Struct Dataset 

pub struct Dataset {
    pub features: Array2<f64>,
    pub targets: Array2<f64>,
    pub feature_names: Option<Vec<String>>,
    pub target_names: Option<Vec<String>>,
}

Dataset container for training data.

Fields

features: Array2<f64>

Feature matrix (samples x features).

targets: Array2<f64>

Target vector or matrix.

feature_names: Option<Vec<String>>

Feature names (if available).

target_names: Option<Vec<String>>

Target names (if available).

Implementations

impl Dataset

pub fn new(features: Array2<f64>, targets: Array2<f64>) -> Self

Create a new dataset.

pub fn with_feature_names(self, names: Vec<String>) -> Self

Set feature names.

pub fn with_target_names(self, names: Vec<String>) -> Self

Set target names.

pub fn num_samples(&self) -> usize

Get number of samples.

pub fn num_features(&self) -> usize

Get number of features.

pub fn num_targets(&self) -> usize

Get number of targets.

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

Shuffle the dataset in place using Fisher-Yates algorithm.

pub fn split(&self, ratios: &[f64]) -> TrainResult<Vec<Dataset>>

Split dataset into subsets.

Arguments

• ratios - Ratios for each split (must sum to 1.0)

Returns

Vector of datasets corresponding to each ratio

pub fn train_test_split( &self, train_ratio: f64, ) -> TrainResult<(Dataset, Dataset)>

Split into train and test sets.

pub fn train_val_test_split( &self, train_ratio: f64, val_ratio: f64, ) -> TrainResult<(Dataset, Dataset, Dataset)>

Split into train, validation, and test sets.

pub fn subset(&self, indices: &[usize]) -> TrainResult<Dataset>

Get a subset of the dataset by indices.

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.