Crate linfa_clustering

source ·
Expand description

linfa-clustering aims to provide pure Rust implementations of popular clustering algorithms.

The big picture

linfa-clustering is a crate in the linfa ecosystem, a wider effort to bootstrap a toolkit for classical Machine Learning implemented in pure Rust, kin in spirit to Python’s scikit-learn.

You can find a roadmap (and a selection of good first issues) here - contributors are more than welcome!

Current state

Right now linfa-clustering provides the following clustering algorithms:

Implementation choices, algorithmic details and tutorials can be found in the page dedicated to the specific algorithms.

Structs

  • Dbscan
    DBSCAN (Density-based Spatial Clustering of Applications with Noise) clusters together points which are close together with enough neighbors labelled points which are sparsely neighbored as noise. As points may be part of a cluster or noise the predict method returns Array1<Option<usize>>
  • DbscanParams
    Helper struct for building a set of DBSCAN hyperparameters
  • DbscanValidParams
    The set of hyperparameters that can be specified for the execution of the DBSCAN algorithm.
  • GaussianMixtureModel
    Gaussian Mixture Model (GMM) aims at clustering a dataset by finding normally distributed sub datasets (hence the Gaussian Mixture name) .
  • GmmParams
    The set of hyperparameters that can be specified for the execution of the GMM algorithm.
  • GmmValidParams
    The set of hyperparameters that can be specified for the execution of the GMM algorithm.
  • KMeans
    K-means clustering aims to partition a set of unlabeled observations into clusters, where each observation belongs to the cluster with the nearest mean.
  • KMeansParams
    An helper struct used to construct a set of valid hyperparameters for the K-means algorithm (using the builder pattern).
  • KMeansValidParams
    The set of hyperparameters that can be specified for the execution of the K-means algorithm.
  • Optics
    OPTICS (Ordering Points To Identify Clustering Structure) is a clustering algorithm that doesn’t explicitly cluster the data but instead creates an “augmented ordering” of the dataset representing it’s density-based clustering structure. This ordering contains information which is equivalent to the density-based clusterings and can then be used for automatic and interactive cluster analysis.
  • OpticsAnalysis
    The analysis from running OPTICS on a dataset, this allows you iterate over the data points and access their core and reachability distances. The ordering of the points also doesn’t match that of the dataset instead ordering based on the clustering structure worked out during analysis.
  • OpticsParams
  • OpticsValidParams
    The set of hyperparameters that can be specified for the execution of the OPTICS algorithm.
  • Sample
    This struct represents a data point in the dataset with it’s associated distances obtained from the OPTICS analysis

Enums

Type Aliases