Package index • multivarious

Model construction

Functions that compute multivariate decompositions

pca(): Principal Components Analysis (PCA)

svd_wrapper(): Singular Value Decomposition (SVD) Wrapper

regress(): Multi-output linear regression

cPCAplus(): Contrastive PCA++ (cPCA++) Performs Contrastive PCA++ (cPCA++) to find directions that capture variation enriched in a "foreground" dataset relative to a "background" dataset. This implementation follows the cPCA++ approach which directly solves the generalized eigenvalue problem Rf v = lambda Rb v, where Rf and Rb are the covariance matrices of the foreground and background data, centered using the background mean.

geneig(): Generalized Eigenvalue Decomposition

Model classes for multivariate decompositions and extension

Generic S3 classes use to represented multivariate model fits

projector(): Construct a projector instance

bi_projector(): Construct a bi_projector instance

bi_projector_union(): A Union of Concatenated bi_projector Fits

discriminant_projector(): Construct a Discriminant Projector

cross_projector(): Two-way (cross) projection to latent components

multiblock_biprojector(): Create a Multiblock Bi-Projector

multiblock_projector(): Create a Multiblock Projector

Model Fitting and Projections

Functions for fitting models and applying projections.

project(): New sample projection

residualize(): Compute a regression model for each column in a matrix and return residual matrix

partial_project(): Partially project a new sample onto subspace

partial_projector(): Construct a partial projector

project_block(): Project a single "block" of data onto the subspace

project_vars(): Project one or more variables onto a subspace

transpose(): Transpose a model

reconstruct(): Reconstruct the data

inverse_projection(): Inverse of the Component Matrix

partial_inverse_projection(): Partial Inverse Projection of a Columnwise Subset of Component Matrix

compose_projector(): Compose Two Projectors

compose_partial_projector() `%>>%`: Compose Multiple Partial Projectors

refit(): refit a model

nystrom_approx(): Nyström approximation for kernel-based decomposition (Unified Version)

fit(): Fit a preprocessing pipeline

fit_transform(): Fit and transform data in one step

transform(): Transform data using a fitted preprocessing pipeline

inverse_transform(): Inverse transform data using a fitted preprocessing pipeline

Cross Projection

Functions for creating and working with cross_projectors for two-way projection between two sets of variables or features.

project(<cross_projector>): project a cross_projector instance

coef(<cross_projector>): Extract coefficients from a cross_projector object

reprocess(<cross_projector>): reprocess a cross_projector instance

shape(<cross_projector>): shape of a cross_projector instance

transfer(): Transfer data from one domain/block to another via a latent space

inverse_projection(<cross_projector>): Default inverse_projection method for cross_projector

partial_inverse_projection(<cross_projector>): Partial Inverse Projection of a Subset of the Loading Matrix in cross_projector

partial_project(<cross_projector>): Partially project data for a cross_projector

Model Components and Properties

Functions for working with model components and properties.

components(): get the components

scores(): Retrieve the component scores

std_scores(): Compute standardized component scores

sdev(): standard deviations

ncomp(): Get the number of components

shape(): Shape of the Projector

is_orthogonal(): is it orthogonal

truncate(): truncate a component fit

block_lengths(): get block_lengths

block_indices(): get block_indices

nblocks(): get the number of blocks

prinang(): Calculate Principal Angles Between Subspaces

principal_angles(): Principal angles (two sub‑spaces)

variables_used(): Identify Original Variables Used by a Projector

vars_for_component(): Identify Original Variables for a Specific Component

Rotation and Transformation

Functions for rotating and transforming model components.

rotate(): Rotate a Component Solution

apply_rotation(): Apply rotation

Resampling and Confidence Intervals

Functions for bootstrapping and estimating confidence intervals.

bootstrap(): Bootstrap Resampling for Multivariate Models

bootstrap_pca(): Fast, Exact Bootstrap for PCA Results from pca function

perm_ci(): Permutation Confidence Intervals

perm_test perm_test.pca perm_test.cross_projector perm_test.discriminant_projector perm_test.multiblock_biprojector: Generic Permutation-Based Test

cv(): Cross-validation Framework

cv_generic(): Generic cross-validation engine

Classifier Construction

Functions for constructing classifiers.

classifier(): Construct a Classifier

classifier(<discriminant_projector>): Create a k-NN classifier for a discriminant projector

classifier(<multiblock_biprojector>): Multiblock Bi-Projector Classifier

classifier(<projector>): create classifier from a projector

rf_classifier(): construct a random forest wrapper classifier

rf_classifier(<projector>): Create a random forest classifier

predict(<classifier>): Predict Class Labels using a Classifier Object

feature_importance(): Evaluate feature importance

feature_importance(<classifier>): Evaluate Feature Importance for a Classifier

Model Diagnostics and Residuals

Functions for evaluating model fit and residuals.

residuals(): Obtain residuals of a component model fit

measure_reconstruction_error(): Compute reconstruction-based error metrics

measure_interblock_transfer_error(): Compute inter-block transfer error metrics for a cross_projector

pca_outliers(): PCA Outlier Diagnostics

rank_score(): Calculate Rank Score for Predictions

subspace_similarity(): Compute subspace similarity

Pre-processing

Functions for pre-processing data and managing pipelines.

