eval

package
v0.0.0-...-14a59ba Latest Latest
Warning

This package is not in the latest version of its module.

Go to latest
Published: Oct 27, 2017 License: MIT Imports: 3 Imported by: 0

Documentation

Index

Constants

This section is empty.

Variables

This section is empty.

Functions

func AUC

func AUC(predictions0 []*LabelPrediction) float64

func BalanceErrorRate

func BalanceErrorRate(predictions []*LabelPrediction, ssr float64) float64

BalanceErrorRate considers the real ratio between positive and negative samples. Sample labels should be marked 1 for positive samples and 0 for negative. The ssr is sub-sample rate (0,1]. If no sub-sample applied on sample set, ssr should be set as 1. Sub-sample is on negative samples.

func ErrorRate

func ErrorRate(predictions []*LabelPrediction) float64

func RMSE

func RMSE(predictions []*LabelPrediction) float64

func RegRMSE

func RegRMSE(predictions []*RealPrediction) float64

Types

type By

type By func(p1, p2 *LabelPrediction) bool

func (By) Sort

func (by By) Sort(predictions []*LabelPrediction)

type LabelPrediction

type LabelPrediction struct {
	Prediction float64
	Label      int
}

type RealPrediction

type RealPrediction struct {
	Prediction float64
	Value      float64
}

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL