README
¶
variance 
Go implementation of Welford's method for one-pass variance computation with D. H. D. West improved methods.
Install
go get github.com/axiomhq/variance
Usage
package main
import (
"fmt"
"github.com/axiomhq/variance"
)
func main() {
stats := variance.New()
stats.Add(1)
stats.Add(1)
stats.Add(1)
stats.Add(0)
stats.Add(0)
stats.Add(0)
fmt.Println(
stats.Mean(),
stats.Variance(),
stats.StandardDeviation(),
stats.VariancePopulation(),
stats.StandardDeviationPopulation(),
stats.NumDataValues(),
)
}
For more examples, check out the example or run it on pkg.go.dev.
Features
- One-pass variance computation
- Merging of multiple sets of statistics
- Support for weighted values
- Stable and accurate computation using D. H. D. West's improved method
Reference
A method of improved efficiency is given for updating the mean and variance of weighted sampled data when an additional data value is included in the set. Evidence is presented that the method is stable and at least as accurate as the best existing updating method.
-- Updating mean and variance estimates: an improved method - D. H. D. West
License
Documentation
¶
Overview ¶
Example ¶
package main
import (
"fmt"
"github.com/axiomhq/variance"
)
func main() {
stats1 := variance.New()
stats1.Add(1)
stats1.Add(1)
stats1.Add(1)
stats1.Add(0)
stats1.Add(0)
stats1.Add(0)
fmt.Println(
stats1.Mean(),
stats1.Variance(),
stats1.StandardDeviation(),
stats1.VariancePopulation(),
stats1.StandardDeviationPopulation(),
stats1.NumDataValues(),
)
stats2 := variance.New()
stats2.Add(3)
// Merge the values of stats2 into stats1.
stats1.Merge(stats2)
// Reset the values in stats2.
stats2.Clear()
}
Output: 0.5 0.3 0.5477225575051661 0.25 0.5 6
Index ¶
- type Stats
- func (sts *Stats) Add(x float64)
- func (sts *Stats) AddWeighted(val, weight float64)
- func (sts *Stats) Clear()
- func (sts *Stats) Clone() *Stats
- func (sts *Stats) Mean() float64
- func (sts *Stats) Merge(other *Stats)
- func (sts *Stats) NumDataValues() uint
- func (sts *Stats) ReadFrom(r io.Reader) (int64, error)
- func (sts *Stats) StandardDeviation() float64
- func (sts *Stats) StandardDeviationPopulation() float64
- func (sts *Stats) Variance() float64
- func (sts *Stats) VariancePopulation() float64
- func (sts *Stats) WriteTo(w io.Writer) (int64, error)
Examples ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type Stats ¶
type Stats struct {
// contains filtered or unexported fields
}
Stats of welford's algorithm for computing the mean and variance.
func New ¶
func New() *Stats
New returns new Welford's algorithm stats. The stats are initialized to their respective zero values.
func (*Stats) AddWeighted ¶
AddWeighted adds a new weighted value to the stats.
func (*Stats) NumDataValues ¶
NumDataValues returns the number of data values in the stats.
func (*Stats) StandardDeviation ¶
StandardDeviation returns the standard deviation of the data, which is the square root of the variance.
func (*Stats) StandardDeviationPopulation ¶
StandardDeviationPopulation returns the standard deviation of the data, which is the square root of the variance of the sampled data.
func (*Stats) Variance ¶
Variance returns the variance of the data, assuming the data added was sampled.
func (*Stats) VariancePopulation ¶
VariancePopulation returns the variance of the data, assuming the data added was not sampled.
Source Files