pmdarima.arima.nsdiffs

pmdarima.arima.nsdiffs(x, m, max_D=2, test='ocsb', **kwargs)

Estimate the seasonal differencing term, D.

Perform a test of seasonality for different levels of D to estimate the number of seasonal differences required to make a given time series stationary. Will select the maximum value of D for which the time series is judged seasonally stationary by the statistical test.

Parameters:

x : array-like, shape=(n_samples, [n_features])

The array to difference.

m : int

The number of seasonal periods (i.e., frequency of the time series)

max_D : int, optional (default=2)

Maximum number of seasonal differences allowed. Must be a positive integer. The estimated value of D will not exceed max_D.

test : str, optional (default=’ocsb’)

Type of unit root test of seasonality to use in order to detect seasonal periodicity. Valid tests include (“ocsb”, “ch”). Note that the CHTest is very slow for large data.

Returns:

D : int

The estimated seasonal differencing term. This is the maximum value of D such that D <= max_D and the time series is judged seasonally stationary. If the time series is constant, will return 0.