Class

com.databricks.labs.automl.sanitize

OutlierFiltering

Related Doc: package sanitize

Permalink

class OutlierFiltering extends SparkSessionWrapper with DataValidation

Linear Supertypes
DataValidation, SparkSessionWrapper, Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. OutlierFiltering
  2. DataValidation
  3. SparkSessionWrapper
  4. Serializable
  5. Serializable
  6. AnyRef
  7. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new OutlierFiltering(df: DataFrame)

    Permalink

    df

    - Input DataFrame pre-feature vectorization

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 _allowableCardinalilties: List[String]

    Permalink
    Definition Classes
    DataValidation

  5. def _allowableCategoricalFilterModes: List[String]

    Permalink
    Definition Classes
    DataValidation

  6. def _allowableDateTimeConversions: List[String]

    Permalink
    Definition Classes
    DataValidation

  7. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any

  8. def clone(): AnyRef

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

  9. def convertDateAndTime(df: DataFrame, dateFields: List[String], timeFields: List[String], mode: String): (DataFrame, List[String])

    Permalink
    Definition Classes
    DataValidation

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

    Permalink
    Definition Classes
    AnyRef

  11. def equals(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  12. def filterContinuousOutliers(manualFilter: List[ManualFilters], vectorIgnoreList: Array[String]): (DataFrame, DataFrame, Map[String, (Double, String)])

    Permalink

  13. def filterContinuousOutliers(vectorIgnoreList: Array[String], ignoreList: Array[String] = Array.empty[String]): (DataFrame, DataFrame, Map[String, (Double, String)])

    Permalink

  14. def finalize(): Unit

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

  15. def generateAssembly(numericColumns: List[String], characterColumns: List[String], featureCol: String): (Array[StringIndexer], Array[String], VectorAssembler)

    Permalink
    Definition Classes
    DataValidation

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

    Permalink
    Definition Classes
    AnyRef → Any

  17. def getContinuousDataThreshold: Int

    Permalink

  18. def getFilterBounds: String

    Permalink

  19. def getFilterPrecision: Double

    Permalink

  20. def getLabelCol: String

    Permalink

  21. def getLowerFilterNTile: Double

    Permalink

  22. def getParallelism: Int

    Permalink

  23. def getUpperFilterNTile: Double

    Permalink

  24. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any

  25. def indexStrings(categoricalFields: List[String]): (Array[StringIndexer], Array[String])

    Permalink
    Definition Classes
    DataValidation

  26. def invalidateSelection(value: String, allowances: Seq[String]): String

    Permalink
    Definition Classes
    DataValidation

  27. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any

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

    Permalink
    Definition Classes
    AnyRef

  29. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef

  30. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef

  31. def oneHotEncodeStrings(stringIndexedFields: List[String]): (OneHotEncoderEstimator, Array[String])

    Permalink
    Definition Classes
    DataValidation

  32. lazy val sc: SparkContext

    Permalink
    Definition Classes
    SparkSessionWrapper

  33. def setContinuousDataThreshold(value: Int): OutlierFiltering.this.type

    Permalink

  34. def setFilterBounds(value: String): OutlierFiltering.this.type

    Permalink

  35. def setFilterPrecision(value: Double): OutlierFiltering.this.type

    Permalink

  36. def setLabelCol(value: String): OutlierFiltering.this.type

    Permalink

  37. def setLowerFilterNTile(value: Double): OutlierFiltering.this.type

    Permalink

  38. def setParallelism(value: Int): OutlierFiltering.this.type

    Permalink

  39. def setUpperFilterNTile(value: Double): OutlierFiltering.this.type

    Permalink

  40. lazy val spark: SparkSession

    Permalink
    Definition Classes
    SparkSessionWrapper

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

    Permalink
    Definition Classes
    AnyRef

  42. def toString(): String

    Permalink
    Definition Classes
    AnyRef → Any

  43. def validateCardinality(df: DataFrame, stringFields: List[String], cardinalityLimit: Int = 500, parallelism: Int = 20): ValidatedCategoricalFields

    Permalink
    Definition Classes
    DataValidation

  44. def validateFieldPresence(df: DataFrame, column: String): Unit

    Permalink
    Definition Classes
    DataValidation

  45. def validateInputDataframe(df: DataFrame): Unit

    Permalink
    Definition Classes
    DataValidation

  46. def validateLabelAndFeatures(df: DataFrame, labelCol: String, featureCol: String): Unit

    Permalink
    Definition Classes
    DataValidation

  47. final def wait(): Unit

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

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

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

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

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

Inherited from DataValidation

Inherited from SparkSessionWrapper

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped