Trains a Projection-Pursuit oblique decision tree.

This function trains a Projection-Pursuit oblique decision tree using either a formula and data frame interface or a matrix-based interface. When using the formula interface, specify the model formula and the data frame containing the variables. For the matrix-based interface, provide matrices for the features and labels directly. If lambda = 0, the model is trained using Linear Discriminant Analysis (LDA). If lambda > 0, the model is trained using Penalized Discriminant Analysis (PDA).

Usage

pptr(
  formula = NULL,
  data = NULL,
  x = NULL,
  y = NULL,
  mode = NULL,
  lambda = 0,
  seed = NULL,
  pp = NULL,
  cutpoint = NULL,
  stop = NULL,
  binarize = NULL,
  grouping = NULL,
  leaf = NULL
)

Arguments

formula

A formula of the form y ~ x1 + x2 + ..., where y is a vector of labels and x1, x2, ... are the features.

data

A data frame containing the variables in the formula.

x

A matrix containing the features for each observation.

y

A matrix containing the labels for each observation.

mode

Training mode: either "classification" or "regression". When NULL (default), mode is auto-detected from y's type — factor or character vectors trigger classification, numeric vectors trigger regression. Setting it explicitly is useful for the binary-integer-labels case (mode = "classification" with integer 0/1 labels) and for failing fast on a type mismatch (mode = "regression" with a factor y errors immediately).

lambda

A regularization parameter. If lambda = 0, the model is trained using Linear Discriminant Analysis (LDA). If lambda > 0, the model is trained using Penalized Discriminant Analysis (PDA). Cannot be used together with pp.

seed

An optional integer seed for reproducibility. If NULL (default), a seed is drawn from R's RNG, so set.seed() controls reproducibility. If an integer is provided, that value is used directly.

pp

A projection pursuit strategy object created by pp_pda. Cannot be used together with lambda.

cutpoint

A split cutpoint strategy object created by cutpoint_mean_of_means (default).

stop

A stopping rule object. Default depends on mode: stop_pure_node() for classification, and stop_any(stop_min_size(5), stop_min_variance(0.01)) for regression.

binarize

A binarization strategy object. Default depends on mode: binarize_largest_gap() for classification, and binarize_disabled() for regression (regression's default grouping always yields a 2-group partition, so no binarization is needed).

grouping

A grouping strategy object. Default depends on mode: grouping_by_label() for classification, and grouping_by_cutpoint() for regression.

leaf

A leaf strategy object. Default depends on mode: leaf_majority_vote() for classification, and leaf_mean_response() for regression.

Value

A pptr model. Its S3 class vector is c("pptr_classification", "pptr", "ppmodel") or c("pptr_regression", "pptr", "ppmodel") depending on the mode.

Details

Mode is taken from the mode argument when explicit, and otherwise auto-detected from `y` (factor/character → classification, numeric → regression). Pass mode = "classification" to force classification on integer labels (e.g. binary 0/1), or mode = "regression" to assert intent on numeric responses.

See also

predict.pptr_classification, predict.pptr_regression, formula.ppmodel, print.pptr, save_json, load_json, pp_tree for parsnip integration

Examples

# Example 1: formula interface with the `iris` dataset
pptr(Species ~ ., data = iris)
#> 
#> Call: pptr(formula = Species ~ ., data = iris)
#> 
#> Projection-Pursuit Oblique Decision Tree:
#> If ([ 0.01 0.04 -0.04 -0.01 ] * x) < 0.06660754:
#>  If ([ 0.04 0.07 -0.09 -0.15 ] * x) < -0.2075133:
#>    Predict: virginica 
#>  Else:
#>    Predict: versicolor 
#> Else:
#>   Predict: setosa 
#> 

# Example 2: formula interface with the `iris` dataset with regularization
pptr(Species ~ ., data = iris, lambda = 0.5)
#> 
#> Call: pptr(formula = Species ~ ., data = iris, lambda = 0.5)
#> 
#> Projection-Pursuit Oblique Decision Tree:
#> If ([ 0 -0.04 0.03 0.03 ] * x) < 0.01580044:
#>   Predict: setosa 
#> Else:
#>  If ([ 0 0.03 -0.06 -0.15 ] * x) < -0.4503323:
#>    Predict: virginica 
#>  Else:
#>    Predict: versicolor 
#> 

# Example 3: matrix interface with the `iris` dataset
pptr(x = iris[, 1:4], y = iris[, 5])
#> 
#> Call: pptr(x = iris[, 1:4], y = iris[, 5])
#> 
#> Projection-Pursuit Oblique Decision Tree:
#> If ([ 0.01 0.04 -0.04 -0.01 ] * x) < 0.06660754:
#>  If ([ 0.04 0.07 -0.09 -0.15 ] * x) < -0.2075133:
#>    Predict: virginica 
#>  Else:
#>    Predict: versicolor 
#> Else:
#>   Predict: setosa 
#>