Struct AlignClusterConfig 

#[non_exhaustive]
pub struct AlignClusterConfig {
    pub k: usize,
    pub max_iter: usize,
    pub seed: u64,
    pub use_amplitude_only: bool,
    pub elastic_lambda: f64,
    pub karcher_max_iter: usize,
    pub karcher_tol: f64,
}

Configuration for joint align-and-cluster (elastic k-means).

Alternates between updating per-cluster template curves (via Karcher mean in the elastic metric) and reassigning each curve to the nearest template by elastic distance. This is the only clusterer in this module that is shape-invariant — it finds clusters based on amplitude shape, not phase.

Reference: Inspired by Sangalli et al. (2010) joint clustering and alignment and the fdasrvf elastic k-means variant (Srivastava et al.).

Example

use fdars_core::clustering_advanced::{align_cluster_fd, AlignClusterConfig};
use fdars_core::matrix::FdMatrix;
use std::f64::consts::PI;

let m = 25;
let n = 10;
let t: Vec<f64> = (0..m).map(|i| i as f64 / (m - 1) as f64).collect();
let mut col_major = vec![0.0_f64; n * m];
for i in 0..5 {
    for (j, &tj) in t.iter().enumerate() {
        col_major[i + j * n] = (2.0 * PI * tj).sin();
    }
}
for i in 5..10 {
    for (j, &tj) in t.iter().enumerate() {
        col_major[i + j * n] = (2.0 * PI * tj).sin() + 5.0;
    }
}
let data = FdMatrix::from_column_major(col_major, n, m).unwrap();

let mut cfg = AlignClusterConfig::default();
cfg.k = 2;
cfg.max_iter = 10;
cfg.karcher_max_iter = 8;
let result = align_cluster_fd(&data, &t, &cfg).unwrap();
assert_eq!(result.cluster.len(), n);
assert_eq!(result.templates.len(), 2);

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

k: usize

Number of clusters (default: 2). Must be ≥ 1 and ≤ n.

max_iter: usize

Maximum number of outer iterations (default: 20).

seed: u64

Random seed for initial template selection (default: 42).

use_amplitude_only: bool

If true, use amplitude_distance (shape-invariant); otherwise use elastic_distance (full Fisher-Rao distance including phase). Default: true.

elastic_lambda: f64

Penalty weight for elastic_distance when use_amplitude_only = false (default: 0.0).

karcher_max_iter: usize

Maximum inner iterations for Karcher mean (default: 15).

karcher_tol: f64

Convergence tolerance for Karcher mean (default: 1e-4).

Trait Implementations

impl Clone for AlignClusterConfig

fn clone(&self) -> AlignClusterConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AlignClusterConfig

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

Formats the value using the given formatter.

impl Default for AlignClusterConfig

fn default() -> Self

Returns the “default value” for a type.

impl PartialEq for AlignClusterConfig

fn eq(&self, other: &AlignClusterConfig) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl StructuralPartialEq for AlignClusterConfig