pmdarima.arima
.ndiffs¶

pmdarima.arima.
ndiffs
(x, alpha=0.05, test='kpss', max_d=2, **kwargs)[source][source]¶ Estimate ARIMA differencing term,
d
.Perform a test of stationarity for different levels of
d
to estimate the number of differences required to make a given time series stationary. Will select the maximum value ofd
for which the time series is judged stationary by the statistical test.Parameters: x : arraylike, shape=(n_samples, [n_features])
The array (time series) to difference.
alpha : float, optional (default=0.05)
Level of the test. This is the value above below which the Pvalue will be deemed significant.
test : str, optional (default=’kpss’)
Type of unit root test of stationarity to use in order to test the stationarity of the timeseries. One of (‘kpss’, ‘adf’, ‘pp’)
max_d : int, optional (default=2)
Maximum number of nonseasonal differences allowed. Must be a positive integer. The estimated value of
d
will not exceedmax_d
.Returns: d : int
The estimated differencing term. This is the maximum value of
d
such thatd <= max_d
and the time series is judged stationary. If the time series is constant, will return 0.References
[R70] R’s auto_arima ndiffs function https://github.com/robjhyndman/forecast/blob/19b0711e554524bf6435b7524517715658c07699/R/arima.R#L132 # noqa: E501