def testComputeOverlapsWithDiagonal(self):
data = scipy.sparse.csr_matrix([
[1, 1, 0, 1],
[0, 1, 1, 0],
[1, 1, 1, 1]
])
dists = HierarchicalClustering._computeOverlaps(data, selfOverlaps=True)
self.assertEqual(dists.shape, (6,))
self.assertEqual(dists.tolist(), [3, 1, 3, 2, 2, 4])
def testGetPrototypes(self):
data = scipy.sparse.csr_matrix([
[1, 1, 0, 1],
[1, 0, 1, 1],
[0, 1, 1, 0],
[1, 1, 1, 1]
])
overlaps = HierarchicalClustering._computeOverlaps(data)
prototypes = HierarchicalClustering._getPrototypes([0, 1, 2, 3], overlaps)
self.assertEqual(set(prototypes.tolist()), set([3]))
prototypes = HierarchicalClustering._getPrototypes([1, 2, 3], overlaps, 2)
self.assertEqual(set(prototypes.tolist()), set([3, 1]))
prototypes = HierarchicalClustering._getPrototypes([0, 2, 3], overlaps, 2)
self.assertEqual(set(prototypes.tolist()), set([3, 0]))
prototypes = HierarchicalClustering._getPrototypes([0, 1, 2], overlaps, 2)
self.assertEqual(set(prototypes.tolist()), set([0, 1]))
