bag: Bag an 'rtemis' learner for regression or classification (C,...

In egenn/rtemis: Machine Learning and Visualization

Bag an rtemis learner for regression or classification (C, R)

Description

Train a bagged ensemble using any learner

Usage

bag(
  x,
  y = NULL,
  x.test = NULL,
  y.test = NULL,
  weights = NULL,
  mod = "cart",
  k = 10,
  mtry = NULL,
  mod.params = list(),
  ifw = TRUE,
  ifw.type = 2,
  upsample = FALSE,
  downsample = FALSE,
  resample.seed = NULL,
  .resample = setup.resample(resampler = "strat.boot", n.resamples = k),
  aggr.fn = NULL,
  x.name = NULL,
  y.name = NULL,
  question = NULL,
  base.verbose = FALSE,
  verbose = TRUE,
  trace = 0,
  print.plot = TRUE,
  plot.fitted = NULL,
  plot.predicted = NULL,
  plot.theme = rtTheme,
  print.base.plot = FALSE,
  n.workers = rtCores,
  parallel.type = ifelse(.Platform$OS.type == "unix", "fork", "psock"),
  outdir = NULL,
  ...
)

Arguments

x	Numeric vector or matrix / data frame of features i.e. independent variables
y	Numeric vector of outcome, i.e. dependent variable
x.test	Numeric vector or matrix / data frame of testing set features Columns must correspond to columns in x
y.test	Numeric vector of testing set outcome
weights	Numeric vector: Weights for cases. For classification, weights takes precedence over ifw, therefore set weights = NULL if using ifw. Note: If weight are provided, ifw is not used. Leave NULL if setting ifw = TRUE.
mod	Character: Algorithm to bag, for options, see select_learn
k	Integer: Number of base learners to train
mtry	Integer: Number of features to randomly sample for each base learner.
mod.params	Named list of arguments for mod
ifw	Logical: If TRUE, apply inverse frequency weighting (for Classification only). Note: If weights are provided, ifw is not used.
ifw.type	Integer 0, 1, 2 1: class.weights as in 0, divided by min(class.weights) 2: class.weights as in 0, divided by max(class.weights)
upsample	Logical: If TRUE, upsample cases to balance outcome classes (for Classification only) Note: upsample will randomly sample with replacement if the length of the majority class is more than double the length of the class you are upsampling, thereby introducing randomness
downsample	Logical: If TRUE, downsample majority class to match size of minority class
resample.seed	Integer: If provided, will be used to set the seed during upsampling. Default = NULL (random seed)
.resample	List: Resample settings to use. There is no need to edit this, unless you want to change the type of resampling. It will use stratified bootstrap by default. Use setup.resample for convenience. Default = setup.resample(resampler = "strat.boot", n.resamples = k)
aggr.fn	Function: used to average base learners' predictions. Default = mean for Classification, median for Regression
x.name	Character: Name for feature set
y.name	Character: Name for outcome
question	Character: the question you are attempting to answer with this model, in plain language.
base.verbose	Logical: verbose argument passed to learner
verbose	Logical: If TRUE, print summary to screen.
trace	Integer: If > 0, print diagnostic info to console
print.plot	Logical: if TRUE, produce plot using mplot3 Takes precedence over plot.fitted and plot.predicted.
plot.fitted	Logical: if TRUE, plot True (y) vs Fitted
plot.predicted	Logical: if TRUE, plot True (y.test) vs Predicted. Requires x.test and y.test
plot.theme	Character: "zero", "dark", "box", "darkbox"
print.base.plot	Logical: Passed to print.plot argument of base learner, i.e. if TRUE, print error plot for each base learner
n.workers	Integer: Number of cores to use
parallel.type	Character: "fork" or "psock". Type of parallelization. Default = "fork" for macOS and Linux, "psock" for Windows
outdir	Character: Path to output directory to save model. Default = NULL
...	Additional parameters to be passed to learner

Author(s)

E.D. Gennatas

Examples

## Not run: 
# Data ----
set.seed(2018)
x <- rnormmat(500, 50)
colnames(x) <- paste0("Feature", 1:50)
w <- rnorm(50)
y <- .7 * x[, 3]^2 + 1.2 * x[, 10] + .5 * x[, 15] + .8 * x[, 20] + rnorm(500)
dat <- data.frame(x, y)
res <- resample(dat, seed = 2018)
dat_train <- dat[res$Subsample_1, ]
dat_test <- dat[-res$Subsample_1, ]

# bag ----
mod <- bag(dat_train, dat_test)

## End(Not run)

egenn/rtemis documentation built on March 28, 2024, 12:53 p.m.