LinearDiscriminantAnalysis<T>

Models & Types · AiDotNet.Classification.DiscriminantAnalysis

Linear Discriminant Analysis classifier.

Inheritance: ClassifierBase<T> → ProbabilisticClassifierBase<T> → LinearDiscriminantAnalysis<T>

Implements: IGeneratedParameterRegistrar<T>

For Beginners

Linear Discriminant Analysis (LDA) is a classification technique that:

  1. Finds the directions that best separate the classes
  2. Projects the data onto these directions
  3. Classifies based on which class region the projection falls into

Key assumptions:

  • Each class follows a Gaussian distribution
  • All classes share the same covariance matrix
  • Features are continuous

When to use LDA:

  • When classes are well-separated
  • When you have more samples than features
  • When you want a simple, interpretable classifier
  • As a dimensionality reduction technique

Trade-offs:

  • Assumes shared covariance (use QDA if classes differ)
  • Linear boundaries (may not work for complex patterns)
  • Sensitive to outliers

How It Works

LDA finds a linear combination of features that best separates classes. It projects data onto a lower-dimensional space while maximizing class separation.

Example

// Create LDA classifier for linear class separation
var options = new DiscriminantAnalysisOptions<double>();
            
// Prepare training data with two classes: 6 samples, 2 features
var features = new Matrix<double>(6, 2);
features[0, 0] = 1.0; features[0, 1] = 1.1;
features[1, 0] = 1.2; features[1, 1] = 0.9;
features[2, 0] = 0.8; features[2, 1] = 1.0;
features[3, 0] = 5.0; features[3, 1] = 5.1;
features[4, 0] = 5.2; features[4, 1] = 4.9;
features[5, 0] = 4.8; features[5, 1] = 5.0;
var labels = new Vector<double>(new double[] { 0, 0, 0, 1, 1, 1 });
            
// Train to find optimal linear projection for class separation
var result = new AiModelBuilder<double, Matrix<double>, Vector<double>>()
    .ConfigureModel(new LinearDiscriminantAnalysis<double>(options))
    .Build(features, labels);
            
// Classify new sample using discriminant function
var newSample = new Matrix<double>(1, 2);
newSample[0, 0] = 1.1; newSample[0, 1] = 1.0;
var prediction = result.Predict(newSample);
// Result is available in the returned value

Constructors

Constructor Summary
LinearDiscriminantAnalysis(DiscriminantAnalysisOptions<T> options, IRegularization<T, Matrix<T>, Vector<T>> regularization) Initializes a new instance of the LinearDiscriminantAnalysis class.

Properties

Property Summary
bool SupportsParameterInitialization { get; } LDA computes parameters from class covariance matrices during training.

Methods

Method Summary
IFullModel<T, Matrix<T>, Vector<T>> WithParameters(Vector<T> parameters)
Matrix<T> PredictLogProbabilities(Matrix<T> input)
Matrix<T> PredictProbabilities(Matrix<T> input)
ModelMetadata<T> GetModelMetadata()
Vector<T> Predict(Matrix<T> input)
void Train(Matrix<T> x, Vector<T> y) Returns the model type identifier for this classifier.