EvaluationComparison#

class scikitplot.corpus.EvaluationComparison(metrics, n_queries, n_resamples, seed)[source]#

Paired comparison of two evaluations of the same queries.

Parameters:

metricstuple of MetricComparison

One entry per metric both evaluations report, in the candidate’s order.

n_queriesint

Queries (or answer items) in both evaluations.

n_resamplesint

Random sign flips drawn when the pairs exceed EXACT_SIGN_FLIP_LIMIT (otherwise every flip is enumerated).

seedint

Seed of those draws.

Parameters:

• metrics (tuple)

• n_queries (int)

• n_resamples (int)

• seed (int)

dumps(format='json')[source]#

Serialise to "json", "jsonl" (one row per metric), "yaml" or "toml".

Parameters:

format (str)

Return type:

str

metrics: tuple[source]#

n_queries: int[source]#

n_resamples: int[source]#

seed: int[source]#

to_dict()[source]#

Return a mapping in the comparison schema.

Return type:

dict[str, Any]

write(path, format=None)[source]#

Write atomically; the format defaults to the path suffix.

Parameters:

• path (Any)

• format (str | None)

Return type:

Any