|
<html><head><title>dlib C++ Library - chinese_whispers_abstract.h</title></head><body bgcolor='white'><pre> |
|
<font color='#009900'>// Copyright (C) 2012 Davis E. King ([email protected]) |
|
</font><font color='#009900'>// License: Boost Software License See LICENSE.txt for the full license. |
|
</font><font color='#0000FF'>#undef</font> DLIB_CHINESE_WHISPErS_ABSTRACT_Hh_ |
|
<font color='#0000FF'>#ifdef</font> DLIB_CHINESE_WHISPErS_ABSTRACT_Hh_ |
|
|
|
<font color='#0000FF'>#include</font> <font color='#5555FF'><</font>vector<font color='#5555FF'>></font> |
|
<font color='#0000FF'>#include</font> "<a style='text-decoration:none' href='../rand.h.html'>../rand.h</a>" |
|
<font color='#0000FF'>#include</font> "<a style='text-decoration:none' href='../graph_utils/ordered_sample_pair_abstract.h.html'>../graph_utils/ordered_sample_pair_abstract.h</a>" |
|
<font color='#0000FF'>#include</font> "<a style='text-decoration:none' href='../graph_utils/sample_pair_abstract.h.html'>../graph_utils/sample_pair_abstract.h</a>" |
|
|
|
<font color='#0000FF'>namespace</font> dlib |
|
<b>{</b> |
|
|
|
<font color='#009900'>// ---------------------------------------------------------------------------------------- |
|
</font> |
|
<font color='#0000FF'><u>unsigned</u></font> <font color='#0000FF'><u>long</u></font> <b><a name='chinese_whispers'></a>chinese_whispers</b> <font face='Lucida Console'>(</font> |
|
<font color='#0000FF'>const</font> std::vector<font color='#5555FF'><</font>ordered_sample_pair<font color='#5555FF'>></font><font color='#5555FF'>&</font> edges, |
|
std::vector<font color='#5555FF'><</font><font color='#0000FF'><u>unsigned</u></font> <font color='#0000FF'><u>long</u></font><font color='#5555FF'>></font><font color='#5555FF'>&</font> labels, |
|
<font color='#0000FF'>const</font> <font color='#0000FF'><u>unsigned</u></font> <font color='#0000FF'><u>long</u></font> num_iterations, |
|
dlib::rand<font color='#5555FF'>&</font> rnd |
|
<font face='Lucida Console'>)</font>; |
|
<font color='#009900'>/*! |
|
requires |
|
- is_ordered_by_index(edges) == true |
|
ensures |
|
- This function implements the graph clustering algorithm described in the |
|
paper: Chinese Whispers - an Efficient Graph Clustering Algorithm and its |
|
Application to Natural Language Processing Problems by Chris Biemann. |
|
- Interprets edges as a directed graph. That is, it contains the edges on the |
|
said graph and the ordered_sample_pair::distance() values define the edge |
|
weights (larger values indicating a stronger edge connection between the |
|
nodes). If an edge has a distance() value of infinity then it is considered |
|
a "must link" edge. |
|
- returns the number of clusters found. |
|
- #labels.size() == max_index_plus_one(edges) |
|
- for all valid i: |
|
- #labels[i] == the cluster ID of the node with index i in the graph. |
|
- 0 <= #labels[i] < the number of clusters found |
|
(i.e. cluster IDs are assigned contiguously and start at 0) |
|
- Duplicate edges are interpreted as if there had been just one edge with a |
|
distance value equal to the sum of all the duplicate edge's distance values. |
|
- The algorithm performs exactly num_iterations passes over the graph before |
|
terminating. |
|
!*/</font> |
|
|
|
<font color='#009900'>// ---------------------------------------------------------------------------------------- |
|
</font> |
|
<font color='#0000FF'><u>unsigned</u></font> <font color='#0000FF'><u>long</u></font> <b><a name='chinese_whispers'></a>chinese_whispers</b> <font face='Lucida Console'>(</font> |
|
