AnalysisData

AnalysisData(
    exact=None,
    interval=None,
    threshold=None,
    uncertain=None,
    low_outlier_threshold=None,
    mgbt_low_outliers=False,
)

Censored observation data for an analysis.

Beyond a plain systematic record (exact), a frame can carry the censored observation types Bulletin 17C flood-frequency work depends on: historical or paleoflood observations known only within a range (interval), perception thresholds recording that nothing above a level occurred over a span of years (threshold), and observations whose measurement error is itself a distribution (uncertain).

This is the port of the RMC.BestFit DataFrame class, named AnalysisData to avoid colliding with :class:pandas.DataFrame.

Indexes are 0-based, matching the C# library and the shared C++ core, and are generated sequentially when not supplied. An index is a position in the record, so an interval observation at index 40 sits after the 40th exact observation in chronological order.

Parameters

Name	Type	Description	Default
exact	array_like or dict	Observations, or a mapping with a "value" key plus optional "index" and "is_low_outlier" keys.	None
interval	dict	Mapping with "lower", "value", and "upper" keys plus an optional "index", giving observations known only to lie in a range.	None
threshold	dict	Mapping with "start_index", "end_index", "value", and "number_above" keys, giving perception thresholds over spans of the record.	None
uncertain	sequence of Distribution or dict	One distribution per observation, or a mapping with "index" and "distribution" keys.	None
low_outlier_threshold	float	Values at or below it are treated as left-censored low outliers.	None
mgbt_low_outliers	bool	Let the Multiple Grubbs-Beck test pick the low outlier threshold from the data. Mutually exclusive with low_outlier_threshold and with explicit is_low_outlier flags.	False

Examples

>>> peaks = [12500, 15300, 8900, 22100, 18700, 14200, 9800, 28500]
>>> AnalysisData(peaks)
<AnalysisData 8 exact>

Two historical floods known only within a range, and a perception threshold covering the 40 years before the gauge was installed:

>>> AnalysisData(
...     exact=peaks,
...     interval={"index": [8, 9], "lower": [30000, 26000],
...               "value": [35000, 29000], "upper": [40000, 32000]},
...     threshold={"start_index": 8, "end_index": 47,
...                "value": 25000, "number_above": 2},
... )
<AnalysisData 8 exact, 2 interval, 1 threshold>

Methods

Name	Description
to_json	The frame as the JSON spec the shared C++ core parses.

to_json

AnalysisData.to_json()

The frame as the JSON spec the shared C++ core parses.