jarvisPatrick_c


	  A matrix of integers. Non integer matricies will be coerced. 
	  Each row represensts one element, indexed 1 to N. The values in row
	  i should be the index value of the neighbors of i. Thus, each value should 
	  itself be a valid row index. 


neighbors


	  The minimum number of common neibhbors needed for two elements to be merged.


minNbrs


	  If true, only the neibhors given in each row are checked to see if they share <code>minNbrs</code> 
	  neighbors in common. If false, all pairs of elements are compared. For a matrix of size NxM,
	  the first method yeilds a running time of O(NM), while the second yeilds a running time of O(N^2).


fast


	  If true, two elements must contain each other in their neighbor list in order to be merged.
	  If false and fast is true, then only one element must contain the other as a neighbor. If
	  false and fast is false, than neither element must contain the other as a neighbor, though
	  in all cases there must still be at least <code>minNbrs</code> neibhros in common.


bothDirections


		See <code><a rd-options="" href="/link/jarvisPatrick?package=ChemmineR&version=2.24.2" data-mini-rdoc="ChemmineR::jarvisPatrick">jarvisPatrick</a></code> for details.
	

linkage


	This not meant to be used directly, use <code><a rd-options="" href="/link/jarvisPatrick?package=ChemmineR&version=2.24.2" data-mini-rdoc="ChemmineR::jarvisPatrick">jarvisPatrick</a></code> instead. It is exposed so other
	libraries can make use of it.


ChemmineR is a cheminformatics package for analyzing drug-like small molecule data in R. Its latest version contains functions for efficient processing of large numbers of molecules, physicochemical/structural property predictions, structural similarity searching, classification and clustering of compound libraries with a wide spectrum of algorithms. In addition, it offers visualization functions for compound clustering results and chemical structures.

Thomas Girke

ChemmineR

Cheminformatics Toolkit for R

jarvisPatrick_c function

A matrix of integers. Non integer matricies will be coerced. 
	  Each row represensts one element, indexed 1 to N. The values in row
	  i should be the index value of the neighbors of i. Thus, each value should 
	  itself be a valid row index.

The minimum number of common neibhbors needed for two elements to be merged.

If true, only the neibhors given in each row are checked to see if they share <code>minNbrs</code> 
	  neighbors in common. If false, all pairs of elements are compared. For a matrix of size NxM,
	  the first method yeilds a running time of O(NM), while the second yeilds a running time of O(N^2).

If true, two elements must contain each other in their neighbor list in order to be merged.
	  If false and fast is true, then only one element must contain the other as a neighbor. If
	  false and fast is false, than neither element must contain the other as a neighbor, though
	  in all cases there must still be at least <code>minNbrs</code> neibhros in common.

See <code><a href="jarvisPatrick" rd-options="">jarvisPatrick</a></code> for details.

This not meant to be used directly, use <code><a href="jarvisPatrick" rd-options="">jarvisPatrick</a></code> instead. It is exposed so other
	libraries can make use of it.

jarvisPatrick_c: Jarvis Patrick Clustering in C code

Description

Usage

Arguments

Value