clueless-kmean now takes as parameter in which mode to work, and test.sh generate...

[clueless-kmeans.git] / clusterer.h

diff --git a/clusterer.h b/clusterer.h
index 065dd3f..a0a29f9 100644 (file)
--- a/clusterer.h
+++ b/clusterer.h
@@ -30,34 +30,39 @@
 class Clusterer {
 public:
 
-  enum { STANDARD_ASSOCIATION, STANDARD_LP_ASSOCIATION, UNINFORMATIVE_LP_ASSOCIATION };
+  enum {
+    STANDARD_ASSOCIATION,
+    STANDARD_LP_ASSOCIATION,
+    UNINFORMATIVE_LP_ASSOCIATION
+  };
 
   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);
 
-  // Does the standard hard k-mean association
+  // Standard hard k-mean association
 
   scalar_t baseline_cluster_association(int nb_points, scalar_t **points,
                                         int nb_classes, int *labels,
                                         scalar_t **gamma);
 
-  // Does the same with an LP formulation, as a sanity check
+  // Standard k-mean 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);
 
-  // Does the association under constraints that each cluster gets
-  // associated clusters with the same class proportion as the overall
-  // training set
+  // 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,