Crate flow_pacmap 

flow-pacmap

First-party implementation of PaCMAP (Pairwise Controlled Manifold Approximation Projection) from Wang et al. 2021 (JMLR 22, Algorithm 1).

Designed for large-n flow cytometry data:

• No ndarray version conflicts — pure &[f32] / Vec<[f32;2]> API
• PCA via faer SVD on the d×d covariance matrix (O(n·d²), no large intermediates)
• HNSW KNN via usearch (C++ FFI, hardware SIMD, optional f16 quantization)
• All pair counts use checked_mul; no debug-mode overflow panics
• Progress reporting via mpsc::Sender<PaCMAPProgress> (per phase + every 10 iters)
• Cancellation via Arc<AtomicBool>
• Staged KNN: compute_knn → KnnGraph → optional input to fit_transform

Re-exports

pub use config::Init;

pub use config::OptimizeBackend;

pub use config::PaCMAPConfig;

pub use error::PaCMAPError;

pub use knn::compute_knn;

pub use knn::validate_knn_for_pacmap;

Modules

adam

Adam optimizer step for the 2-D embedding.

config

Configuration types for a PaCMAP embedding run.

error

Error types for flow-pacmap.

gradient

PaCMAP loss gradient computation (Algorithm 1, Wang et al. 2021).

knn

Re-export and PaCMAP-facing adapters for flow_knn.

pairs

Near, mid-near, and further pair construction from Algorithm 1.

pca

PCA initialisation for PaCMAP.

weights

Three-phase weight schedule from Algorithm 1 of Wang et al. 2021.

Structs

HnswParams

Quality / memory trade-off for HNSW indices (usearch or ann-search-rs).

KnnGraph

Portable k-nearest-neighbour graph: per-point indices and distances only.

NeighborList

Neighbours of a single query point.

PaCMAPProgress

Progress event emitted during optimization.

Enums

DistanceMetric

Distance metric for the KNN graph.

KnnMethod

Approximate / exact nearest-neighbour method.

Quantization

Vector quantization for usearch HNSW storage.

Functions

fit_transform

Embed n × d row-major f32 data into 2 dimensions.

read_knn_graph

Read a KnnGraph previously written by write_knn_graph.

write_knn_graph

Write a KnnGraph to path (creates/overwrites the file).