org.apache.mahout.math

drm

package drm

Linear Supertypes
AnyRef, Any
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. drm
  2. AnyRef
  3. Any
  1. Hide All
  2. Show all
Learn more about member selection
Visibility
  1. Public
  2. All

Type Members

  1. trait BCast[T] extends Closeable

    Broadcast variable abstraction

  2. type BlockMapFunc[S, R] = ((Array[S], Matrix)) ⇒ (Array[R], Matrix)

    Block-map func

  3. type BlockMapFunc2[S] = ((Array[S], Matrix)) ⇒ Matrix

  4. type BlockReduceFunc = (Matrix, Matrix) ⇒ Matrix

  5. type BlockifiedDrmTuple[K] = Tuple2[Array[K], _ <: Matrix]

    Drm block-wise tuple: Array of row keys and the matrix block.

  6. trait CheckpointedDrm[K] extends DrmLike[K]

    Checkpointed DRM API.

  7. class CheckpointedOps[K] extends AnyRef

    Additional experimental operations over CheckpointedDRM implementation.

  8. trait DistributedContext extends Closeable

    Distributed context (a.

  9. trait DistributedEngine extends AnyRef

    Abstraction of optimizer/distributed engine

  10. final class DrmDoubleScalarOps extends AnyVal

  11. trait DrmLike[K] extends AnyRef

    Basic DRM trait.

  12. class DrmLikeOps[K] extends AnyRef

    Common Drm ops

  13. type DrmTuple[K] = (K, Vector)

    Drm row-wise tuple

  14. class RLikeDrmIntOps extends RLikeDrmOps[Int]

  15. class RLikeDrmOps[K] extends DrmLikeOps[K]

Value Members

  1. object CacheHint extends Enumeration

  2. object DistributedEngine

  3. object RLikeDrmOps

  4. implicit def bcast2val[T](bcast: BCast[T]): T

    Implicit broadcast -> value conversion.

  5. implicit def ctx2engine(ctx: DistributedContext): DistributedEngine

    Just throw all engine operations into context as well.

  6. def dabs[K](drmA: DrmLike[K]): DrmLike[K]

  7. def dcolMeanCov[K](drmA: DrmLike[K])(implicit arg0: ClassTag[K]): (Vector, DrmLike[Int])

    Compute COV(X) matrix and mean of row-wise data set.

    Compute COV(X) matrix and mean of row-wise data set. X is presented as row-wise input matrix A.

    This is a "wide" procedure, covariance matrix is returned as a DRM.

    drmA

    note: will pin input into cache if not yet pinned.

    returns

    mean → covariance DRM

  8. def dcolMeanCovThin[K](drmA: DrmLike[K])(implicit arg0: ClassTag[K]): (Vector, Matrix)

    Thin column-wise mean and covariance matrix computation.

    Thin column-wise mean and covariance matrix computation. Same as dcolMeanCov() but suited for thin and tall inputs where covariance matrix can be reduced and finalized in driver memory.

    drmA

    note: will pin input to cache if not yet pinned.

    returns

    mean → covariance matrix (in core)

  9. def dcolMeanStdevs[K](drmA: DrmLike[K]): (Vector, Vector)

    Compute column wise means and standard deviations -- distributed version.

    Compute column wise means and standard deviations -- distributed version.

    drmA

    note: input will be pinned to cache if not yet pinned

    returns

    colMeans → colStdevs

  10. def dcolMeanVars[K](drmA: DrmLike[K]): (Vector, Vector)

    Compute column wise means and variances -- distributed version.

    Compute column wise means and variances -- distributed version.

    K
    drmA

    Note: will pin input to cache if not yet pinned.

    returns

    colMeans → colVariances

  11. def dexp[K](drmA: DrmLike[K]): DrmLike[K]

  12. def dlog[K](drmA: DrmLike[K]): DrmLike[K]

  13. implicit def drm2Checkpointed[K](drm: DrmLike[K]): CheckpointedDrm[K]

    We assume that whenever computational action is invoked without explicit checkpoint, the user doesn't imply caching

  14. implicit def drm2InCore[K](drm: DrmLike[K]): Matrix

    Implicit conversion to in-core with NONE caching of the result.

  15. def drm2IntKeyed[K](drmX: DrmLike[K], computeMap: Boolean = false): (DrmLike[Int], Option[DrmLike[K]])

    Convert arbitrarily-keyed matrix to int-keyed matrix.

