Aggregates multiple classifiers into a single ensemble classifier.
buildEnsemble(object, ...)# S4 method for ExprsModel
buildEnsemble(object, ...)
# S4 method for ExprsPipeline
buildEnsemble(object, colBy = 0, how = 0,
gate = 0, top = 0)
An ExprsModel-class object.
Additional ExprsModel objects to use in the ensemble.
Argument applies to ExprsModel-class method only.
A character vector or string. Specifies column(s) to use when filtering by classifier performance. Listing multiple columns will result in a filter based on a performance metric equal to the product of those listed columns.
A numeric scalar. Arguments between 0 and 1 will impose
a threshold or ceiling filter, respectively, based on the raw value of
colBy. Arguments between 1 and 100 will impose a filter based on
the percentile of colBy. The user may also provide "midrange",
"median", or "mean" as an argument for these filters. Set how = 0
or gate = 0, to skip the threshold or ceiling filter,
respectively.
A numeric scalar. Arguments between 0 and 1 will impose
a threshold or ceiling filter, respectively, based on the raw value of
colBy. Arguments between 1 and 100 will impose a filter based on
the percentile of colBy. The user may also provide "midrange",
"median", or "mean" as an argument for these filters. Set how = 0
or gate = 0, to skip the threshold or ceiling filter,
respectively.
A numeric scalar. Determines the top N models based on
colBy to include after the threshold and ceiling filters.
In the case that the @summary slot contains the column
"boot", this determines the top N models for each unique bootstrap.
Set top = 0 to skip this subset.
An ExprsEnsemble-class object.
ExprsModel: Method to build ensemble from ExprsModel objects.
ExprsPipeline: Method to build ensemble from ExprsPipeline objects.
The ExprsModel-class method:
Combine any number of ExprsModel objects into an ensemble. These models
do not necessarily have to derive from the same build method. This
method works identically to the conjoin ExprsModel method.
The ExprsPipeline-class method:
Build an ensemble from an ExprsPipeline object. This method works by
calling pipeFilter, then aggregating those results into an ensemble.
As an adjunct to this method, consider first combining multiple
ExprsPipeline objects together with conjoin.
pipeFilter
pipeUnboot
plCV
plGrid
plGridMulti
plMonteCarlo
plNested