split_node {IntegratedMRF}

Splitting Criteria of all the nodes of the tree

Description

Stores the Splitting criteria of all the nodes of a tree in a list

Usage

split_node(X, Y, m_feature, Index, i, model, min_leaf, Inv_Cov_Y, Command)

Arguments

X

Input Training matrix of size M x N, M is the number of training samples and N is the number of features

Y

Output Training response of size M x T, M is the number of samples and T is the number of output responses

m_feature

Number of randomly selected features considered for a split in each regression tree node

Index

Index of training samples

i

Number of split. Used as an index, which indicates where in the list the splitting criteria of this split will be stored.

model

A list of lists with the spliting criteria of all the node splits. In each iteration, a new list is included with the spliting criteria of the new split of a node.

min_leaf

Minimum number of samples in the leaf node. If a node has less than or, equal to min_leaf samples, then there will be no splitting in that node and the node is a leaf node. Valid input is a positive integer and less than or equal to M (number of training samples)

Inv_Cov_Y

Inverse of Covariance matrix of Output Response matrix for MRF (Input [0 0; 0 0] for RF)

Command

1 for univariate Regression Tree (corresponding to RF) and 2 for Multivariate Regression Tree (corresponding to MRF)

Details

This function calculates the splitting criteria of a node and stores the information in a list format. If the node is a parent node, then indices of left and right nodes and feature number and threshold value of the feature for the split are stored. If the node is a leaf, the output feature matrix of the samples for the node are stored as a list.

Value

model: A list of lists with the splitting criteria of all the split of the nodes. In each iteration, the Model is updated with a new list that includes the splitting criteria of the new split of a node.