| Copyright | (c) Fabricio Olivetti de Franca 2022 |
|---|---|
| License | GPL-3 |
| Maintainer | fabricio.olivetti@gmail.com |
| Stability | experimental |
| Portability | POSIX |
| Safe Haskell | Safe-Inferred |
MachineLearning.Model.Regression
Description
Fitting functions for the coefficients.
Synopsis
- fitTask :: Task -> TIR -> Dataset Double -> Vector Double -> [Vector Double]
- predictTask :: Task -> [Vector Double] -> Vector Double
- evalPenalty :: Penalty -> Int -> Double -> Double
- applyMeasures :: [Measure] -> Vector Double -> Vector Double -> [Double]
- nonlinearFit :: Int -> Matrix Double -> Matrix Double -> Vector Double -> (Vector Double -> Vector Double) -> (Vector Double -> Vector Double) -> Vector Double -> Vector Double
- tirToMatrix :: Dataset Double -> TIR -> (Matrix Double, Matrix Double)
Documentation
fitTask :: Task -> TIR -> Dataset Double -> Vector Double -> [Vector Double] Source #
chooses the appropriate fitting function fitTask :: Task -> Matrix Double -> Vector Double -> [Vector Double]
predictTask :: Task -> [Vector Double] -> Vector Double Source #
chooses the appropriate prediction function
evalPenalty :: Penalty -> Int -> Double -> Double Source #
evals the penalty function
applyMeasures :: [Measure] -> Vector Double -> Vector Double -> [Double] Source #
applies a list of performance measures
nonlinearFit :: Int -> Matrix Double -> Matrix Double -> Vector Double -> (Vector Double -> Vector Double) -> (Vector Double -> Vector Double) -> Vector Double -> Vector Double Source #
Non-linear optimization using Levenberg-Marquardt method. nonlinearFit :: Monad m => Vector Double -> Matrix Double -> Matrix Double -> Vector Double -> m (Vector Double)
tirToMatrix :: Dataset Double -> TIR -> (Matrix Double, Matrix Double) Source #
transform a data matrix using a TIR expression. This function returns a tuple with the transformed data of the numerator and denominator, respectivelly. Each column of the transformed data represents one term of the TIR expression.