TimeSeries

TimeSeries / TopPeriods / 0.2.1

README.md

Top Periods

This algorithm calls calculates the largest periodic sequences within a dataset, while also removing signal noise via the Autocorrelate algorithm.


Table of Contents


Inputs

All TimeSeries algorithms have a json object input, as well as array input formatting.

Json Format

{  
   "data":Double[],
   "numOfPeriods": Int
}
{  
   "data": [1,2,3,4,3,4,6,7,5,4,2,1,1],
   "numOfPeriods": 4
}
  • data - (required) - The timeseries input data you wish to calculate periods from, this algorithm assumes the values are evenly spaced. (dx(1) == dx(n))
  • numOfPeriods (optional) - The maximum number of periods to return, defaults to 3.

Array Format

There are two separate input formats for this algorithm.

Basic format

data: Double[]
[1,2,3,4,3,4,6,7,5,4,2,1,1]
  • data - (required) - The timeseries input data you wish to calculate periods from, this algorithm assumes the values are evenly spaced. (dx(1) == dx(n))

Advanced Format

[data: Double[], numOfPeriods: Int]
[[1,2,3,4,3,4,6,7,5,4,2,1,1], 4]
  • data - (required) - The timeseries input data you wish to calculate periods from, this algorithm assumes the values are evenly spaced. (dx(1) == dx(n))
  • numOfPeriods (optional) - The maximum number of periods to return, defaults to 3.

Outputs

This algorithm has json output for json input, and array output for array input.

JSON Format

{  
   "topPeriods": Int[]
}
{  
   "topPeriods": [4,3,2]
}
  • topPeriods - The largest periodic sequences in descending order, the number of sequences depends on the numOfPeriods parameter.

Array Format

topPeriods: Double[]
[1,2,3,4,3,4,6,7,5,4,2,1,1]
  • topPeriods - The largest periodic sequences in descending order, the number of sequences depends on the numOfPeriods parameter.