def testMakePricesDifferencesVectors(self):
diff_vecs = utils.make_prices_diffs_vecs(self.data1)
self.assertEqual(diff_vecs, [[-0.5, 1.5, 10.0], [7.0, 1.0, 1.0]])
data3 = [["A", {0: 1, 1: 1}], ["B", {0: 1, 1: 1}]]
diff_vecs = utils.make_prices_diffs_vecs(data3)
self.assertEqual(diff_vecs, [[0], [0]])
def testPricesDiffsVecsKmeansClustering(self):
"""Testing whether kmeans clustering with prices differences
vectors works."""
prices_diffs_vecs = utils.make_prices_diffs_vecs(self.data1)
labels, wcss, n = Pycluster.kcluster(prices_diffs_vecs, 3, npass=100)
clusters = utils.make_groups_from_labels(labels, self.data1)
# The result should be sth like this modulo group numbers. Probability
# that this isn't like this with npass=100 is (I think) very low! But
# it can happen that this grouping will be different.
suggested_clusters = {0: ['E'], 1: ['A', 'D'], 2: ['B', 'C']}
# Let's check this.
num_matches = 0
for cluster in clusters.values():
cluster.sort()
for suggested_cluster in suggested_clusters.values():
suggested_cluster.sort()
if cluster == suggested_cluster:
num_matches = num_matches + 1
# Ok, so we've found out that each suggested cluster exists
# in output of our kcluster algorithm and because length of
# clusters dict is 3 we can be sure these dictionaries are equal.
self.assertEqual(num_matches, 3)
self.assertEqual(len(clusters), 3)
except IOError, err: sys.exit(err) # TODO(patryk): plot events. # Preprocessing phase. if compress_to_weekly_data: data = utils.compress_data_weekly(data) if trimming_range > 0: data = eventutils.trim_data_to_events(data, events, trimming_range) input_vecs = [] if treat_data_differentially: input_vecs = utils.make_prices_diffs_vecs(data) else: input_vecs = utils.make_prices_vecs(data) # Run clustering algorithm. if algorithm_type == ClusterAlg.KMEANS: labels, wcss, n = Pycluster.kcluster(input_vecs, number_of_clusters, dist = dist_measure, npass = number_of_iters, method = dist_method) elif algorithm_type == ClusterAlg.HIERARCHICAL: tree = Pycluster.treecluster(input_vecs, method = dist_method, dist = dist_method) labels = tree.cut(number_of_clusters) elif algorithm_type == ClusterAlg.SELFORGMAPS: labels, celldata = Pycluster.somcluster(input_vecs, nxgrid = xgrid,
