LatentSemanticIndexBuilder

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 buildFromCsv(inputCsv: String, docIdCols: Seq[Int], skipHeader: Boolean = true, stemTerms: Boolean = true): (Double, DenseVector[Double], LatentSemanticIndex)

   

   recompute the entire latent semantic index from the data stored in the supplied CSV file.

   recompute the entire latent semantic index from the data stored in the supplied CSV file. The CSV file must include one or more document ids for each row and must include the document text content in the remaining column.

   Eg: DocID1,SubID2,Text 1, 111 , "This is some text data"

   The fields should be quoted either with " or '.

   returns

   The return result includes the latent semantic index, along with the entropy of the terms calculated from the data set and the contributions of each singular component to the total entropy of the document set.

6. def clone(): AnyRef

   

   Attributes

   protected[java.lang]

   Definition Classes

   AnyRef

   Annotations

   @throws( ... )

7. def computeSvd(tfIdf: DenseMatrix[Double]): (DenseSVD, Double, DenseVector[Double])

   

   compute the Svd along with the entropy of the data set and the contributions of each singular value component.

8. def computeTfIdf(terms: Seq[Array[String]]): (Map[Int, (String, Int, Int)], DenseMatrix[Double])

   

   compute the TfIdf matrix

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

   

   Definition Classes

   AnyRef

10. def equals(arg0: Any): Boolean

    

    Definition Classes

    AnyRef → Any

11. def extractStemmedTerms(stopwords: Seq[String], lines: Seq[String]): Seq[Array[String]]

    

    extract stemmed terms from the supplied sequence of lines

12. def extractTerms(stopwords: Seq[String], lines: Seq[String]): Seq[Array[String]]

    

    extract terms without stemming.

13. def finalize(): Unit

    

    Attributes

    protected[java.lang]

    Definition Classes

    AnyRef

    Annotations

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

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

    

    Definition Classes

    AnyRef → Any

15. def hashCode(): Int

    

    Definition Classes

    AnyRef → Any

16. final def isInstanceOf[T0]: Boolean

    

    Definition Classes

    Any

17. def loadStopWords(): Seq[String]

    

    load the default set of stopwords using the embedded stopwords loader.

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

    

    Definition Classes

    AnyRef

19. final def notify(): Unit

    

    Definition Classes

    AnyRef

20. final def notifyAll(): Unit

    

    Definition Classes

    AnyRef

21. def readIndexedCsv(path: String, docIdCols: Seq[Int], skipHeader: Boolean = true): (Map[Int, Seq[String]], ListBuffer[String])

    

    read an indexed CSV file containing document Ids for each row and string text for each document.

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

    

    Definition Classes

    AnyRef

23. def toString(): String

    

    Definition Classes

    AnyRef → Any

24. final def wait(): Unit

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

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

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )

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

    

    Definition Classes

    AnyRef

    Annotations

    @throws( ... )