Merge branch 'feature/progress-callback' into develop

Author: exhuma

cluster/method/base.py

@@ -39,11 +39,12 @@ class BaseClusterMethod(object):
         they are comparable, it's ok.
     """
 
-    def __init__(self, input, distance_function):
+    def __init__(self, input, distance_function, progress_callback=None):
         self.distance = distance_function
         self._input = input    # the original input
         self._data = input[:]  # clone the input so we can work with it
                                # without distroying the original data.
+        self.progress_callback = progress_callback
 
     def topo(self):
         """

cluster/method/hierarchical.py

@@ -57,16 +57,22 @@ class HierarchicalClustering(BaseClusterMethod):
         evenly.
     """
 
-    def __init__(self, data, distance_function, linkage=None, num_processes=1):
+    def __init__(self, data, distance_function, linkage=None, num_processes=1,
+                 progress_callback=None):
         if not linkage:
             linkage = single
         logger.info("Initializing HierarchicalClustering object with linkage "
                     "method %s", linkage)
         BaseClusterMethod.__init__(self, sorted(data), distance_function)
         self.set_linkage_method(linkage)
         self.num_processes = num_processes
+        self.progress_callback = progress_callback
         self.__cluster_created = False
 
+    def publish_progress(self, total, current):
+        if self.progress_callback:
+            self.progress_callback(total, current)
+
     def set_linkage_method(self, method):
         """
         Sets the method to determine the distance between two clusters.
@@ -107,6 +113,7 @@ def cluster(self, matrix=None, level=None, sequence=None):
 
         # if the matrix only has two rows left, we are done
         linkage = partial(self.linkage, distance_function=self.distance)
+        initial_element_count = len(self._data)
         while len(matrix) > 2 or matrix == []:
 
             item_item_matrix = Matrix(self._data,
@@ -151,6 +158,8 @@ def cluster(self, matrix=None, level=None, sequence=None):
                                              smallestpair[1])])  # remove item 2
             self._data.append(cluster)  # append item 1 and 2 combined
 
+            self.publish_progress(initial_element_count, len(self._data))
+
         # all the data is in one single cluster. We return that and stop
         self.__cluster_created = True
         logger.info("Call to cluster() is complete")