OpenMS
ClusterAnalyzer.h
Go to the documentation of this file.
1 // --------------------------------------------------------------------------
2 // OpenMS -- Open-Source Mass Spectrometry
3 // --------------------------------------------------------------------------
4 // Copyright The OpenMS Team -- Eberhard Karls University Tuebingen,
5 // ETH Zurich, and Freie Universitaet Berlin 2002-2023.
6 //
7 // This software is released under a three-clause BSD license:
8 // * Redistributions of source code must retain the above copyright
9 // notice, this list of conditions and the following disclaimer.
10 // * Redistributions in binary form must reproduce the above copyright
11 // notice, this list of conditions and the following disclaimer in the
12 // documentation and/or other materials provided with the distribution.
13 // * Neither the name of any author or any participating institution
14 // may be used to endorse or promote products derived from this software
15 // without specific prior written permission.
16 // For a full list of authors, refer to the file AUTHORS.
17 // --------------------------------------------------------------------------
18 // THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
19 // AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
20 // IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
21 // ARE DISCLAIMED. IN NO EVENT SHALL ANY OF THE AUTHORS OR THE CONTRIBUTING
22 // INSTITUTIONS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
23 // EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
24 // PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
25 // OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
26 // WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
27 // OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
28 // ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
29 //
30 // --------------------------------------------------------------------------
31 // $Maintainer: Mathias Walzer $
32 // $Authors: $
33 // --------------------------------------------------------------------------
34 
35 #pragma once
36 
39 
40 #include <vector>
41 
42 namespace OpenMS
43 {
44  class String;
45 
51  class OPENMS_DLLAPI ClusterAnalyzer
52  {
53 public:
56 
59 
61  virtual ~ClusterAnalyzer();
62 
73  std::vector<float> averageSilhouetteWidth(const std::vector<BinaryTreeNode> & tree, const DistanceMatrix<float> & original);
74 
83  std::vector<float> dunnIndices(const std::vector<BinaryTreeNode> & tree, const DistanceMatrix<float> & original, const bool tree_from_singlelinkage = false);
84 
92  std::vector<float> cohesion(const std::vector<std::vector<Size> > & clusters, const DistanceMatrix<float> & original);
93 
103  float averagePopulationAberration(Size cluster_quantity, std::vector<BinaryTreeNode> & tree);
104 
120  void cut(const Size cluster_quantity, const std::vector<BinaryTreeNode> & tree, std::vector<std::vector<Size> > & clusters);
121 
133  void cut(const Size cluster_quantity, const std::vector<BinaryTreeNode> & tree, std::vector<std::vector<BinaryTreeNode> > & subtrees);
134 
143  String newickTree(const std::vector<BinaryTreeNode> & tree, const bool include_distance = false);
144 
145 private:
148 
149  };
152 
153 }
Elements of a binary tree used to represent a hierarchical clustering process.
Definition: BinaryTreeNode.h:49
Bundles analyzing tools for a clustering (given as sequence of BinaryTreeNode's)
Definition: ClusterAnalyzer.h:52
std::vector< float > cohesion(const std::vector< std::vector< Size > > &clusters, const DistanceMatrix< float > &original)
Method to calculate the cohesions of a certain partition.
void cut(const Size cluster_quantity, const std::vector< BinaryTreeNode > &tree, std::vector< std::vector< Size > > &clusters)
Method to calculate a partition resulting from a certain step in clustering given by the number of cl...
ClusterAnalyzer & operator=(const ClusterAnalyzer &source)
assignment operator
virtual ~ClusterAnalyzer()
destructor
std::vector< float > averageSilhouetteWidth(const std::vector< BinaryTreeNode > &tree, const DistanceMatrix< float > &original)
Method to calculate the average silhouette widths for a clustering.
ClusterAnalyzer(const ClusterAnalyzer &source)
copy constructor
float averagePopulationAberration(Size cluster_quantity, std::vector< BinaryTreeNode > &tree)
Method to calculate the average aberration from average population in partition resulting from a cert...
std::vector< float > dunnIndices(const std::vector< BinaryTreeNode > &tree, const DistanceMatrix< float > &original, const bool tree_from_singlelinkage=false)
Method to calculate Dunns indices for a clustering.
void cut(const Size cluster_quantity, const std::vector< BinaryTreeNode > &tree, std::vector< std::vector< BinaryTreeNode > > &subtrees)
Method to calculate subtrees from a given tree resulting from a certain step in clustering given by t...
String newickTree(const std::vector< BinaryTreeNode > &tree, const bool include_distance=false)
Returns the hierarchy described by a clustering tree as Newick-String.
ClusterAnalyzer()
default constructor
A two-dimensional distance matrix, similar to OpenMS::Matrix.
Definition: DistanceMatrix.h:68
A more convenient string class.
Definition: String.h:60
size_t Size
Size type e.g. used as variable which can hold result of size()
Definition: Types.h:127
Main OpenMS namespace.
Definition: FeatureDeconvolution.h:48
bool compareBinaryTreeNode(const BinaryTreeNode &x, const BinaryTreeNode &y)
returns the value of (x.distance < y.distance) for use with sort