center(): center a data matrix

pass(): a no-op pre-processing step

standardize(): center and scale each vector of a matrix

colscale(): scale a data matrix

prep(): prepare a dataset by applying a pre-processing pipeline

fresh(): Get a fresh pre-processing node cleared of any cached data

reprocess(): apply pre-processing parameters to a new data matrix

apply_transform(): apply a pre-processing transform

reverse_transform(): reverse a pre-processing transform

init_transform(): initialize a transform

concat_pre_processors(): bind together blockwise pre-processors

add_node(): add a pre-processing stage

preprocess(): Convenience function for preprocessing workflow

check_fitted(): Check if preprocessor is fitted and error if not

is_fitted(): Check if a preprocessing object is fitted

mark_fitted(): Enhanced fitted state tracking

get_fitted_state(): Get fitted state from attributes

Visualization

Functions for plotting and visualization.

biplot(<pca>): Biplot for PCA Objects (Enhanced with ggrepel)

screeplot(): Screeplot for PCA

screeplot(<pca>): Screeplot for PCA

Utilities

Utility functions.

group_means(): Compute column-wise mean in X for each factor level of Y

robust_inv_vTv(): Possibly use ridge-regularized inversion of crossprod(v)

topk(): top-k accuracy indicator

reconstruct_new(): Reconstruct new data in a model's subspace

Other

Other functions

print(<bi_projector>): Pretty Print S3 Method for bi_projector Class

print(<classifier>): Pretty Print Method for classifier Objects

print(<concat_pre_processor>): Print a concat_pre_processor object

print(<multiblock_biprojector>): Pretty Print Method for multiblock_biprojector Objects

print(<pca>): Print Method for PCA Objects

print(<perm_test>): Print Method for perm_test Objects

print(<perm_test_pca>): Print Method for perm_test_pca Objects

print(<pre_processor>): Print a pre_processor object

print(<prepper>): Print a prepper pipeline

print(<regress>): Pretty Print Method for regress Objects

print(<rf_classifier>): Pretty Print Method for rf_classifier Objects

summary(<composed_projector>): Summarize a Composed Projector

coef(<composed_projector>): Get Coefficients of a Composed Projector

coef(<cross_projector>): Extract coefficients from a cross_projector object

coef(<multiblock_projector>): Coefficients for a Multiblock Projector

predict(<classifier>): Predict Class Labels using a Classifier Object

predict(<discriminant_projector>): Predict method for a discriminant_projector, supporting LDA or Euclid

predict(<rf_classifier>): Predict Class Labels using a Random Forest Classifier Object

reprocess(): apply pre-processing parameters to a new data matrix

reprocess(<cross_projector>): reprocess a cross_projector instance

reprocess(<nystrom_approx>): Reprocess data for Nyström approximation

project(): New sample projection

project(<cross_projector>): project a cross_projector instance

project(<nystrom_approx>): Project new data using a Nyström approximation model

project_block(): Project a single "block" of data onto the subspace

project_block(<multiblock_projector>): Project Data onto a Specific Block

project_vars(): Project one or more variables onto a subspace

projector(): Construct a projector instance

truncate(): truncate a component fit

truncate(<composed_projector>): Truncate a Composed Projector

block_indices(): get block_indices

block_indices(<multiblock_projector>): Extract the Block Indices from a Multiblock Projector

inverse_projection(): Inverse of the Component Matrix

inverse_projection(<composed_projector>): Compute the Inverse Projection for a Composed Projector

inverse_projection(<cross_projector>): Default inverse_projection method for cross_projector

partial_inverse_projection(): Partial Inverse Projection of a Columnwise Subset of Component Matrix

partial_inverse_projection(<cross_projector>): Partial Inverse Projection of a Subset of the Loading Matrix in cross_projector

partial_inverse_projection(<regress>): Partial Inverse Projection for a regress Object

partial_project(): Partially project a new sample onto subspace

partial_project(<composed_partial_projector>): Partial Project Through a Composed Partial Projector

partial_project(<cross_projector>): Partially project data for a cross_projector

partial_projector(): Construct a partial projector

reconstruct(): Reconstruct the data

reconstruct(<composed_projector>): Reconstruct Data from Scores using a Composed Projector

reconstruct(<pca>): Reconstruct Data from PCA Results

reconstruct_new(): Reconstruct new data in a model's subspace

rotate(): Rotate a Component Solution

rotate(<pca>): Rotate PCA Loadings

std_scores(): Compute standardized component scores

std_scores(<svd>): Calculate Standardized Scores for SVD results

is_orthogonal(): is it orthogonal

is_orthogonal(<projector>): Stricter check for true orthogonality

add_node(): add a pre-processing stage

add_node(<prepper>): Add a pre-processing node to a pipeline

shape(): Shape of the Projector

shape(<cross_projector>): shape of a cross_projector instance

transfer(): Transfer data from one domain/block to another via a latent space

transfer(<cross_projector>): Transfer from X domain to Y domain (or vice versa) in a cross_projector