Struct EvalComparison 

pub struct EvalComparison {
    pub cases: Vec<CaseComparison>,
}

Comparison of two eval runs for A/B testing and regression detection.

Fields

cases: Vec<CaseComparison>

Per-case comparison results.

Implementations

impl EvalComparison

pub fn compare(baseline: &[EvalResult], candidate: &[EvalResult]) -> Self

Compare baseline and candidate eval results.

Matches results by case_name. Cases present in only one run are skipped.

pub fn baseline_wins(&self) -> usize

Number of cases where baseline scored higher.

pub fn candidate_wins(&self) -> usize

Number of cases where candidate scored higher.

pub fn ties(&self) -> usize

Number of cases with equal scores (within tolerance).

pub fn has_regressions(&self) -> bool

Whether any case regressed from baseline to candidate.

pub fn regressions(&self) -> Vec<&str>

Names of cases where candidate scored lower than baseline.

Trait Implementations

impl Clone for EvalComparison

fn clone(&self) -> EvalComparison

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for EvalComparison

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for EvalComparison

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Display for EvalComparison

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Serialize for EvalComparison

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.