Merge branch 'release-1.2.0' into develop

Author: exhuma

CHANGELOG

@@ -1,6 +1,9 @@
 1.2.0
+   - Multiprocessing (by loisaidasam)
    - Python 3 support
    - Split up one big file into smaller more logical sub-modules
+   - Fixed https://github.com/exhuma/python-cluster/issues/11
+   - Documentation update.
 
 1.1.1b3
    - Fixed bug #1727558

cluster/method/hierarchical.py

@@ -31,7 +31,7 @@ class HierarchicalClustering(BaseClusterMethod):
     Implementation of the hierarchical clustering method as explained in a
     tutorial_ by *matteucc*.
 
-    .. _tutorial:: http://www.elet.polimi.it/upload/matteucc/Clustering/tutorial_html/hierarchical.html
+    .. _tutorial: http://www.elet.polimi.it/upload/matteucc/Clustering/tutorial_html/hierarchical.html
 
     Example:
 
@@ -61,7 +61,7 @@ def __init__(self, data, distance_function, linkage=None, num_processes=1):
             linkage = 'single'
         logger.info("Initializing HierarchicalClustering object with linkage "
                     "method %s", linkage)
-        BaseClusterMethod.__init__(self, data, distance_function)
+        BaseClusterMethod.__init__(self, sorted(data), distance_function)
         self.set_linkage_method(linkage)
         self.num_processes = num_processes
         self.__cluster_created = False

docs/index.rst

@@ -3,14 +3,10 @@ Welcome to python-cluster's documentation!
 
 Implementation of cluster algorithms in pure Python.
 
-.. warning::
 
-    This is currently a bug in HierarchicalClustering which causes incorrect
-    output. This is currently being worked on. In the meantime
-    ``HierarchicalClustering`` should be regarded as *broken*!
 
-Example
--------
+Example for K-Means Clustering
+------------------------------
 
 ::
 
@@ -30,7 +26,7 @@ Example
         (9, 3)
     ]
     cl = KMeansClustering(data)
-    c.getclusters(2)
+    cl.getclusters(2)
 
 The above code would give the following result::
 
@@ -39,6 +35,44 @@ The above code would give the following result::
         [(3, 5), (1, 5), (3, 4), (2, 6), (2, 5), (3, 6)]
     ]
 
+
+Example for Hierarchical Clustering
+-----------------------------------
+
+::
+
+    from cluster import HierarchicalClustering
+    data = [791, 956, 676, 124, 564, 84, 24, 365, 594, 940, 398,
+            971, 131, 365, 542, 336, 518, 835, 134, 391]
+    cl = HierarchicalClustering(data)
+    cl.getlevel(40)
+
+The above code would give the following result::
+
+    [
+        [24],
+        [84, 124, 131, 134],
+        [336, 365, 365, 391, 398],
+        [676],
+        [594, 518, 542, 564],
+        [940, 956, 971],
+        [791],
+        [835],
+    ]
+
+
+Using :py:meth:`~cluster.method.hierarchical.HierarchicalClustering.getlevel()`
+returns clusters where the distance between each cluster is no less than
+*level*.
+
+.. note::
+
+    Due to a bug_ in earlier releases, the elements of the input data *must be*
+    sortable!
+
+    .. _bug: https://github.com/exhuma/python-cluster/issues/11
+
+
 API
 ---
 

test.py

@@ -71,22 +71,22 @@ class HClusterIntegerTestCase(unittest.TestCase):
 
     def setUp(self):
         self.__data = [791, 956, 676, 124, 564, 84, 24, 365, 594, 940, 398,
-                            971, 131, 365, 542, 336, 518, 835, 134, 391]
+                       971, 131, 365, 542, 336, 518, 835, 134, 391]
 
     def testCluster(self):
         "Basic Hierarchical Clustering test with integers"
         cl = HierarchicalClustering(self.__data, lambda x, y: abs(x - y))
         cl.cluster()
         self.assertEqual([
-                [24],
-                [84, 124, 131, 134],
-                [336, 365, 365, 365, 398, 391],
-                [940, 956, 971],
-                [791],
-                [835],
-                [676],
-                [518, 564, 542]],
-                cl.getlevel(40))
+            [24],
+            [84, 124, 131, 134],
+            [336, 365, 365, 391, 398],
+            [676],
+            [594, 518, 542, 564],
+            [940, 956, 971],
+            [791],
+            [835],
+        ], cl.getlevel(40))
 
     def testUnmodifiedData(self):
         cl = HierarchicalClustering(self.__data, lambda x, y: abs(x - y))
@@ -102,9 +102,9 @@ def sim(self, x, y):
         return 1 - sm.ratio()
 
     def setUp(self):
-        self.__data = ("Lorem ipsum dolor sit amet, consectetuer adipiscing "
-                "elit. Ut elit. Phasellus consequat ultricies mi. Sed congue "
-                "leo at neque. Nullam."). split()
+        self.__data = ("Lorem ipsum dolor sit amet consectetuer adipiscing "
+                       "elit Ut elit Phasellus consequat ultricies mi Sed "
+                       "congue leo at neque Nullam").split()
 
     def testDataTypes(self):
         "Test for bug #?"
@@ -118,19 +118,17 @@ def testCluster(self):
         "Basic Hierachical clustering test with strings"
         cl = HierarchicalClustering(self.__data, self.sim)
         self.assertEqual([
-                    ['Nullam.'],
-                    ['Sed'],
-                    ['mi.'],
-                    ['ultricies'],
-                    ['Phasellus'],
-                    ['amet,', 'at'],
-                    ['sit', 'elit.', 'elit.', 'elit.'],
-                    ['leo', 'Lorem', 'dolor'],
-                    ['neque.', 'congue', 'consectetuer', 'consequat'],
-                    ['ipsum'],
-                    ['adipiscing']
-                    ],
-                cl.getlevel(0.5))
+            ['ultricies'],
+            ['Sed'],
+            ['Phasellus'],
+            ['mi'],
+            ['Nullam'],
+            ['sit', 'elit', 'elit', 'Ut', 'amet', 'at'],
+            ['leo', 'Lorem', 'dolor'],
+            ['congue', 'neque', 'consectetuer', 'consequat'],
+            ['adipiscing'],
+            ['ipsum'],
+        ], cl.getlevel(0.5))
 
     def testUnmodifiedData(self):
         cl = HierarchicalClustering(self.__data, self.sim)