Struct ModelEvalResult 

pub struct ModelEvalResult {
    pub model_id: String,
    pub metric: EmbedMetric,
    pub scores: Vec<f64>,
    pub mean: f64,
    pub std_dev: f64,
    pub sample_count: usize,
}

Evaluation result for a single model on a given metric

Fields

model_id: String

Identifier for the model being evaluated

metric: EmbedMetric

Metric being measured

scores: Vec<f64>

Per-sample scores (e.g., per-query MRR, per-entity accuracy)

mean: f64

Arithmetic mean of scores

std_dev: f64

Standard deviation of scores

sample_count: usize

Number of samples

Implementations

impl ModelEvalResult

pub fn new( model_id: String, metric: EmbedMetric, scores: Vec<f64>, ) -> Result<Self>

Create a new evaluation result, computing statistics automatically

pub fn confidence_interval(&self, alpha: f64) -> (f64, f64)

Compute a two-sided confidence interval for the mean.

Uses the t-distribution approximation. alpha is the significance level (e.g., 0.05 for 95% CI).

Returns (lower_bound, upper_bound).

Trait Implementations

impl Clone for ModelEvalResult

fn clone(&self) -> ModelEvalResult

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelEvalResult

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ModelEvalResult

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ModelEvalResult

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

where __S: Serializer,

Serialize this value into the given Serde serializer.