FloatPCA Class

Class FloatPCA performs a principal component analysis on a given single-precision data matrix.

Inheritance Hierarchy

SystemObject
CenterSpace.NMath.CoreFloatPCA

Namespace: CenterSpace.NMath.Core
Assembly: NMath (in NMath.dll) Version: 7.4

Syntax

C++

Copy

[SerializableAttribute]
public class FloatPCA : ICloneable

<SerializableAttribute>
Public Class FloatPCA
	Implements ICloneable

[SerializableAttribute]
public ref class FloatPCA : ICloneable

[<SerializableAttribute>]
type FloatPCA = 
    class
        interface ICloneable
    end

The FloatPCA type exposes the following members.

Constructors

	Name	Description
	FloatPCA(FloatMatrix)	Constructs a FloatPCA instance from the given data.
	FloatPCA(FloatMatrix, Boolean, Boolean)	Constructs a FloatPCA instance from the given data, optionally centering and scaling the data before analysis takes place.

Top

Properties

	Name	Description
	CumulativeVarianceProportions	Gets the cumulative variance proportions.
	Data	Gets the data matrix.
	Eigenvalues	Gets the eigenvalues of the covariance/correlation matrix, though the calculation is actually performed using the singular values of the data matrix.
	IsCentered	Returns true if the data supplied at construction time was shifted to be zero-centered.
	IsScaled	Returns true if the data supplied at construction time was scaled to have unit variance.
	Item	Gets the specified principal component.
	Loadings	Gets the loading matrix. Each column is a principal component.
	Means	Gets the column means of the data matrix.
	Norms	Gets the column norms (1-norm).
	NumberOfObservations	Gets the number of observations in the data matrix.
	NumberOfVariables	Gets the number of variables in the data matrix.
	Scores	Gets the score matrix.
	StandardDeviations	Gets the standard deviations of the principal components.
	VarianceProportions	Gets the proportion of the total variance accounted for by each principal component.

Top

Methods

	Name	Description
	Clone	Creates a deep copy of this principal component analysis.
	Threshold	Gets the number of principal components required to account for the given proportion of the total variance.

Top

Fields

	Name	Description
	center_	If true, the data supplied at construction time will be shifted to be zero-centered.
	d_	Eigenvalues.
	means_	Column means. Used for centering.
	norms_	Column 1-norms. Used for scaling.
	scale_	If true, the data supplied at construction time will be scaled to have unit variance.
	scores_	Scores matrix.
	v_	Right eigenvectors.
	x_	The data matrix.

Top

Remarks

The first principal component accounts for as much of the variability in the data as possible, and each succeeding component accounts for as much of the remaining variability as possible.
The calculation is performed using a singular value decomposition of the data matrix. The data may optionally be centered and scaled before analysis takes place.

Reference

CenterSpace.NMath.Core Namespace