Diff for "UPGMA" - BioHackersNet

Differences between revisions 3 and 5 (spanning 2 versions)

One of the Clustering methods. AverageLinkage method

It works by Clustering the nodes, at each stage amalgamating two clusters and at the same time creating a new node on a tree.

두 cluster사이의 거리는 다음의 공식에 의해서 계산된다.

$d_{ij} = \frac{1}{|C_{i}||C_{j}|} \sum_{p \ in \ C_{i}, q \ in \ C_{j}} d_{pq}$

여기서의 |Ci|는 클러스터내 노드의 갯수를 의미한다. Ck가 Ci와 Cj의 합집합관계에 있을때 Cl과의 거리는 다음처럼 쉽게 계산될 수 있다.

$d_{kl} = \frac{d_{il}|C_{i}| + d_{jl}|C_{j}|}{|C_{i}| + |C_{j}|}$

소스코드참고. Cluster.py

-  ⇤ ← Revision 3 as of 2011-08-03 11:00:45 → 
  Size: 826
  Editor: localhost
  Comment: converted to 1.6 markup
+   ← Revision 5 as of 2012-09-03 13:06:23 → ⇥
  Size: 832
  Editor: 182
  Comment:
-Deletions are marked like this.
+Additions are marked like this.
 Line 3:
-One of the [Clustering] methods. AverageLinkage method
+One of the [[Clustering]] methods. AverageLinkage method
 Line 8:
-It works by [Clustering] the nodes, at each stage amalgamating two clusters and at the same time creating a new node on a tree.
+It works by [[Clustering]] the nodes, at each stage amalgamating two clusters and at the same time creating a new node on a tree.
 Line 23:
-소스코드참고. [Cluster.py]
+소스코드참고. [[Cluster.py]]