dragonpilot/selfdrive/controls/lib/cluster

C++ interface to fast hierarchical clustering algorithms
========================================================

This is a simplified C++ interface to fast implementations of hierarchical
clustering by Daniel Müllner. The original library with interfaces to R
and Python is described in:

Daniel Müllner: "fastcluster: Fast Hierarchical, Agglomerative Clustering
Routines for R and Python." Journal of Statistical Software 53 (2013),
no. 9, pp. 1–18, http://www.jstatsoft.org/v53/i09/


Usage of the library
--------------------

For using the library, the following source files are needed:

fastcluster_dm.cpp, fastcluster_R_dm.cpp
   original code by Daniel Müllner
   these are included by fastcluster.cpp via #include, and therefore
   need not be compiled to object code

fastcluster.[h|cpp]
   simplified C++ interface
   fastcluster.cpp is the only file that must be compiled

The library provides the clustering function *hclust_fast* for
creating the dendrogram information in an encoding as used by the
R function *hclust*. For a description of the parameters, see fastcluster.h.
Its parameter *method* can be one of

HCLUST_METHOD_SINGLE
  single link with the minimum spanning tree algorithm (Rohlf, 1973)

HHCLUST_METHOD_COMPLETE
  complete link with the nearest-neighbor-chain algorithm (Murtagh, 1984)

HCLUST_METHOD_AVERAGE
  complete link with the nearest-neighbor-chain algorithm (Murtagh, 1984)

HCLUST_METHOD_MEDIAN
  median link with the generic algorithm (Müllner, 2011)

For splitting the dendrogram into clusters, the two functions *cutree_k*
and *cutree_cdist* are provided.

Note that output parameters must be allocated beforehand, e.g.
  int* merge = new int[2*(npoints-1)];
For a complete usage example, see lines 135-142 of demo.cpp.


Demonstration program
---------------------

A simple demo is implemented in demo.cpp, which can be compiled and run with

   make
   ./hclust-demo -m complete lines.csv

It creates two clusters of line segments such that the segment angle between
line segments of different clusters have a maximum (cosine) dissimilarity.
For visualizing the result, plotresult.r can be used as follows
(requires R <https://r-project.org> to be installed):

  ./hclust-demo -m complete lines.csv | Rscript plotresult.r


Authors & Copyright
-------------------

Daniel Müllner, 2011, <http://danifold.net>
Christoph Dalitz, 2018, <http://www.hsnr.de/ipattern/>


License
-------

This code is provided under a BSD-style license.
See the file LICENSE for details.