Struct DatasetStats 

pub struct DatasetStats {
    pub num_examples: usize,
    pub num_entities: usize,
    pub type_distribution: HashMap<String, f64>,
    pub avg_entities_per_example: f64,
    pub vocab_size: usize,
    pub entity_length_stats: LengthStats,
    pub unique_entity_texts: usize,
    pub entity_diversity: f64,
}

Statistics about a single dataset.

Fields

num_examples: usize

Number of examples

num_entities: usize

Total number of entities

type_distribution: HashMap<String, f64>

Entity type distribution (type -> proportion)

avg_entities_per_example: f64

Average entities per example

vocab_size: usize

Vocabulary (unique tokens)

entity_length_stats: LengthStats

Entity length distribution stats

unique_entity_texts: usize

Unique entity texts

entity_diversity: f64

Entity text repetition rate (1.0 = all unique, lower = more repetition)

Trait Implementations

impl Clone for DatasetStats

fn clone(&self) -> DatasetStats

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for DatasetStats

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for DatasetStats

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for DatasetStats

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

where __S: Serializer,

Serialize this value into the given Serde serializer.