API Reference

Current

Table of the package models and corresponding function names used by these models.

Function \ Model	CCA	WHT	ICA	LDA	FA	PPCA	PCA	KPCA	MDS
fit	x	x	x	x	x	x	x	x	x
transform	x	x	x	x	x	x	x	x	x
predict				x
indim		x	x	x	x	x	x	x	x
outdim	x	x	x	x	x	x	x	x	x
mean	x	x	x	x	x	x	x	?
var					x	x	?	?	?
cov					x	?
cor	x
projection	x				x	x	x	x	x
reconstruct					x	x	x	x
loadings	?			?	x	x	?	?	?
eigvals					?	?	?	?	x
eigvecs					?	?	?	?	?
length
size

Note: ? refers to a possible implementation that is missing or called differently.

New

Function \ Model	WHT	CCA	LDA	MC-LDA	SS-LDA	ICA	FA	PPCA	PCA	KPCA	MDS
fit	x	x	x	x	x	x	x	x	x	x	x
transform	x	-	-	-	-	-	x	x	-	-	-
predict		+	x	+	+	+			+	+	+
indim	-			-	-	-	x	x	-	-	-
outdim	-	-		-	-	-	x	x	-	-	-
mean	x	x		x	x	x	x	x	x
var							x	x	x		?
cov							x	x
cor		+
projection	?	x		x	x		x	x	x	x	x
reconstruct							x	x	x	x
loadings							x	x	x		+
eigvals					+		?	?	x	x	x
eigvecs							?	?	x	+	+
length	+		+	+	+
size	+	+		+	+	+			x	+	+

StatsBase.AbstractDataTransform
- Whitening
  - Interface: fit, transform
  - New: length, mean, size
StatsBase.RegressionModel
- Interface: fit, predict
- LinearDiscriminant
  - Functions: coef, dof, weights, evaluate, length
- MulticlassLDA
  - Functions: size, mean, projection, length
- SubspaceLDA
  - Functions: size, mean, projection, length, eigvals
- CCA
  - Functions: size, mean, projection, predict, cor
- Subtypes:
  - AbstractDimensionalityReduction
    - Interface: projection, var, reconstruct, loadings
    - Interface: projection == weights
  - Subtypes:
    - LinearDimensionalityReduction
      - Methods: ICA, PCA
    - NonlinearDimensionalityReduction
      - Methods: KPCA, MDS
        Functions: modelmatrix(X),
    - LatentVariableModel or LatentVariableDimensionalityReduction
      - Methods: FA, PPCA
        Functions: cov

Generic Interface

The models above share a type hierarchy, and the following methods are defined generically on its abstract types.

Base.size — Method

size(model::AbstractDimensionalityReduction, d::Int)

Returns the dimension of the input data if d == 1, the dimension of the output data if d == 2, otherwise throws error.

source

MultivariateStats.projection — Method

projection(model::AbstractDimensionalityReduction)

Return the projection matrix of the model.

source

MultivariateStats.reconstruct — Method

reconstruct(model::AbstractDimensionalityReduction, y)

Return the model response (a.k.a. the dependent variable).

source

MultivariateStats.loadings — Method

loadings(model::LinearDimensionalityReduction)

Return the model loadings (a.k.a. eigenvectors scaled up by the variances).

source

Internals

These are not part of the public API and may change without a breaking release.

MultivariateStats.calcscattermat — Method

calcscattermat([covestimator::CovarianceEstimator], Z::DenseMatrix)

Calculate the scatter matrix of centered data Z based on a covariance matrix calculated using covariance estimator covestimator (by default, SimpleCovariance()).

source

MultivariateStats.toindices — Method

toindices(labels::AbstractVector)

Generate integer indices for the collection labels. Generated indices will be in 1:nc range where nc is a number of classes in the labels collection.

source

MultivariateStats.L2distance — Method

L2distance(X)

Calculate a symmetric Euclidean (L2) distance matrix.

source