RNN DBSCAN

バージョン 1.0.1 (1.42 MB) 作成者: Trevor Vannoy
MATLAB implementation of the RNN-DBSCAN clustering algorithm

ダウンロード 90 件

更新 2021/8/20

GitHub から

GitHub でライセンスを表示

matlab-rnn-dbscan

View RNN DBSCAN on File Exchange

This repo contains a MATLAB implementation of the RNN-DBSCAN algorithm by Bryant and Cios. This implementation is based upon the graph-based interpretation presented in their paper.

RNN DBSCAN is a density-based clustering algorithm that uses reverse nearest neighbor counts as an estimate of observation density. It is based upon traversals of the directed k-nearest neighbor graph, and can handle clusters of different densities, unlike DBSCAN. For more details about the algorithm, see the original paper.

Dependencies

  • My knn-graphs MATLAB library
  • Statistics and Machine Learning Toolbox

To run the tests contained in the Jupyter notebook, you will need to install the Jupyter matlab kernel.

To use the NN Descent algorithm to construct the KNN graph used by RNN DBSCAN, you need pynndescent and MATLAB's Python language interface. I recommend using Conda to set up an environment, as MATLAB is picky about which Python versions it supports.

Installation

Install with mpm:

mpm install knn-graphs
mpm install matlab-rnn-dbscan

Manual installation

Usage

RnnDbscan is a class with a single public method, cluster. The results of the clustering operation are stored in read-only public properties.

Creating an RnnDbscan object:

% Create an RnnDbscan object using a 5-nearest-neighbor graph.
% nNeighborsIndex is how many neighbors used to create the knn index, and must be >= nNeighbors + 1
% because the index includes self-edges (each point is it's own nearest neighbor).
nNeighors = 5;
nNeighborsIndex = 6;
rnndbscan = RnnDbscan(data, nNeighbors, nNeighborsIndex);

% Use the NN Descent algorithm to create the knn index; this is much faster than an exhaustive search
rnndbscan = RnnDbscan(data, nNeighbors, nNeighborsIndex, 'Method', 'nndescent');

% Explicitly use an exhaustive search, which is the default
rnndbscan = RnnDbscan(data, nNeighbors, nNeighborsIndex, 'Method', 'knnsearch');

% Use a precomputed knn index
knnidx = knnindex(data, nNeighborsIndex);
rnndbscan = RnnDbscan(data, nNeighbors, knnidx);

Clustering:

rnndbscan.cluster();
% Or
cluster(rnndbscan);

% Inspect clusters, outliers, and labels
rnndbscan.Clusters
rnndbscan.Outliers
rnndbscan.Labels

For more details, see the help text: help RnnDbscan. RNN-DBSCAN tests.ipynb also contains many tests, which can be used as usage examples.

Contributing

All contributions are welcome! Just submit a pull request or open an issue.

引用

Trevor Vannoy (2022). RNN DBSCAN (https://github.com/tvannoy/matlab-rnn-dbscan/releases/tag/v1.0.1), GitHub. 取得済み .

MATLAB リリースの互換性
作成: R2020a
R2020a 以降と互換性あり
プラットフォームの互換性
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!
この GitHub アドオンでの問題を表示または報告するには、GitHub リポジトリにアクセスしてください。
この GitHub アドオンでの問題を表示または報告するには、GitHub リポジトリにアクセスしてください。