partial_project.cross_projector

Projects new data from either the X or Y domain onto the latent subspace,
considering only a specified subset of original features (<code>colind</code>).

Provides a set of basic and extensible data structures and functions for multivariate analysis, including dimensionality reduction techniques, projection methods, and preprocessing functions. The aim of this package is to offer a flexible and user-friendly framework for multivariate analysis that can be easily extended for custom requirements and specific data analysis tasks.

Bradley Buchsbaum

multivarious

Extensible Data Structures for Multivariate Analysis

partial_project.cross_projector function

<dl><dt>x</dt>
<dd>A <code>cross_projector</code> object.</dd>
<dt>new_data</dt>
<dd>A numeric matrix (n x length(colind)) or vector, representing
the observations corresponding to the columns specified by <code>colind</code>.</dd>
<dt>colind</dt>
<dd>A numeric vector of column indices in the original data space
(either X or Y domain, specified by <code>source</code>) that correspond to <code>new_data</code>'s columns.</dd>
<dt>least_squares</dt>
<dd>Logical; if TRUE (default), use ridge-regularized least squares for projection.</dd>
<dt>lambda</dt>
<dd>Numeric; ridge penalty (default 1e-6). Ignored if <code>least_squares=FALSE</code>.</dd>
<dt>source</dt>
<dd>Character, either "X" or "Y", indicating which domain <code>new_data</code> and <code>colind</code> belong to.</dd>
<dt>...</dt>
<dd>Additional arguments (currently ignored).</dd></dl>

Arguments

Partially project data for a cross_projector — partial_project.cross_projector

<dl>

<dt>x</dt>
<dd>A <code>cross_projector</code> object.</dd>


<dt>new_data</dt>
<dd>A numeric matrix (n x length(colind)) or vector, representing
the observations corresponding to the columns specified by <code>colind</code>.</dd>


<dt>colind</dt>
<dd>A numeric vector of column indices in the original data space
(either X or Y domain, specified by <code>source</code>) that correspond to <code>new_data</code>'s columns.</dd>


<dt>least_squares</dt>
<dd>Logical; if TRUE (default), use ridge-regularized least squares for projection.</dd>


<dt>lambda</dt>
<dd>Numeric; ridge penalty (default 1e-6). Ignored if <code>least_squares=FALSE</code>.</dd>


<dt>source</dt>
<dd>Character, either "X" or "Y", indicating which domain <code>new_data</code> and <code>colind</code> belong to.</dd>


<dt>...</dt>
<dd>Additional arguments (currently ignored).</dd>

</dl>

partial_project.cross_projector: Partially project data for a cross_projector

Description

Usage

Value

Arguments