man/agghoo.Rd

   1 % Generated by roxygen2: do not edit by hand
   2 % Please edit documentation in R/agghoo.R
   3 \name{agghoo}
   4 \alias{agghoo}
   5 \title{agghoo}
   6 \usage{
   7 agghoo(data, target, task = NA, gmodel = NA, params = NA, quality = NA)
   8 }
   9 \arguments{
  10 \item{data}{Data frame or matrix containing the data in lines.}
  11
  12 \item{target}{The target values to predict. Generally a vector.}
  13
  14 \item{task}{"classification" or "regression". Default:
  15 regression if target is numerical, classification otherwise.}
  16
  17 \item{gmodel}{A "generic model", which is a function returning a predict
  18 function (taking X as only argument) from the tuple
  19 (dataHO, targetHO, param), where 'HO' stands for 'Hold-Out',
  20 referring to cross-validation. Cross-validation is run on an array
  21 of 'param's. See params argument. Default: see R6::Model.}
  22
  23 \item{params}{A list of parameters. Often, one list cell is just a
  24 numerical value, but in general it could be of any type.
  25 Default: see R6::Model.}
  26
  27 \item{quality}{A function assessing the quality of a prediction.
  28 Arguments are y1 and y2 (comparing a prediction to known values).
  29 Default: see R6::AgghooCV.}
  30 }
  31 \value{
  32 An R6::AgghooCV object.
  33 }
  34 \description{
  35 Run the agghoo procedure. (...)
  36 }
  37 \examples{
  38 # Regression:
  39 a_reg <- agghoo(iris[,-c(2,5)], iris[,2])
  40 a_reg$fit()
  41 pr <- a_reg$predict(iris[,-c(2,5)] + rnorm(450, sd=0.1))
  42 # Classification
  43 a_cla <- agghoo(iris[,-5], iris[,5])
  44 a_cla$fit(mode="standard")
  45 pc <- a_cla$predict(iris[,-5] + rnorm(600, sd=0.1))
  46
  47 }