Construct the projection pursuit classification tree extensions
TreeExt.construct(origclass, origdata, Tree.Struct, id, rep, rep1, rep2,
projbest.node, splitCutoff.node, PPmethod,
lambda = NULL, q = 1, weight = TRUE, srule=TRUE, tot=NULL, tol = .5,...)A list containing the complete tree structure and node information:
A matrix where each row represents a node in the projection pursuit classification tree. The matrix has 5 columns:
Column 1: Node ID
Column 2: ID of the left child node (or 0 if terminal node)
Column 3: ID of the right child node, or the predicted class label if terminal node
Column 4: Projection index (which projection vector is used at this node)
Column 5: Optimization criterion value for the projection at this node
A matrix where each row contains the optimal projection coefficients (Alpha vector) for each split node.
A matrix/vector containing the optimal cutpoint values used at each split node.
Integer counter tracking the current node being processed (internal use).
Integer counter for assigning child node IDs (internal use).
Integer counter for tracking projection indices (internal use).
factor or numeric vector containing the class labels for each observation.
data frame with the original data without class variable
tree structure of projection pursuit classification tree
tree node id
internal counter for nodes
internal counter for nodes
internal counter for nodes
bests projection node
cutof node
method for projection pursuit; "LDA", "PDA"
lambda in PDA index
numeric value with dimension of the projected data, if it is 1 then 1D projection is used
weight flag in LDA, PDA
stopping rule flag; if TRUE use stopping rule, if FALSE stop only for pure or empty nodes
total number of observations
tolerance value for entropy stopping rule for splitting a node
additional arguments to pass trough
Find tree structure using various projection pursuit indices of classification in each split.
This function recursively constructs a binary classification tree using projection pursuit. At each node, it finds the optimal projection direction that best separates classes, determines a cutpoint, and creates child nodes until stopping criteria are met (pure nodes, small node size, or low entropy).