Struct MultiRunEvaluator 

pub struct MultiRunEvaluator { /* private fields */ }

Multi-run evaluator for NER models.

Runs evaluation multiple times and aggregates results with statistics.

Implementations

impl MultiRunEvaluator

pub fn new(config: MultiRunConfig) -> Self

Create a new evaluator with the given config.

pub fn default_config() -> Self

Create with default config.

pub fn evaluate( &self, model: &dyn Model, test_cases: &[(String, Vec<GoldEntity>)], ) -> Result<MultiRunResults>

Evaluate a model on test cases with multiple runs.

pub fn quick_eval( model: &dyn Model, test_cases: &[(String, Vec<GoldEntity>)], ) -> Result<MultiRunResults>

Quick evaluation with 3 runs (suitable for development).

pub fn thorough_eval( model: &dyn Model, test_cases: &[(String, Vec<GoldEntity>)], ) -> Result<MultiRunResults>

Thorough evaluation with 10 runs (suitable for publication).

Trait Implementations

impl Clone for MultiRunEvaluator

fn clone(&self) -> MultiRunEvaluator

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for MultiRunEvaluator

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

Formats the value using the given formatter.