linreg

Documentation

Index

• func ComputeCost(X, y, theta *mat.Dense) float64
• func GradientDescent(X, y, theta *mat.Dense, alpha float64, iters int) (*mat.Dense, [][]float64, []float64)
• func InitParameters(data mat.Matrix) (X, y, theta *mat.Dense)
• func NormalizeFeatures(X *mat.Dense) (means, stdDevs *mat.Dense)

Functions

func ComputeCost

func ComputeCost(X, y, theta *mat.Dense) float64

ComputeCost computes the cost of using theta as the parameter for linear regression to fit the data points in X and y.

func GradientDescent

func GradientDescent(X, y, theta *mat.Dense, alpha float64, iters int) (*mat.Dense, [][]float64, []float64)

GradientDescent performs gradient descent to learn theta returns the updated theta after taking iters gradient steps with learning rate alpha.

func InitParameters

func InitParameters(data mat.Matrix) (X, y, theta *mat.Dense)

InitParameters returns the X, y and theta parameters extracted from the given data matrix. It uses the last column for y, the rest for X, and zeros for theta.

func NormalizeFeatures

func NormalizeFeatures(X *mat.Dense) (means, stdDevs *mat.Dense)

NormalizeFeatures normalizes the given matrix of features and returns the matrix of means and standard deviations.