treelet (version 0.3-0)

Build_JTree: Builds a hierarchical/wavelet tree of 2-by-2 Jacobi rotations

Description

Builds a hierarchical binary tree using the covariance structure of the inputs. Decorrelates groups of two with PCA .

Usage

Build_JTree(C, cc, maxlevel)

Arguments

C

input covariance matrix

cc

correlation coeffs

maxlevel

default: dim-1 (levels L=0,1,2,...,maxlevel)

Value

• Zpos
  Zpos[dim-1,2] positions of the two clusters merged; number between 1 and d (the length of the comp vector)
• PCidx
  ID of principal components; [1 2] or [2 1]
• T
  Element T{k} in the list array contains a 2-by-2 rot matrix
• all_nodes
  node labels
• theta
  rotation angles that decorrelates inputs X(:,Z(k,1)) and X(:,Z(k,2))
• Z
  contain the indices of clusters that are merged
• all_d
  labels of the d-components in the comp vector (=0 if s-component, otherwise 1,...,d-1)
• C
  updated covariance matrix
• cc
  updated coefficients