Description Usage Arguments Value
This function computes a single canonical correlation tree given its input values.
1 2 3 | canonical_correlation_tree(X, Y, depth = 0, minPointsForSplit = 2,
maxDepthSplit = Inf, xVariationTolerance = 1e-10,
projectionBootstrap = FALSE, ancestralProbs = NULL)
|
X |
Predictor matrix of size n \times p with n observations and p variables. |
Y |
Predicted values as a matrix of size n \times p with n observations and p variables. |
depth |
Depth of subtree. |
minPointsForSplit |
Optional parameter setting the threshold when to construct a leaf (default: 2). If the number of data points is smaller than this value, a leaf is constructed. |
maxDepthSplit |
Optional parameter controlling the construction of leaves after a
certain depth (default: |
xVariationTolerance |
Features with variance less than this value are not considered
for splitting at tree nodes. (default |
projectionBootstrap |
Use projection bootstrapping. (default |
ancestralProbs |
Probabilities of ancestors. Default is |
Function returns an object of class canonical_correlation_tree
,
where the object is a list containing at the following components:
isLeafBoolean whether the tree is a leaf itself.
trainingCountsNumber of training examples for constructing this tree (i.e.
number of rows in input argument X
).
indicesFeaturesFeature indices which the node received, as needed for prediction.
decisionProjectionNumeric matrix containing the projection matrix that was used to find the best split point.
refLeftChildReference to the left subtree.
refRightChildReference to the right subtree.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.