# HG changeset patch
# User Nicolas Saunier <nicolas.saunier@polymtl.ca>
# Date 1439243509 14400
# Node ID 4e89341edd29f6fe41b9a0fc668e27da030446bb
# Parent  85af65b6d5317852b4b243857330f66d601c86d7
added the capability to enforce a minimum cluster size and re-assign the indicators to other clusters

diff -r 85af65b6d531 -r 4e89341edd29 python/events.py
--- a/python/events.py	Sat Jul 25 23:28:52 2015 -0400
+++ b/python/events.py	Mon Aug 10 17:51:49 2015 -0400
@@ -295,13 +295,15 @@
         print('unknown type of point: '+pointType)
     return allPoints
 
-def prototypeCluster(interactions, similarityMatrix, alignmentMatrix, indicatorName, minSimilarity):
+def prototypeCluster(interactions, similarityMatrix, alignmentMatrix, indicatorName, minSimilarity, minClusterSize = None):
     '''Finds exemplar indicator time series for all interactions
     Returns the prototype indices (in the interaction list) and the label of each indicator (interaction)
 
     if an indicator profile (time series) is different enough (<minSimilarity), 
     it will become a new prototype. 
-    Non-prototype interactions will be assigned to an existing prototype'''
+    Non-prototype interactions will be assigned to an existing prototype
+    if minClusterSize is not None, the clusters will be refined by removing iteratively the smallest clusters
+    and reassigning all elements in the cluster until no cluster is smaller than minClusterSize'''
 
     # sort indicators based on length
     indices = range(similarityMatrix.shape[0])
@@ -320,13 +322,22 @@
              prototypeIndices.append(i)
 
     # assignment
-    labels = [-1]*similarityMatrix.shape[0]
     indices = [i for i in range(similarityMatrix.shape[0]) if i not in prototypeIndices]
-    for i in prototypeIndices:
-        labels[i] = i
-    for i in indices:
-        prototypeIndex = similarityMatrix[i][prototypeIndices].argmax()
-        labels[i] = prototypeIndices[prototypeIndex]
+    assign = True
+    while assign:
+        labels = [-1]*similarityMatrix.shape[0]
+        for i in prototypeIndices:
+            labels[i] = i
+        for i in indices:
+            prototypeIndex = similarityMatrix[i][prototypeIndices].argmax()
+            labels[i] = prototypeIndices[prototypeIndex]
+        clusterSizes = {i: sum(np.array(labels) == i) for i in prototypeIndices}
+        smallestClusterIndex = min(clusterSizes, key = clusterSizes.get) 
+        assign = (clusterSizes[smallestClusterIndex] < minClusterSize)
+        print prototypeIndices, smallestClusterIndex, clusterSizes[smallestClusterIndex]
+        if assign:
+            prototypeIndices.remove(smallestClusterIndex)
+            indices.append(smallestClusterIndex)
 
     return prototypeIndices, labels