Added some logging

Should be helpful for when the matrix is huge

Author: loisaidasam

cluster/method/hierarchical.py

@@ -15,12 +15,16 @@
 # Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
 #
 
+import logging
 
 from cluster.cluster import Cluster
 from cluster.method.base import BaseClusterMethod
 from cluster.util import median, mean, genmatrix
 
 
+logger = logging.getLogger(__name__)
+
+
 class HierarchicalClustering(BaseClusterMethod):
     """
     Implementation of the hierarchical clustering method as explained in
@@ -37,15 +41,17 @@ class HierarchicalClustering(BaseClusterMethod):
         Note that all of the returned clusters are more that 90 apart
     """
 
-    def __init__(self, data, distance_function, linkage='single'):
+    def __init__(self, data, distance_function, linkage=None):
         """
         Constructor
 
         See BaseClusterMethod.__init__ for more details.
         """
+        if not linkage:
+            linkage = 'single'
+        logger.info("Initializing HierarchicalClustering object with linkage method %s",
+                    linkage)
         BaseClusterMethod.__init__(self, data, distance_function)
-
-        # set the linkage type to single
         self.set_linkage_method(linkage)
         self.__cluster_created = False
 
@@ -199,6 +205,7 @@ def cluster(self, matrix=None, level=None, sequence=None):
             level    -  The current level of clustering
             sequence -  The sequence number of the clustering
         """
+        logger.info("Performing cluster()")
 
         if matrix is None:
             # create level 0, first iteration (sequence)
@@ -247,6 +254,7 @@ def cluster(self, matrix=None, level=None, sequence=None):
 
         # all the data is in one single cluster. We return that and stop
         self.__cluster_created = True
+        logger.info("Call to cluster() is complete")
         return
 
     def getlevel(self, threshold):

cluster/util.py

@@ -15,6 +15,11 @@
 # Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
 #
 
+import logging
+
+
+logger = logging.getLogger(__name__)
+
 
 class ClusteringError(Exception):
     pass
@@ -100,12 +105,12 @@ def genmatrix(data, combinfunc, symmetric=False, diagonal=None):
                       will be "0".  If this value is set to None, then the
                       diagonal will be calculated.  Default: None
     """
+    logger.info("Generating matrix for %s items - O(n^2)", len(data))
     matrix = []
-    row_index = 0
-    for item in data:
+    for row_index, item in enumerate(data):
+        logger.debug("Generating row %s", row_index)
         row = []
-        col_index = 0
-        for item2 in data:
+        for col_index, item2 in enumerate(data):
             if diagonal is not None and col_index == row_index:
                 # if this is a cell on the diagonal
                 row.append(diagonal)
@@ -116,9 +121,8 @@ def genmatrix(data, combinfunc, symmetric=False, diagonal=None):
             else:
                 # if this cell is not on the diagonal
                 row.append(combinfunc(item, item2))
-            col_index += 1
         matrix.append(row)
-        row_index += 1
+    logger.info("Matrix generated")
     return matrix