Struct Dataset 

pub struct Dataset {
    pub rows: Vec<DataRow>,
    pub feature_names: Vec<String>,
    pub class_names: Vec<String>,
}

A dataset with optional train/validation split.

Fields

rows: Vec<DataRow>

All rows.

feature_names: Vec<String>

Feature names.

class_names: Vec<String>

Class names (index → name).

Implementations

impl Dataset

pub fn new() -> Self

Create an empty dataset.

pub fn push(&mut self, row: DataRow)

Add a row.

pub fn len(&self) -> usize

Number of rows.

pub fn is_empty(&self) -> bool

Whether the dataset is empty.

pub fn num_features(&self) -> usize

Number of features (from the first row, or 0).

pub fn shuffle(&mut self, seed: u64)

Shuffle rows using Fisher-Yates with a simple LCG.

pub fn train_val_split(&self, val_fraction: f64) -> (Dataset, Dataset)

Split into training and validation subsets.

val_fraction is the fraction of rows reserved for validation.

pub fn feature_stats(&self) -> (Vec<f64>, Vec<f64>)

Compute per-feature mean and standard deviation.

Returns (means, stds) each of length num_features.

Trait Implementations

impl Clone for Dataset

fn clone(&self) -> Dataset

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Dataset

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

Formats the value using the given formatter.

impl Default for Dataset

fn default() -> Dataset

Returns the “default value” for a type.