Struct Dataset 

pub struct Dataset {
    pub data: Array2<f64>,
    pub target: Option<Array1<f64>>,
    pub targetnames: Option<Vec<String>>,
    pub featurenames: Option<Vec<String>>,
    pub feature_descriptions: Option<Vec<String>>,
    pub description: Option<String>,
    pub metadata: HashMap<String, String>,
}

Represents a dataset with features, optional targets, and metadata

The Dataset struct is the core data structure for managing machine learning datasets. It stores the feature matrix, optional target values, and rich metadata including feature names, descriptions, and arbitrary key-value pairs.

Examples

use scirs2_core::ndarray::Array2;
use scirs2_datasets::utils::Dataset;

let data = Array2::from_shape_vec((3, 2), vec![1.0, 2.0, 3.0, 4.0, 5.0, 6.0]).expect("Operation failed");
let dataset = Dataset::new(data, None)
    .with_featurenames(vec!["feature1".to_string(), "feature2".to_string()])
    .with_description("Sample dataset".to_string());

assert_eq!(dataset.n_samples(), 3);
assert_eq!(dataset.n_features(), 2);

Fields

data: Array2<f64>

Features/data matrix (n_samples, n_features)

target: Option<Array1<f64>>

Optional target values

targetnames: Option<Vec<String>>

Optional target names for classification problems

featurenames: Option<Vec<String>>

Optional feature names

feature_descriptions: Option<Vec<String>>

Optional descriptions for each feature

description: Option<String>

Optional dataset description

metadata: HashMap<String, String>

Optional dataset metadata

Implementations

impl Dataset

pub fn new(data: Array2<f64>, target: Option<Array1<f64>>) -> Self

Create a new dataset with the given data and target

Arguments

• data - The feature matrix (n_samples, n_features)
• target - Optional target values (n_samples,)

Returns

A new Dataset instance with empty metadata

Examples

use scirs2_core::ndarray::{Array1, Array2};
use scirs2_datasets::utils::Dataset;

let data = Array2::zeros((100, 5));
let target = Some(Array1::zeros(100));
let dataset = Dataset::new(data, target);

pub fn from_metadata( data: Array2<f64>, target: Option<Array1<f64>>, metadata: DatasetMetadata, ) -> Self

Create a new dataset with the given data, target, and metadata

Arguments

• data - The feature matrix (n_samples, n_features)
• target - Optional target values (n_samples,)
• metadata - Dataset metadata information

Returns

A new Dataset instance with metadata applied

pub fn with_targetnames(self, targetnames: Vec<String>) -> Self

Add target names to the dataset (builder pattern)

Arguments

• targetnames - Vector of target class names

Returns

Self for method chaining

pub fn with_featurenames(self, featurenames: Vec<String>) -> Self

Add feature names to the dataset (builder pattern)

Arguments

• featurenames - Vector of feature names

Returns

Self for method chaining

pub fn with_feature_descriptions(self, featuredescriptions: Vec<String>) -> Self

Add feature descriptions to the dataset (builder pattern)

Arguments

• feature_descriptions - Vector of feature descriptions

Returns

Self for method chaining

pub fn with_description(self, description: String) -> Self

Add a description to the dataset (builder pattern)

Arguments

• description - Dataset description

Returns

Self for method chaining

pub fn with_metadata(self, key: &str, value: &str) -> Self

Add metadata to the dataset (builder pattern)

Arguments

• key - Metadata key
• value - Metadata value

Returns

Self for method chaining

pub fn n_samples(&self) -> usize

Get the number of samples in the dataset

Returns

Number of samples (rows) in the dataset

pub fn n_features(&self) -> usize

Get the number of features in the dataset

Returns

Number of features (columns) in the dataset

pub fn shape(&self) -> (usize, usize)

Get dataset shape as (n_samples, n_features)

Returns

Tuple of (n_samples, n_features)

pub fn has_target(&self) -> bool

Check if the dataset has target values

Returns

True if target values are present, false otherwise

pub fn featurenames(&self) -> Option<&Vec<String>>

Get a reference to the feature names if available

Returns

Optional reference to feature names vector

pub fn targetnames(&self) -> Option<&Vec<String>>

Get a reference to the target names if available

Returns

Optional reference to target names vector

pub fn description(&self) -> Option<&String>

Get a reference to the dataset description if available

Returns

Optional reference to dataset description

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

Get a reference to the metadata

Returns

Reference to metadata HashMap

pub fn set_metadata(&mut self, key: &str, value: &str)

Add or update a metadata entry

Arguments

• key - Metadata key
• value - Metadata value

pub fn get_metadata(&self, key: &str) -> Option<&String>

Get a metadata value by key

Arguments

• key - Metadata key to lookup

Returns

Optional reference to the metadata value

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<'de> Deserialize<'de> for Dataset

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for Dataset

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

where __S: Serializer,

Serialize this value into the given Serde serializer.