projectedLearner-class: Class '"projectedLearner"'

In lgatto/MLInterfaces: Uniform interfaces to R machine learning procedures for data in Bioconductor containers

Description

helps depict prediction hyperregions from high-dimensional models

Objects from the Class

Objects can be created by calls of the form new("projectedLearner", ...).

Slots

fittedLearner:

Object of class "classifierOutput"

trainingSetPCA:

Object of class "prcomp"

trainingLabels:

Object of class "ANY" given labels for features used in training

testLabels:

Object of class "ANY" given labels for features used in testing

gridFeatsProjectedToTrainingPCs:

Object of class "matrix" rotated coordinates of training features

gridPredictions:

Object of class "ANY" predicted labels for all grid points

trainFeatsProjectedToTrainingPCs:

Object of class "matrix" rotated coordinates of training features

testFeatsProjectedToTrainingPCs:

Object of class "matrix" rotated coordinates of test features

trainPredictions:

Object of class "ANY" predicted labels for training features

testPredictions:

Object of class "ANY" predicted labels for test features

theCall:

Object of class "call" call used to generate this wonderful thing

Methods

learnerIn3D

signature(x = "projectedLearner"): uses rgl to give a dynamic 3d-like projection of labels in colored regions. See projectLearnerToGrid for an example.

plot

signature(x = "projectedLearner", y = "ANY"): pairs plot of the tesselated PCA of the training features

plotOne

signature(x = "projectedLearner"): a 2d plot of tesselation projection for selected axes of the PCA

show

signature(object = "projectedLearner"): object housing numerical resources for the renderings

Note

plot may need to be modified when there are many features/PCs in use

plotOne has additional arguments ind1, ind2, and type. ind1 and ind2 specify the PCs to display. type is one of "showTestPredictions" (default), "showTrainPredictions", "showTestLabels", "showTrainLabels". These indicate what will be used to locate glyphs with labels in the projected scatterplots.

Author(s)

VJ Carey <[e-mail]>

References

None.

Examples

showClass("projectedLearner")

lgatto/MLInterfaces documentation built on May 21, 2019, 5:12 a.m.