Kernel density estimation is a non-parametric test method. It is used to estimate unkonwn density functions in probability theory.

Kernel density estimation functions use a smooth peak function to simulate the real probability distribution curve by fitting the observed data points.
  • Function format: 
    select kernel_density_estimation(bigint stamp, double value, varchar kernelType)
  • Parameters
    Parameter Description
    stamp Unix timestamp. Unit: second.
    value Observed value.
    kernelType
    • box: rectangle.
    • epanechnikov: Epanechnikov curve.
    • gaussian: Gaussian curve.
  • Output result
    Display item Description
    unixtime The time of the source data.
    real Observed value.
    pdf The probability of each point.
  • Examples
    • Sample code: 
      * | 
select 
    date_trunc('second', cast(t1[1] as bigint)) as time, t1[2] as real, t1[3] as pdf from (
        select kernel_density_estimation(time, num, 'gaussian') as res from ( 
            select __time__ - __time__ % 10 as time, COUNT(*) * 1.0 as num from log group by time order by time)
        ), unnest(res) as t(t1)  limit 1000
    • Sample result: