model_point_process

model_point_process(
    data,
    threshold=None,
    total_years=None,
    use_defaults=True,
    seasonal=False,
    time_block='water_year',
    start_month=10,
    parameters=None,
    parameter_values=None,
    use_default_flat_priors=None,
)

A point process over exceedances of a threshold.

Combines an arrival rate with a magnitude distribution.

With seasonal=True the magnitude distribution becomes TWO generalized extreme value marginals with two fitted change points, and each observation is assigned to a season by its day of the year – so the data must carry DATES, not bare indices::

data = analysis_data(exact={"date": dates, "value": peaks})
model = model_point_process(data, seasonal=True)

Observations supplied with integer indices are treated as January 1 of that year, which puts every one of them in the same season.

Parameters

Name	Type	Description	Default
data	AnalysisData or array_like	Observations.	required
threshold	float	Exceedance threshold; derived from the data when omitted. See :func:~corehydropy.data.threshold_diagnostics for choosing one.	None
total_years	float	Record length in years, used for the arrival rate.	None
use_defaults	bool	Let the model derive its threshold and record length from the data. Applied before an explicit threshold or total_years, so an explicit value wins.	True
seasonal	bool	Fit two seasonal magnitude distributions with fitted change points.	False
time_block	str	The block a seasonal model reduces the record over: "water_year", "calendar_year", "custom_year", "quarter" or "month".	"water_year"
start_month	int	The month a water year or custom year begins.	10
parameters		As in :func:model_univariate.	None
parameter_values		As in :func:model_univariate.	None
use_default_flat_priors		As in :func:model_univariate.	None

Returns

Name	Type	Description
	Model	The assembled model spec.