Moodle PHP Documentation 4.3
Moodle 4.3.5 (Build: 20240610) (7dcfaa79f78)
Phpml\DimensionReduction\LDA Class Reference
Inheritance diagram for Phpml\DimensionReduction\LDA:
Phpml\DimensionReduction\EigenTransformerBase

Public Member Functions

 __construct (?float $totalVariance=null, ?int $numFeatures=null)
 Linear Discriminant Analysis (LDA) is used to reduce the dimensionality of the data.
 
 fit (array $data, array $classes)
 Trains the algorithm to transform the given data to a lower dimensional space.
 
 transform (array $sample)
 Transforms the given sample to a lower dimensional vector by using the eigenVectors obtained in the last run of fit.
 

Public Attributes

array $counts = []
 
bool $fit = false
 
array $labels = []
 
array $means = []
 
int $numFeatures = null
 Number of features to be preserved after the reduction.
 
float[] $overallMean = []
 
float $totalVariance = 0.9
 Total variance to be conserved after the reduction.
 

Protected Member Functions

 calculateClassCov ()
 Returns between-class scatter matrix for each class, which is an n by m matrix where n is number of classes and m is number of columns.
 
 calculateClassVar (array $data, array $classes)
 Returns in-class scatter matrix for each class, which is a n by m matrix where n is number of classes and m is number of columns.
 
 calculateMeans (array $data, array $classes)
 Calculates mean of each column for each class and returns n by m matrix where n is number of labels and m is number of columns.
 
 calculateVar (array $row, array $means)
 Returns the result of the calculation (x - m)T.
 
 eigenDecomposition (array $matrix)
 Calculates eigenValues and eigenVectors of the given matrix.
 
 getLabels (array $classes)
 Returns unique labels in the dataset.
 
 reduce (array $data)
 Returns the reduced data.
 

Protected Attributes

array $eigValues = []
 Top eigenValues of the matrix.
 
array $eigVectors = []
 Top eigenvectors of the matrix.
 

Constructor & Destructor Documentation

◆ __construct()

Phpml\DimensionReduction\LDA::__construct ( ?float $totalVariance = null,
?int $numFeatures = null )

Linear Discriminant Analysis (LDA) is used to reduce the dimensionality of the data.

Unlike Principal Component Analysis (PCA), it is a supervised technique that requires the class labels in order to fit the data to a lower dimensional space.

The algorithm can be initialized by speciyfing either with the totalVariance(a value between 0.1 and 0.99) or numFeatures (number of features in the dataset) to be preserved.

Parameters
float | null$totalVarianceTotal explained variance to be preserved
int | null$numFeaturesNumber of features to be preserved
Exceptions
InvalidArgumentException

Member Function Documentation

◆ calculateVar()

Phpml\DimensionReduction\LDA::calculateVar ( array $row,
array $means )
protected

Returns the result of the calculation (x - m)T.

(x - m)

◆ eigenDecomposition()

Phpml\DimensionReduction\EigenTransformerBase::eigenDecomposition ( array $matrix)
protectedinherited

Calculates eigenValues and eigenVectors of the given matrix.

Returns top eigenVectors along with the largest eigenValues. The total explained variance of these eigenVectors will be no less than desired $totalVariance value

◆ transform()

Phpml\DimensionReduction\LDA::transform ( array $sample)

Transforms the given sample to a lower dimensional vector by using the eigenVectors obtained in the last run of fit.

Exceptions
InvalidOperationException

The documentation for this class was generated from the following file: