Struct TrainedDiffusionModel 

pub struct TrainedDiffusionModel {
    pub column_params: Vec<ColumnDiffusionParams>,
    pub correlation_matrix: Vec<Vec<f64>>,
    pub config: DiffusionConfig,
    pub metadata: ModelMetadata,
}

A trained diffusion model that can generate samples and be persisted to disk.

Fields

column_params: Vec<ColumnDiffusionParams>

Per-column statistical parameters.

correlation_matrix: Vec<Vec<f64>>

Correlation matrix (n_columns x n_columns).

config: DiffusionConfig

Diffusion configuration used during training.

metadata: ModelMetadata

Model metadata.

Implementations

impl TrainedDiffusionModel

pub fn generate(&self, n_samples: usize, seed: u64) -> Vec<Vec<f64>>

Generate n_samples rows of synthetic data using the trained model parameters.

Each row contains one value per column. Column types are respected:

• Continuous: clipped to [min, max]
• Integer: rounded and clipped to [min, max]
• Categorical: mapped to category indices, rounded and clipped to [0, n_categories - 1]

pub fn save(&self, path: &Path) -> Result<(), SynthError>

Serialize and save the model to a JSON file at path.

pub fn load(path: &Path) -> Result<Self, SynthError>

Load a model from a JSON file at path.

Trait Implementations

impl Clone for TrainedDiffusionModel

fn clone(&self) -> TrainedDiffusionModel

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TrainedDiffusionModel

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for TrainedDiffusionModel

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for TrainedDiffusionModel

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

where __S: Serializer,

Serialize this value into the given Serde serializer.