    Convert arbitrarily-keyed matrix to int-keyed matrix. Some algebra will accept only int-numbered row matrices. So this method is to help.

    K

    key type

    drmX

    input to be transcoded

    computeMap

    collect old key -> int key map to front-end?

    returns

    Sequentially keyed matrix + (optionally) map from non-int key to Int key. If the key type is actually Int, then we just return the argument with None for the map, regardless of computeMap parameter.

  16. implicit def drm2drmCpOps[K](drm: CheckpointedDrm[K]): CheckpointedOps[K]

  17. def drmBroadcast(v: Vector)(implicit ctx: DistributedContext): BCast[Vector]

    Broadcast support API

  18. def drmBroadcast(m: Matrix)(implicit ctx: DistributedContext): BCast[Matrix]

    Broadcast support API

  19. def drmDfsRead(path: String)(implicit ctx: DistributedContext): CheckpointedDrm[_]

    Load DRM from hdfs (as in Mahout DRM format)

  20. def drmParallelize(m: Matrix, numPartitions: Int = 1)(implicit sc: DistributedContext): CheckpointedDrm[Int]

    Shortcut to parallelizing matrices with indices, ignore row labels.

  21. def drmParallelizeEmpty(nrow: Int, ncol: Int, numPartitions: Int = 10)(implicit ctx: DistributedContext): CheckpointedDrm[Int]

    This creates an empty DRM with specified number of partitions and cardinality.

  22. def drmParallelizeEmptyLong(nrow: Long, ncol: Int, numPartitions: Int = 10)(implicit ctx: DistributedContext): CheckpointedDrm[Long]

    Creates empty DRM with non-trivial height

  23. def drmParallelizeWithRowIndices(m: Matrix, numPartitions: Int = 1)(implicit ctx: DistributedContext): CheckpointedDrm[Int]

    Parallelize in-core matrix as a distributed matrix, using row ordinal indices as data set keys.

  24. def drmParallelizeWithRowLabels(m: Matrix, numPartitions: Int = 1)(implicit ctx: DistributedContext): CheckpointedDrm[String]

    Parallelize in-core matrix as a distributed matrix, using row labels as a data set keys.

  25. def drmSampleKRows[K](drmX: DrmLike[K], numSamples: Int, replacement: Boolean = false): Matrix

  26. def drmSampleRows[K](drmX: DrmLike[K], fraction: Double, replacement: Boolean = false): DrmLike[K]

    (Optional) Sampling operation.

    (Optional) Sampling operation. Consistent with Spark semantics of the same.

    K
    drmX
    fraction
    replacement
    returns

    samples

  27. def drmSampleToTSV[K](drmX: DrmLike[K], samplePercent: Double = 1): String

    Convert a DRM sample into a Tab Separated Vector (TSV) to be loaded into an R-DataFrame for plotting and sketching

    Convert a DRM sample into a Tab Separated Vector (TSV) to be loaded into an R-DataFrame for plotting and sketching

    K
    drmX

    - DRM

    samplePercent

    - Percentage of Sample elements from the DRM to be fished out for plotting

    returns

    TSV String

  28. def dsignum[K](drmA: DrmLike[K]): DrmLike[K]

  29. def dsqDist(drmX: DrmLike[Int], drmY: DrmLike[Int]): DrmLike[Int]

    Compute fold-in distances (distributed version).

    Compute fold-in distances (distributed version). Here, we use pretty much the same math as with squared distances.

    D_sq = s*1' + 1*t' - 2*X*Y'

    where s is row sums of hadamard product(X, X), and, similarly, s is row sums of Hadamard product(Y, Y).

    drmX

    m x d row-wise dataset. Pinned to cache if not yet pinned.

    drmY

    n x d row-wise dataset. Pinned to cache if not yet pinned.

    returns

    m x d pairwise squared distance matrix (between rows of X and Y)

  30. def dsqDist(drmX: DrmLike[Int]): DrmLike[Int]

    Distributed Squared distance matrix computation.

  31. def dsqrt[K](drmA: DrmLike[K]): DrmLike[K]

  32. package logical

  33. def safeToNonNegInt(x: Long): Int

    CacheHint type

Inherited from AnyRef

Inherited from Any

Ungrouped