SegmentAccuracyScenario
Statistics scenarios · Implementation: mlsysim/engine/scenario_definitions/statistics.py.
Construct this scenario with keyword inputs. The fields below show the types and defaults declared by this class.
Accuracy measured separately on each traffic segment; traffic_shares and accuracies are keyed by segment name.
Notes
Equation: Overall accuracy sums traffic_share[k]*accuracy[k]; the worst segment minimizes the declared accuracy mapping.
Assumptions: The two mappings use matching keys and traffic shares sum to one when interpreting the weighted sum as population accuracy.
Excludes: Automatic share normalization, uncertainty intervals, and changes in segment traffic mix.
References
Derivation: Overall accuracy sums traffic_share[k]*accuracy[k]; the worst segment minimizes the declared accuracy mapping. This is declared scenario accounting rather than a fitted empirical law.
Examples
>>> from mlsysim import Scenarios
>>> scenario = Scenarios.RecommendationAccuracyByDevice
>>> value = scenario.total_share
>>> round(float(value), 3)
1.0Attributes
| Name | Description |
|---|---|
| accuracies | |
| overall_accuracy | Sum of traffic share times accuracy by matching segment key, dimensionless. |
| total_share | Sum of declared traffic shares; this property reports rather than normalizes them. |
| traffic_shares | |
| worst_segment | Segment key with the smallest declared accuracy, preserving mapping tie order. |
accuracies
Type: Dict[str, float].
Declared default: required.
overall_accuracy
engine.scenario_types.SegmentAccuracyScenario.overall_accuracy
Sum of traffic share times accuracy by matching segment key, dimensionless.
Equation: sum((traffic_shares[k] * accuracies[k] for k in traffic_shares)).
worst_segment
engine.scenario_types.SegmentAccuracyScenario.worst_segment
Segment key with the smallest declared accuracy, preserving mapping tie order.
Equation: min(accuracies, key=accuracies.get).