Changeset 3718:aa32620f92ae in orange


Ignore:
Timestamp:
06/01/07 19:11:55 (7 years ago)
Author:
blaz <blaz.zupan@…>
Branch:
default
Convert:
6ee672cbcd11ef4700eff076631a4c6df072f497
Message:

added the definition of linkage types

File:
1 edited

Legend:

Unmodified
Added
Removed
  • orange/doc/reference/Clustering.htm

    r2653 r3718  
    2020<P>The distance should contain no negative elements. This limitation is due to implementation details of the algorithm (it is not absolutely necessary and can be lifted in future versions if often requested; it only helps the algorithm run a bit faster). The elements on the diagonal (representing the element's distance from itself) are ignored.</P> 
    2121 
    22 <P>Distance matrix can have the attribute <CODE>objects</CODE> describing the objects we are clustering (this is available only in Python). This can be any sequence of the same length as the matrix - an <CODE>ExampleTable</CODE>, a list of examples, a list of attributes (if you're clustering attributes), or even a string of the correct length. This attribute is not used in clustering but is only passed to the clusters' attribute <CODE>mapping</CODE> (see below), which will hold a reference to it (if you modify the list, the changes will affect the clusters as well).</P> 
     22<P>Distance matrix can have the attribute <CODE>objects</CODE> 
     23describing the objects we are clustering (this is available only in 
     24Python). This can be any sequence of the same length as the matrix - 
     25an <CODE>ExampleTable</CODE>, a list of examples, a list of attributes 
     26(if you're clustering attributes), or even a string of the correct 
     27length. This attribute is not used in clustering but is only passed to 
     28the clusters' attribute <CODE>mapping</CODE> (see below), which will 
     29hold a reference to it (if you modify the list, the changes will 
     30affect the clusters as well).</P> 
    2331 
    2432<P class=section>Attributes of <CODE>HierarchicalClustering</CODE></P> 
    2533<DL class=attributes> 
    2634<DT>linkage</DT> 
    27 <DD>Specifies the linkage method; it can be either <CODE>HierarchicalClustering.Single</CODE> (default), <CODE>HierarchicalClustering.Average</CODE> or <CODE>HierarchicalClustering.Complete</CODE>.</DD> 
     35<DD>Specifies the linkage method, which can be either 
     36<ol> 
     37  <li><CODE>HierarchicalClustering.Single</CODE> (default), where 
     38distance between groups is defined as the distance between the closest 
     39pair of objects, one from each group,</li> 
     40  <li><CODE>HierarchicalClustering.Average</CODE></li>, where the 
     41distance between two clusters is defined as the average of distances 
     42between all pairs of objects, where each pair is made up of one object 
     43from each group, or 
     44  <li><CODE>HierarchicalClustering.Complete</CODE>, where the distance 
     45between groups is defined as the distance between the most distant 
     46pair of objects, one from each group. Complete linkage is also called 
     47farthest neighbor.</li> 
     48</ol> 
     49</DD> 
    2850 
    2951<DT>overwriteMatrix</DT> 
Note: See TracChangeset for help on using the changeset viewer.