reflect_feature_space: reflect_feature_space

In hhcartr: HHCART(G) - A Reflected Feature Space for CART

Description

This function is in an internal only function. It applies the householder transformation to the feature data.

Usage

reflect_feature_space(
  X_matrix,
  X,
  y,
  most_freq_class,
  n_classes,
  max_features,
  n_features,
  depth,
  colx
)

Arguments

X_matrix	The current node to be tested for a split.
X	The feature variables of the current node being processed.
y	The target variable for the corresponding feature variables.
most_freq_class	The most frequently occurring class at the current node.
n_classes	The number of classes in the target variable.
max_features	The maximum number of features to consider in the current split.
n_features	The number of feature variables.
depth	The depth of the current tree.
colx	The eigenvector column to use.

Details

The following parameters are supported:

Value

Returns idxA, thrA, gidxA, X_houseA, newH_A if split is on reflected data, otherwise a list containing idx, thr, X, NULL, FALSE is returned when the split is made using the original data when the first eigen vector equals the first column of the identity matrix.

hhcartr documentation built on July 2, 2021, 9:06 a.m.