ExprsPipeline-class: An S4 class to store models built during high-throughput...

In exprso: Rapid Deployment of Machine Learning Algorithms

Description

An S4 class to store models built during high-throughput learning

Usage

## S4 method for signature 'ExprsPipeline'
show(object)

## S4 method for signature 'ExprsPipeline,ANY,ANY,ANY'
x[i, j]

## S4 method for signature 'ExprsPipeline'
x$name

## S4 method for signature 'ExprsPipeline'
subset(x, subset, select)

## S4 method for signature 'ExprsPipeline'
summary(object)

## S4 method for signature 'ExprsPipeline'
getFeatures(object, index)

## S4 method for signature 'ExprsPipeline'
getWeights(object, index, ...)

Arguments

object, x	An object of class ExprsPipeline.
i, j	Subsets entire ExprsPipeline object via object@summary[i, j]. Returns object@summary[, j] if argument i is missing.
name	Returns object@summary[, name].
subset	Subsets entire ExprsPipeline object via object@summary[subset, ]. Can be used to rearrange summary table.
select	Subsets entire ExprsPipeline object via object@summary[, select]. Can be used to rearrange summary table.
index	A numeric scalar. The i-th model from which to retrieve features or weights. If missing, function will tabulate features or weights across all models.
...	For getWeights, optional arguments passed to glmnet::coef.cv.glmnet.

Methods (by generic)

• show: Method to show ExprsPipeline object.

• [: Method to subset ExprsPipeline object.

• $: Method to subset ExprsPipeline object.

• subset: Method to subset ExprsPipeline object.

• summary: Method to summarize ExprsPipeline results.

• getFeatures: Method to return features within an ExprsPredict model.

• getWeights: Method to return LASSO weights.

Slots

summary

Typically a data.frame. Stores the parameters and performances for the models.

machs

Typically a list. Stores the models referenced in summary slot.

See Also

ExprsArray-class
ExprsModel-class
ExprsPipeline-class
ExprsEnsemble-class
ExprsPredict-class
RegrsPredict-class

exprso documentation built on May 1, 2019, 7:11 p.m.