<font color='#0000FF'>const</font> std::vector<font color='#5555FF'><</font>sample_pair<font color='#5555FF'>></font><font color='#5555FF'>&</font> edges, |
|
std::vector<font color='#5555FF'><</font><font color='#0000FF'><u>unsigned</u></font> <font color='#0000FF'><u>long</u></font><font color='#5555FF'>></font><font color='#5555FF'>&</font> labels, |
|
<font color='#0000FF'>const</font> <font color='#0000FF'><u>unsigned</u></font> <font color='#0000FF'><u>long</u></font> num_iterations, |
|
dlib::rand<font color='#5555FF'>&</font> rnd |
|
<font face='Lucida Console'>)</font>; |
|
<font color='#009900'>/*! |
|
ensures |
|
- This function is identical to the above chinese_whispers() routine except |
|
that it operates on a vector of sample_pair objects instead of |
|
ordered_sample_pairs. Therefore, this is simply a convenience routine. In |
|
particular, it is implemented by transforming the given edges into |
|
ordered_sample_pairs and then calling the chinese_whispers() routine defined |
|
above. |
|
!*/</font> |
|
|
|
<font color='#009900'>// ---------------------------------------------------------------------------------------- |
|
</font> |
|
<font color='#0000FF'><u>unsigned</u></font> <font color='#0000FF'><u>long</u></font> <b><a name='chinese_whispers'></a>chinese_whispers</b> <font face='Lucida Console'>(</font> |
|
<font color='#0000FF'>const</font> std::vector<font color='#5555FF'><</font>ordered_sample_pair<font color='#5555FF'>></font><font color='#5555FF'>&</font> edges, |
|
std::vector<font color='#5555FF'><</font><font color='#0000FF'><u>unsigned</u></font> <font color='#0000FF'><u>long</u></font><font color='#5555FF'>></font><font color='#5555FF'>&</font> labels, |
|
<font color='#0000FF'>const</font> <font color='#0000FF'><u>unsigned</u></font> <font color='#0000FF'><u>long</u></font> num_iterations <font color='#5555FF'>=</font> <font color='#979000'>100</font> |
|
<font face='Lucida Console'>)</font>; |
|
<font color='#009900'>/*! |
|
requires |
|
- is_ordered_by_index(edges) == true |
|
ensures |
|
- performs: return chinese_whispers(edges, labels, num_iterations, rnd) |
|
where rnd is a default initialized dlib::rand object. |
|
!*/</font> |
|
|
|
<font color='#009900'>// ---------------------------------------------------------------------------------------- |
|
</font> |
|
<font color='#0000FF'><u>unsigned</u></font> <font color='#0000FF'><u>long</u></font> <b><a name='chinese_whispers'></a>chinese_whispers</b> <font face='Lucida Console'>(</font> |
|
<font color='#0000FF'>const</font> std::vector<font color='#5555FF'><</font>sample_pair<font color='#5555FF'>></font><font color='#5555FF'>&</font> edges, |
|
std::vector<font color='#5555FF'><</font><font color='#0000FF'><u>unsigned</u></font> <font color='#0000FF'><u>long</u></font><font color='#5555FF'>></font><font color='#5555FF'>&</font> labels, |
|
<font color='#0000FF'>const</font> <font color='#0000FF'><u>unsigned</u></font> <font color='#0000FF'><u>long</u></font> num_iterations <font color='#5555FF'>=</font> <font color='#979000'>100</font> |
|
<font face='Lucida Console'>)</font>; |
|
<font color='#009900'>/*! |
|
ensures |
|
- performs: return chinese_whispers(edges, labels, num_iterations, rnd) |
|
where rnd is a default initialized dlib::rand object. |
|
!*/</font> |
|
|
|
<font color='#009900'>// ---------------------------------------------------------------------------------------- |
|
</font> |
|
<b>}</b> |
|
|
|
<font color='#0000FF'>#endif</font> <font color='#009900'>// DLIB_CHINESE_WHISPErS_ABSTRACT_Hh_ |
|
</font> |
|
|
|
</pre></body></html> |
