgumentException is thrown.

    v

    H2O vector

    returns

    catalyst data type

  32. final def wait(): Unit

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  33. final def wait(arg0: Long, arg1: Int): Unit

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  34. final def wait(arg0: Long): Unit

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

Inherited from AnyRef

Inherited from Any

Ungrouped