Struct AgglomerativeClustering 

#[non_exhaustive]
pub struct AgglomerativeClustering { /* private fields */ }

Agglomerative (hierarchical) clustering.

Starts with each sample as its own cluster and iteratively merges the closest pair until n_clusters remain. Supports four linkage criteria.

Example

use scry_learn::cluster::AgglomerativeClustering;
use scry_learn::dataset::Dataset;

let data = Dataset::new(
    vec![vec![0.0, 0.0, 10.0, 10.0], vec![0.0, 0.0, 10.0, 10.0]],
    vec![0.0; 4],
    vec!["x".into(), "y".into()],
    "label",
);

let mut model = AgglomerativeClustering::new(2);
model.fit(&data).unwrap();
assert_eq!(model.labels().len(), 4);

Implementations

impl AgglomerativeClustering

pub fn new(n_clusters: usize) -> Self

Create a new agglomerative clustering model.

Arguments

• n_clusters — target number of clusters.

pub fn linkage(self, l: Linkage) -> Self

Set the linkage criterion.

pub fn fit(&mut self, data: &Dataset) -> Result<()>

Fit the model on a dataset.

Uses the features and ignores the target column. Computes the full O(n²) pairwise distance matrix, then greedily merges the closest cluster pair using a priority queue.

pub fn labels(&self) -> &[usize]

Get cluster labels for training data.

pub fn n_clusters(&self) -> usize

Number of clusters.

pub fn children(&self) -> &[MergeStep]

Merge history (dendrogram data).

Each entry records which two clusters were merged and at what distance.

Trait Implementations

impl Clone for AgglomerativeClustering

fn clone(&self) -> AgglomerativeClustering

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AgglomerativeClustering

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

Formats the value using the given formatter.