Object

ai.h2o.sparkling.ml.utils

SchemaUtils

Related Doc: package utils

Permalink

object SchemaUtils

Utilities for working with Spark SQL component.

Linear Supertypes
AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. SchemaUtils
  2. AnyRef
  3. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Type Members

  1. case class FieldWithOrder(field: StructField, order: Iterable[Any]) extends Product with Serializable

    Permalink

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. def appendFlattenedStructsToDataFrame(df: DataFrame, prefixForNewColumns: String): DataFrame

    Permalink
  5. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any
  6. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  7. def collectMaxElementSizes(rdd: RDD[Row], schema: StructType): Array[Int]

    Permalink

    Collect max size of each element in DataFrame.

    Collect max size of each element in DataFrame. For array -> max array size For vectors -> max vector size For simple types -> 1

    returns

    array containing size of each element

  8. def collectVectorLikeTypes(flatSchema: StructType): Seq[Int]

    Permalink
  9. final def eq(arg0: AnyRef): Boolean

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

    Permalink
    Definition Classes
    AnyRef → Any
  11. def expandedSchema(flatSchema: StructType, elemMaxSizes: Array[Int]): Seq[StructField]

    Permalink

    Returns expanded schema

    Returns expanded schema

    • schema is represented as list of types
    • all arrays are expanded into columns based on the longest one
    • all vectors are expanded into columns based on the longest one
    flatSchema

    flat schema of spark data frame

    returns

    list of types with their positions

  12. def finalize(): Unit

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  13. def flattenDataFrame(df: DataFrame, flatSchema: StructType): DataFrame

    Permalink
  14. def flattenDataFrame(df: DataFrame): DataFrame

    Permalink
  15. def flattenSchema(df: DataFrame): StructType

    Permalink
  16. def flattenStructsInDataFrame(df: DataFrame): DataFrame

    Permalink
  17. def flattenStructsInSchema(schema: StructType, sourceColPrefix: Option[String] = None, targetColPrefix: Option[String] = None, nullable: Boolean = false): Seq[(StructField, String)]

    Permalink
  18. final def getClass(): Class[_]

    Permalink
    Definition Classes
    AnyRef → Any
  19. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any
  20. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any
  21. final def ne(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef
  22. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef
  23. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef
  24. def rowsToRowSchemas(df: DataFrame): Dataset[ArrayBuffer[FieldWithOrder]]

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

    Permalink
    Definition Classes
    AnyRef
  26. def toString(): String

    Permalink
    Definition Classes
    AnyRef → Any
  27. final def wait(): Unit

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

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

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

Inherited from AnyRef

Inherited from Any

Ungrouped