From 30bf945095e193c7a350d6482739f7297d52e574 Mon Sep 17 00:00:00 2001
From: Davis King <davis@dlib.net>
Date: Fri, 30 May 2008 22:52:51 +0000
Subject: [PATCH] Added a kkmeans example

--HG--
extra : convert_revision : svn%3Afdd8eb12-d10e-0410-9acb-85c331704f74/trunk%402283
---
 examples/kkmeans_ex.cpp | 125 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 125 insertions(+)
 create mode 100644 examples/kkmeans_ex.cpp

diff --git a/examples/kkmeans_ex.cpp b/examples/kkmeans_ex.cpp
new file mode 100644
index 000000000..984411495
--- /dev/null
+++ b/examples/kkmeans_ex.cpp
@@ -0,0 +1,125 @@
+/*
+    This is an example illustrating the use of the kkmeans object 
+    from the dlib C++ Library.
+
+    The kkmeans object is an implementation of a kernelized k-means clustering 
+    algorithm.  It is implemented by using the kcentroid object to represent 
+    each center found by the usual k-means clustering algorithm.  
+
+    So this object allows you to perform non-linear clustering in the same way 
+    a svm classifier finds non-linear decision surfaces.  
+    
+    This example will make points from 3 classes and perform kernelized k-means 
+    clustering on those points.
+
+    The classes are as follows:
+        - points very close to the origin
+        - points on the circle of radius 10 around the origin
+        - points that are on a circle of radius 4 but not around the origin at all
+*/
+
+#include <iostream>
+#include <vector>
+
+#include "dlib/svm.h"
+#include "dlib/rand.h"
+
+using namespace std;
+using namespace dlib;
+
+int main()
+{
+    // Here we declare that our samples will be 2 dimensional column vectors.  
+    typedef matrix<double,2,1> sample_type;
+
+    // Now we are making a typedef for the kind of kernel we want to use.  I picked the
+    // radial basis kernel because it only has one parameter and generally gives good
+    // results without much fiddling.
+    typedef radial_basis_kernel<sample_type> kernel_type;
+
+    // Here we declare an instance of the kcentroid object.  The first argument to the constructor
+    // is the kernel we wish to use.  The second is a parameter that determines the numerical 
+    // accuracy with which the object will perform part of the learning algorithm.  Generally
+    // smaller values give better results but cause the algorithm to run slower.  You just have
+    // to play with it to decide what balance of speed and accuracy is right for your problem.
+    // Here we have set it to 0.01.
+    kcentroid<kernel_type> kc(kernel_type(0.1),0.01);
+
+    // Now we make an instance of the kkmeans object and tell it to use kcentroid objects
+    // that are configured with the parameters from the kc object we defined above.
+    kkmeans<kernel_type> test(kc);
+
+    std::vector<sample_type> samples;
+    std::vector<sample_type> initial_centers;
+
+    sample_type m;
+
+    dlib::rand::float_1a rnd;
+
+    // we will make 25 points from each class
+    const long num = 25;
+
+    // make some samples near the origin
+    double radius = 0.5;
+    for (long i = 0; i < num; ++i)
+    {
+        m(0) = 2*radius*rnd.get_random_double()-radius;
+        m(1) = sqrt(radius*radius - m(0)*m(0));
+
+        // add this sample to our set of samples we will run k-means 
+        samples.push_back(m);
+    }
+
+    // make some samples in a circle around the origin but far away
+    radius = 10.0;
+    for (long i = 0; i < num; ++i)
+    {
+        m(0) = 2*radius*rnd.get_random_double()-radius;
+        m(1) = sqrt(radius*radius - m(0)*m(0));
+
+        // add this sample to our set of samples we will run k-means 
+        samples.push_back(m);
+    }
+
+    // make some samples in a circle around the point (20,20) 
+    radius = 4.0;
+    for (long i = 0; i < num; ++i)
+    {
+        m(0) = 2*radius*rnd.get_random_double()-radius;
+        m(1) = sqrt(radius*radius - m(0)*m(0));
+
+        // translate this point away from the origin
+        m(0) += 25;
+        m(1) += 25;
+
+        // add this sample to our set of samples we will run k-means 
+        samples.push_back(m);
+    }
+
+    // tell the kkmeans object we made that we want to run k-means with k set to 3. 
+    // (i.e. we want 3 clusters)
+    test.set_number_of_centers(3);
+
+    // You need to pick some initial centers for the k-means algorithm.  So here
+    // we will pick a point from each of the classes.
+    initial_centers.push_back(samples[0]);
+    initial_centers.push_back(samples[num]);
+    initial_centers.push_back(samples[num*2]);
+
+    // now run the k-means algorithm on our set of samples.  Note that the train function expects
+    // its arguments to be dlib::matrix objects so since we have our samples in std::vector objects
+    // we need to turn them into matrix objects.  The vector_to_matrix() function does this for us.
+    test.train(vector_to_matrix(samples),vector_to_matrix(initial_centers));
+
+    // now loop over all our samples and print out their predicted class.  In this example
+    // all points are correctly identified.
+    for (unsigned long i = 0; i < samples.size()/3; ++i)
+    {
+        cout << test(samples[i]) << " ";
+        cout << test(samples[i+num]) << " ";
+        cout << test(samples[i+2*num]) << "\n";
+    }
+
+}
+
+