Added README.md

[clueless-kmeans.git] / clusterer.h

diff --git a/clusterer.h b/clusterer.h
index 88c168a..6fa5382 100644 (file)
--- a/clusterer.h
+++ b/clusterer.h
@@ -1,17 +1,17 @@
 /*
- *  clueless-kmean is a variant of k-mean which enforces balanced
+ *  clueless-kmeans is a variant of k-means which enforces balanced
  *  distribution of classes in every cluster
  *
  *  Copyright (c) 2013 Idiap Research Institute, http://www.idiap.ch/
  *  Written by Francois Fleuret <francois.fleuret@idiap.ch>
  *
- *  This file is part of clueless-kmean.
+ *  This file is part of clueless-kmeans.
  *
- *  clueless-kmean is free software: you can redistribute it and/or
+ *  clueless-kmeans is free software: you can redistribute it and/or
  *  modify it under the terms of the GNU General Public License
  *  version 3 as published by the Free Software Foundation.
  *
- *  clueless-kmean is distributed in the hope that it will be useful,
+ *  clueless-kmeans is distributed in the hope that it will be useful,
  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  *  General Public License for more details.
@@ -29,35 +29,65 @@
 
 class Clusterer {
 public:
+
+  enum {
+    // Standard k-mean
+    STANDARD_ASSOCIATION,
+    // Same, implemented as a LP problem for sanity check
+    STANDARD_LP_ASSOCIATION,
+    // Criterion forcing to have the same distribution of classes in
+    // all clusters
+    UNINFORMATIVE_LP_ASSOCIATION,
+    // Criterion forcing to have the same number of samples of each
+    // class in all clusters
+    UNINFORMATIVE_LP_ASSOCIATION_ABSOLUTE
+  };
+
   const static int max_nb_iterations = 10;
   const static scalar_t min_iteration_improvement = 0.999;
+  const static scalar_t min_cluster_variance = 0.01f;
 
   int _nb_clusters;
   int _dim;
+
   scalar_t **_cluster_means, **_cluster_var;
 
+  scalar_t distance_to_centroid(scalar_t *x, int k);
+
   void initialize_clusters(int nb_points, scalar_t **points);
 
+  // Standard hard k-means association
+
   scalar_t baseline_cluster_association(int nb_points, scalar_t **points,
                                         int nb_classes, int *labels,
                                         scalar_t **gamma);
 
+  // Standard k-means association implemented as an LP optimization
+
   scalar_t baseline_lp_cluster_association(int nb_points, scalar_t **points,
                                            int nb_classes, int *labels,
                                            scalar_t **gamma);
 
+  // Association under the constraint that each cluster gets the same
+  // class proportions as the overall training set
+
   scalar_t uninformative_lp_cluster_association(int nb_points, scalar_t **points,
                                                 int nb_classes, int *labels,
-                                                scalar_t **gamma);
+                                                scalar_t **gamma,
+                                                int absolute_proportion);
 
-  void baseline_update_clusters(int nb_points, scalar_t **points, scalar_t **gamma);
+  void update_clusters(int nb_points, scalar_t **points, scalar_t **gamma);
 
 public:
   Clusterer();
   ~Clusterer();
-  void train(int nb_clusters, int dim,
+
+  void train(int mode,
+             int nb_clusters, int dim,
              int nb_points, scalar_t **points,
              int nb_classes, int *labels,
+             // This last array returns for each sample to what
+             // cluster it was associated. It can be null.
              int *cluster_associations);
 
   int cluster(scalar_t *point);