Packages

class ItemBasedRecommender extends Recommender

The ItemBasedRecommender class is used to perform predictions based on Item based Collaborative Filtering techniques (Cosine, Correlation, Adjusted Cosine)

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

Instance Constructors

  1. new ItemBasedRecommender(input: MatrixI, m: Int, n: Int, stream: Int = 0)

    input

    the original 4-column input data matrix

    m

    the number of rows

    n

    the number of columns

    stream

    the random number stream to use

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. def adjCosine: Unit

    Generate the Adjusted Cosine Similarity matrix.

  5. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  6. def clone(): AnyRef
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @native() @throws( ... )
  7. def corrSim: Unit

    Generate the Correlation Similarity matrix.

  8. def cosSim: Unit

    Generate the Cosine Similarity matrix on the basis of column - corated pairs.

  9. def crossValidate(tester: MatrixD): Unit

    Phase 2: Cross validate the final predictions against the test dataset.

    Phase 2: Cross validate the final predictions against the test dataset.

    tester

    testing data matrix

    Definition Classes
    Recommender
  10. def denormalize(i: Int): Double

    Create a column denormalized version of 'this' matrix.

    Create a column denormalized version of 'this' matrix. return the denormalized value of the

    i

    the user index

  11. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  12. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  13. def error_metrics(input: MatrixI): Unit

    Phase 1: Print MAE and RMSE metrics based on the final predictions for the test dataset.

    Phase 1: Print MAE and RMSE metrics based on the final predictions for the test dataset.

    input

    the test portion of the original 4-column input matrix

    Definition Classes
    Recommender
  14. def finalize(): Unit
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  15. def genTrain2(train: MatrixI): Unit

    Generate the training matrix for the dataset for Phase 1.

    Generate the training matrix for the dataset for Phase 1.

    train

    the training data matrix

  16. def genTrainTest(exl: VectorI, input: MatrixI): MatrixD

    Generate the training matrix for the dataset for Phase 2.

    Generate the training matrix for the dataset for Phase 2.

    exl

    the vector of index values which will be excluded in the train

    input

    the original data matrix

  17. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  18. def getStats: Array[Statistic]

    Return the variables for the statistics vectors.

    Return the variables for the statistics vectors.

    Definition Classes
    Recommender
  19. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  20. def impute: Unit

    Impute values for null/zero values in the 'training' matrix using Column Mean Imputation.

  21. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  22. def makeRatings(input: MatrixI, m: Int, n: Int): MatrixD

    Convert an original 4-column 'input' integer matrix (i, j, value, timestamp) into a two-dimensional 'ratings' double matrix with 'm' rows and 'n' columns.

    Convert an original 4-column 'input' integer matrix (i, j, value, timestamp) into a two-dimensional 'ratings' double matrix with 'm' rows and 'n' columns. The 'input' matrix has type MatrixI, while the 'ratings' matrix has type MatrixD.

    input

    the original 4-column input data matrix containing ratings, e.g., from a file

    m

    the number of rows for the ratings matrix

    n

    the number of columns for the ratings matrix

    Definition Classes
    Recommender
  23. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  24. def normalize: Unit

    Normalize the 'training' matrix by subtracting the row mean from each non-zero element.

    Normalize the 'training' matrix by subtracting the row mean from each non-zero element. Row mean calculations exclude the zero elements.

  25. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  26. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  27. def rate(i: Int, j: Int): Double

    Generate a rating based on the similarity between 'nsim' similar items.

    Generate a rating based on the similarity between 'nsim' similar items.

    i

    the user index

    j

    the item index

    Definition Classes
    ItemBasedRecommender → Recommender
  28. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  29. def test(istart: Int, iend: Int, input: MatrixI): Unit

    Phase 3: Test the accuracy of the predictions and add it to the statistics vector.

    Phase 3: Test the accuracy of the predictions and add it to the statistics vector.

    istart

    the start point

    iend

    the end point

    input

    the original 4-column input matrix

    Definition Classes
    Recommender
  30. def toString(): String
    Definition Classes
    AnyRef → Any
  31. def topk(x: VectorD, k: Int): VectorI

    Return the indices of the 'k' largest values in vector 'x'.

    Return the indices of the 'k' largest values in vector 'x'. FIX - replace with more efficient top-k algorithm

    x

    the input vector

    k

    the number of values to be returned

    Definition Classes
    Recommender
  32. def topk2(x: VectorD, k: Int): Array[Int]

    Return the indices of the 'k' largest values in vector 'x'.

    Return the indices of the 'k' largest values in vector 'x'.

    x

    the input vector

    k

    the number of values to be returned

    Definition Classes
    Recommender
  33. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  34. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  35. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @native() @throws( ... )
  36. def zRatings(limit: Int, input: MatrixI): Unit

    Return a matrix with replacing all values with 0 beyond the interval specified corresponds to Phase 3 of the expermiments.

    Return a matrix with replacing all values with 0 beyond the interval specified corresponds to Phase 3 of the expermiments.

    limit

    the interval start point

    input

    the original data matrix

Inherited from Recommender

Inherited from AnyRef

Inherited from Any

Ungrouped