AgghooCV {agghoo}

R6 class with agghoo functions fit() and predict().

Description

Class encapsulating the methods to run to obtain the best predictor from the list of models (see 'Model' class).

Methods

Public methods

• AgghooCV$new()

• AgghooCV$fit()

• AgghooCV$predict()

• AgghooCV$getParams()

• AgghooCV$clone()

Method new()

Create a new AgghooCV object.

Usage

AgghooCV$new(data, target, task, gmodel, loss)

Arguments

data

Matrix or data.frame

target

Vector of targets (generally numeric or factor)

task

"regression" or "classification". Default: classification if target not numeric.

gmodel

Generic model returning a predictive function Default: tree if mixed data, knn/ppr otherwise.

loss

Function assessing the error of a prediction Default: error rate or mean(abs(error)).

Method fit()

Fit an agghoo model.

Usage

AgghooCV$fit(CV = NULL)

Arguments

CV

List describing cross-validation to run. Slots:
- type: 'vfold' or 'MC' for Monte-Carlo (default: MC)
- V: number of runs (default: 10)
- test_size: percentage of data in the test dataset, for MC (irrelevant for V-fold). Default: 0.2.
- shuffle: wether or not to shuffle data before V-fold. Irrelevant for Monte-Carlo; default: TRUE
Default (if NULL): type="MC", V=10, test_size=0.2

Method predict()

Predict an agghoo model (after calling fit())

Usage

AgghooCV$predict(X)

Arguments

X

Matrix or data.frame to predict

Method getParams()

Return the list of V best parameters (after calling fit())

Usage

AgghooCV$getParams()

Method clone()

The objects of this class are cloneable with this method.

Usage

AgghooCV$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.