Struct LoadedDataset 

pub struct LoadedDataset {
    pub id: DatasetId,
    pub sentences: Vec<AnnotatedSentence>,
    pub loaded_at: String,
    pub source_url: String,
    pub data_source: DataSource,
    pub temporal_metadata: Option<TemporalMetadata>,
    pub metadata: DatasetMetadata,
}

A loaded dataset with metadata.

Fields

id: DatasetId

Dataset identifier.

sentences: Vec<AnnotatedSentence>

Annotated sentences.

loaded_at: String

When the dataset was loaded.

source_url: String

Source URL.

data_source: DataSource

Where the data was actually loaded from.

temporal_metadata: Option<TemporalMetadata>

Optional temporal metadata for temporal stratification

metadata: DatasetMetadata

Dataset provenance and attribution metadata.

Implementations

impl LoadedDataset

pub fn len(&self) -> usize

Total number of sentences.

pub fn is_empty(&self) -> bool

Check if empty.

pub fn entity_count(&self) -> usize

Total number of entities.

pub fn entity_counts_by_type(&self) -> HashMap<String, usize>

Count entities by type.

pub fn stats(&self) -> DatasetStats

Get statistics summary.

pub fn to_test_cases(&self) -> Vec<(String, Vec<GoldEntity>)>

Convert to test cases format for evaluation.

Trait Implementations

impl Clone for LoadedDataset

fn clone(&self) -> LoadedDataset

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LoadedDataset

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for LoadedDataset

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for LoadedDataset

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

where __S: Serializer,

Serialize this value into the given Serde serializer.