ACFPeriodicityDetector

class pyriodicity.ACFPeriodicityDetector

Autocorrelation Function (ACF) based periodicity detector.

Find the periods in a given signal or series using its ACF. A lag value is considered a period if it is a local maximum of the ACF [1].

See also

pyriodicity.OnlineACFPeriodicityDetector

online Autocorrelation Function (ACF) based periodicity detector.

References

[1]

Hyndman, R.J., & Athanasopoulos, G. (2021) Forecasting: principles and practice, 3rd edition, OTexts: Melbourne, Australia. https://OTexts.com/fpp3/acf.html. Accessed on 09-15-2024.

Examples

Start by loading Mauna Loa Weekly Atmospheric CO2 Data from statsmodels and downsampling its data to a monthly frequency.

>>> from statsmodels.datasets import co2
>>> data = co2.load().data
>>> data = data.resample("ME").mean().ffill()

Use ACFPeriodicityDetector to find the list of seasonality periods using the ACF.

>>> from pyriodicity import ACFPeriodicityDetector
>>> ACFPeriodicityDetector.detect(data)
array([ 12,  24,  36,  48,  60,  72,  84,  96, 108, 120, 132, 143, 155,
   167, 179, 191, 203, 215, 227, 239, 251])

All of the returned values are either multiples of 12 or very close to it, suggesting a clear yearly periodicity. You can also get the most prominent period length value by setting max_period_count to 1.

>>> ACFPeriodicityDetector.detect(data, max_period_count=1)
array([12])

Methods

detect(data[, window_func, detrend_func, ...])

Find periods in the given series.