LogisticRegression

public class LogisticRegression

A Logistic regression classifier.

In the multiclass classification, the training algorithm uses the one-vs-rest (OvR) scheme.

  • The linear rate for gradient descent.

    Declaration

    Swift

    var learningRate: Float

  • The number of iterations for gradient descent.

    Declaration

    Swift

    var iterationCount: Int

  • Whether to calculate the intercept for this model.

    Declaration

    Swift

    var fitIntercept: Bool

  • The tensor of unique classes.

    Declaration

    Swift

    var classes: Tensor<Int32>

  • The tensor contains the index to unique classes.

    Declaration

    Swift

    var indices: Tensor<Int32>

  • The weights array for the model contains weights of each class agains the rest.

    Declaration

    Swift

    public var weights: <<error type>>

  • Creates a logistic regression model.

    Declaration

    Swift

    public init(
    iterationCount: Int = 1000,
    learningRate: Float = 0.1,
    fitIntercept: Bool = true
)

    Parameters

    iterationCount

    The number of iterations for gradient descent, default to 1000.
    learningRate

    The learning rate for gardient descent, default to 0.1
    fitIntercept

    Whether to calculate the intercept for this model. If set to false, no intercept will be used in calculations, default set to true.

  • Fit a logistic regression model.

    Declaration

    Swift

    public func fit(data: Tensor<Float>, labels: Tensor<Int32>)

    Parameters

    data

    Training data with shape [sample count, feature count].
    labels

    Target value with shape [sample count, 1].

  • Returns the prediction for a single sample.

    Declaration

    Swift

    public func predictSingleSample(_ data: Tensor<Float>) -> Tensor<Int32>

    Parameters

    data

    Single sample data with shape [1, feature count].

    Return Value

    Predicted class label.

  • Returns prediction using logistic regression classifier.

    Declaration

    Swift

    public func prediction(for data: Tensor<Float>) -> Tensor<Int32>

    Parameters

    data

    Smaple data with shape [sample count, feature count].

    Return Value

    Predicted class label of target values.

  • Returns mean accuracy on the given test data and labels.

    Declaration

    Swift

    public func score(data: Tensor<Float>, labels: Tensor<Int32>) -> Float

    Parameters

    data

    Sample data with shape `[sample count, feature count].
    labels

    Target label with shape [sample count, 1].

    Return Value

    Returns the mean accuracy on the given test data and labels.