pastas.modelstats.Statistics.diagnostics#

pastas.modelstats.Statistics.diagnostics(tmin: pandas.Timestamp | str | None = None, tmax: pandas.Timestamp | str | None = None, alpha: float = 0.05, stats: tuple = (), float_fmt: str = '{0:.2f}') → pandas.DataFrame#

Methods to compute various diagnostics checks for the noise time series. If no NoiseModel is used, the diagnostics are computed on the model residuals.

Parameters:

tmin (pandas.Timestamp or str, optional) – A string or pandas.Timestamp with the start date (E.g. ‘1980-01-01 00:00:00’) of the residual / noise time series to compute the diagnostics checks for. Strings are converted to pandas.Timestamp internally.
tmax (pandas.Timestamp or str, optional) – A string or pandas.Timestamp with the end date (E.g. ‘1980-01-01 00:00:00’) of the residuals / noise time series to compute the diagnostics checks for. Strings are converted to pandas.Timestamp internally.
alpha (float, optional) – significance level to use for the hypothesis testing.
stats (tuple, optional) – Tuple with the diagnostic checks to perform. Not implemented yet.
float_fmt (str) – String to use for formatting the floats in the returned DataFrame.

Returns:

df – DataFrame with the information for the diagnostics checks. The final column in this DataFrame report if the Null-Hypothesis is rejected. If H0 is not rejected (=False) the data is in agreement with one of the properties of white noise (e.g., normally distributed).

Return type:

Pandas.DataFrame