Struct TSNE 

pub struct TSNE { /* private fields */ }

t-SNE for dimensionality reduction and visualization.

t-Distributed Stochastic Neighbor Embedding (t-SNE) is a non-linear dimensionality reduction technique optimized for visualization of high-dimensional data in 2D or 3D space.

Algorithm

1. Compute pairwise similarities in high-D using Gaussian kernel
2. Compute perplexity-based conditional probabilities
3. Initialize low-D embedding (random or PCA)
4. Compute pairwise similarities in low-D using Student’s t-distribution
5. Minimize KL divergence via gradient descent with momentum

Example

use aprender::prelude::*;
use aprender::preprocessing::TSNE;

let data = Matrix::from_vec(
    6,
    4,
    vec![
        1.0, 2.0, 3.0, 4.0,
        1.1, 2.1, 3.1, 4.1,
        5.0, 6.0, 7.0, 8.0,
        5.1, 6.1, 7.1, 8.1,
        10.0, 11.0, 12.0, 13.0,
        10.1, 11.1, 12.1, 13.1,
    ],
)
.expect("valid matrix dimensions");

let mut tsne = TSNE::new(2).with_perplexity(5.0).with_n_iter(250);
let embedding = tsne.fit_transform(&data).expect("fit_transform should succeed");
assert_eq!(embedding.shape(), (6, 2));

Implementations

impl TSNE

pub fn new(n_components: usize) -> Self

Create a new t-SNE with default parameters.

Default: perplexity=30.0, learning_rate=200.0, n_iter=1000

pub fn with_perplexity(self, perplexity: f32) -> Self

Set perplexity (balance between local and global structure).

Typical range: 5-50. Higher perplexity considers more neighbors.

pub fn with_learning_rate(self, learning_rate: f32) -> Self

Set learning rate for gradient descent.

pub fn with_n_iter(self, n_iter: usize) -> Self

Set number of gradient descent iterations.

pub fn with_random_state(self, seed: u64) -> Self

Set random seed for reproducibility.

pub fn n_components(&self) -> usize

Get number of components.

pub fn is_fitted(&self) -> bool

Check if model has been fitted.

Trait Implementations

impl Clone for TSNE

fn clone(&self) -> TSNE

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TSNE

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

Formats the value using the given formatter.

impl Default for TSNE

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for TSNE

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for TSNE

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Transformer for TSNE

fn fit(&mut self, x: &Matrix<f32>) -> Result<()>

Fits the transformer to data.

fn transform(&self, _x: &Matrix<f32>) -> Result<Matrix<f32>>

Transforms data using fitted parameters.

fn fit_transform(&mut self, x: &Matrix<f32>) -> Result<Matrix<f32>>

Fits and transforms in one step.