Object

io.archivesunleashed.spark.matchbox

ExtractEntities

Related Doc: package matchbox

Permalink

object ExtractEntities

Extracts entities

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

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. final def eq(arg0: AnyRef): Boolean

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

    Permalink
    Definition Classes
    AnyRef → Any
  8. def extractAndOutput(iNerClassifierFile: String, rdd: RDD[(String, String, String)], outputFile: String): RDD[(String, String, String)]

    Permalink

    iNerClassifierFile

    path of classifier file

    rdd

    with values (date, url, content)

    outputFile

    path of output directory

  9. def extractFromRecords(iNerClassifierFile: String, inputRecordFile: String, outputFile: String, sc: SparkContext): RDD[(String, String, String)]

    Permalink

    iNerClassifierFile

    path of classifier file

    inputRecordFile

    path of ARC or WARC file from which to extract entities

    outputFile

    path of output directory

  10. def extractFromScrapeText(iNerClassifierFile: String, inputFile: String, outputFile: String, sc: SparkContext): RDD[(String, String, String)]

    Permalink

    iNerClassifierFile

    path of classifier file

    inputFile

    path of file with tuples (date: String, url: String, content: String) from which to extract entities

    outputFile

    path of output directory

  11. def finalize(): Unit

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  12. final def getClass(): Class[_]

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

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

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

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

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

    Permalink
    Definition Classes
    AnyRef
  18. final def synchronized[T0](arg0: ⇒ T0): T0

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

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

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

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

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

Inherited from AnyRef

Inherited from Any

Ungrouped