API Reference - Models - SupportVectorMachine

SupportVectorMachine is a supervised machine learning model that predicts values of -1 and 1 only.

Stored Model Parameters

Contains a matrix.

  • ModelParameters[I][J]: Value of matrix at row I and column J. The rows represent the features.

Constructors

new()

Create new model object. If any of the arguments are nil, default argument values for that argument will be used.

SupportVectorMachine.new(maximumNumberOfIterations: integer, cValue: number, kernelFunction: string, kernelParameters: table): ModelObject

Parameters:

  • maximumNumberOfIterations: How many times should the model needed to be trained.

  • cValue: How strict should the model can classify the data correctly. Higher the cValue, the closer the data points to the decision boundary.

  • kernelFunction: The kernel function to be used to train the model. Available options are:

    • Linear

    • Polynomial

    • RadialBasisFunction

    • Sigmoid

    • Cosine

Returns:

  • ModelObject: The generated model object.

Functions

setCValue()

Set how hard the margin should be.

SupportVectorMachine:setCValue(cValue: number)

Parameters:

  • cValue: The value of c to be used.

setSolver()

Set a solver for the model by inputting the optimizer object.

SupportVectorMachine:setSolver(Solver: SolverObject)

Parameters:

  • Solver: The solver to be used.

train()

Train the model.

SupportVectorMachine:train(featureMatrix: Matrix, labelVector: Matrix): number[]

Parameters:

  • featureMatrix: Matrix containing all data.

  • labelVector: A (n x 1) matrix containing values related to featureMatrix.

Returns:

  • costArray: An array containing cost values.

predict()

Predict the values for given data.

SupportVectorMachine:predict(featureMatrix: Matrix, returnOriginalOutput: boolean): matrix -OR- matrix

Parameters:

  • featureMatrix: Matrix containing all data.

Returns:

  • predictedVector: A vector that is predicted by the model.

-OR-

  • originalPredictedVector: A vector that contains the original predicted values.

Inherited From

References


This site uses Just the Docs, a documentation theme for Jekyll.