Datasets

Value Members

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

   

   Definition Classes

   AnyRef → Any

2. final def ##(): Int

   

   Definition Classes

   AnyRef → Any

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

   

   Definition Classes

   AnyRef → Any

4. final def asInstanceOf[T0]: T0

   

   Definition Classes

   Any

5. def clone(): AnyRef

   

   Attributes

   protected[java.lang]

   Definition Classes

   AnyRef

   Annotations

   @throws( ... )

6. def crossValidate[L, F](dataset: Dataset[L, F], classifierFactory: () ⇒ Classifier[L, F], numFolds: Int = 5): Iterable[(L, L)]

   

   Implements classic cross validation; producing pairs of gold/predicted labels across the training dataset

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

   

   Definition Classes

   AnyRef

8. def equals(arg0: Any): Boolean

   

   Definition Classes

   AnyRef → Any

9. def featureSelectionByFrequency[L, F](dataset: Dataset[L, F], classifierFactory: () ⇒ Classifier[L, F], scoringMetric: (Iterable[(L, L)]) ⇒ Double, numFolds: Int = 5): Set[Int]

   

10. def featureSelectionByInformativeness[L, F](dataset: Dataset[L, F], classifierFactory: () ⇒ Classifier[L, F], scoringMetric: (Iterable[(L, L)]) ⇒ Double, minFreq: Int = 10, numFolds: Int = 5, step: Int = 1000): Set[Int]

    

11. def finalize(): Unit

    

    Attributes

    protected[java.lang]

    Definition Classes

    AnyRef

    Annotations

    @throws( classOf[java.lang.Throwable] )

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

    

    Definition Classes

    AnyRef → Any

13. def hashCode(): Int

    

    Definition Classes

    AnyRef → Any

14. def incrementalFeatureSelection[L, F](dataset: Dataset[L, F], classifierFactory: () ⇒ Classifier[L, F], scoringMetric: (Iterable[(L, L)]) ⇒ Double, featureGroups: Map[String, Set[Int]], numFolds: Int = 5, nCores: Int = 8): Set[String]

    

    Performs incremental feature selection through cross-validation on the given dataset

15. def informationGain[L, F](rowsWithTerm: Double, rowsWithoutTerm: Double, labelsWithTerm: Counter[Int], labelsWithoutTerm: Counter[Int], ND: Int, NL: Int): Double

    

    This computes the IG formula from (Yang and Pedersen, 1997) However, this skips the first of the formula, which independent of the term t

16. final def isInstanceOf[T0]: Boolean

    

    Definition Classes

    Any

17. def keepMoreFrequent(features: Counter[Int], threshold: Double): Set[Int]

    

18. val logger: Logger

    

19. def mkFolds(numFolds: Int, size: Int): Iterable[DatasetFold]

    

    Creates dataset folds to be used for cross validation

20. def mkTrainIndices[F](datasetSize: Int, spans: Option[Iterable[(Int, Int)]]): Array[Int]

    

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

    

    Definition Classes

    AnyRef

22. final def notify(): Unit

    

    Definition Classes

    AnyRef

23. final def notifyAll(): Unit

    

    Definition Classes

    AnyRef

24. def scoreFeatures[L, F](dataset: Dataset[L, F], features: HashSet[Int], classifierFactory: () ⇒ Classifier[L, F], numFolds: Int, scoringMetric: (Iterable[(L, L)]) ⇒ Double): Double

    

25. def scoreGroup[L, F](group: String, featureGroups: Map[String, Set[Int]], chosenFeatures: HashSet[Int], dataset: Dataset[L, F], classifierFactory: () ⇒ Classifier[L, F], numFolds: Int, scoringMetric: (Iterable[(L, L)]) ⇒ Double): (String, Double)

    

26. def sortFeaturesByFrequency[L, F](dataset: Dataset[L, F]): Counter[Int]

    

27. def sortFeaturesByInformativeness[L, F](dataset: Dataset[L, F], minFreq: Int): Counter[Int]

    

28. def svmScaleBVFDataset[L, F](dataset: BVFDataset[L, F], lower: Double, upper: Double): ScaleRange[F]

    

29. def svmScaleDataset[L, F](dataset: Dataset[L, F], lower: Double = 1, upper: Double = 1): ScaleRange[F]

    

    Scales feature values using the svm-scale formula.

    Scales feature values using the svm-scale formula. Scaling is performed in place

30. def svmScaleDatum[F](features: Counter[F], ranges: ScaleRange[F], lower: Double = 1, upper: Double = 1): Counter[F]

    

    The same functionality as svmScaleDataset, but applied to an individual datum

31. def svmScaleFeatureTraversable[F](dataset: FeatureTraversable[F, Double], lower: Double, upper: Double): ScaleRange[F]

    

32. def svmScaleRVFDataset[L, F](dataset: RVFDataset[L, F], lower: Double, upper: Double): ScaleRange[F]

    

33. def svmScaleRankingDataset[L, F](dataset: RankingDataset[F], lower: Double = 1, upper: Double = 1): ScaleRange[F]

    

    Scales feature values using the svm-scale formula.

    Scales feature values using the svm-scale formula. Scaling is performed in place

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

    

    Definition Classes

    AnyRef

35. def toString(): String

    

    Definition Classes

    AnyRef → Any

36. final def wait(): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

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

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

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

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )