classification_table

Threshold-sweep classification table analyzer for no-reset benchmarks.

class pysatl_cpd.benchmark.online.noreset.tooling.analyzers.classification_table.NoResetClassificationTableAnalyzer(entries_picker=None)[source]

Bases: NoResetAnalyzerBase, NoResetBisigementClassificationMixin

Analyzer that computes classification metrics across a range of thresholds.

Parameters:: entries_picker (BenchmarkEntriesPicker | None)

analyze(benchmark_entry, thresholds, *, entries_picker=None)[source]

Evaluate classification metrics at every threshold in a sweep.

For each threshold, computes TP, FP, FN, precision, recall, F1, mean delay, and median delay across all runs picked for the entry.

Parameters:

benchmark_entry (OnlineNoResetBenchmarkEntry) – Entry describing detector configuration used for picking and validation.
thresholds (Sequence[float]) – Threshold values to evaluate.
entries_picker (BenchmarkEntriesPicker | None) – Override picker for selecting registry entries.

Returns:

Table with one row per threshold containing all metrics.

Return type:

DataFrame