def test_cluster_algorithm(self): # Check with multiple jumps data
# Inititalize Clusterizer
clusterizer = HitClusterizer(pure_python=self.pure_python)
# TEST 1
hits = create_hits(n_hits=10, max_column=100, max_row=100, max_frame=1, max_charge=2)
clusterizer.cluster_hits(hits) # cluster hits
_, clusters = clusterizer.get_hit_cluster(), clusterizer.get_cluster()
# Define expected output
expected_result = np.zeros(shape=(4, ), dtype=np.dtype([('event_number', '<i8'),
('ID', '<u2'),
('n_hits', '<u2'),
('charge', 'f4'),
('seed_column', '<u2'),
('seed_row', '<u2'),
('mean_column', 'f4'),
('mean_row', 'f4')]))
expected_result['event_number'] = [0, 1, 2, 3]
expected_result['n_hits'] = [3, 3, 3, 1]
expected_result['charge'] = [1, 2, 1, 1]
expected_result['seed_column'] = [2, 4, 8, 10]
expected_result['seed_row'] = [3, 7, 15, 19]
expected_result['mean_column'] = [2.0, 5.0, 8.0, 10.0]
expected_result['mean_row'] = [3.0, 9.0, 15.0, 19.0]
# Test results
self.assertTrue((clusters == expected_result).all())
# TEST 2
clusterizer.create_cluster_hit_info_array(True)
hits = create_hits(n_hits=10, max_column=100, max_row=100, max_frame=1, max_charge=2)
clusterizer.cluster_hits(hits) # cluster hits
cluster_hits, clusters = clusterizer.get_hit_cluster(), clusterizer.get_cluster()
# Define expected output
expected_result = np.zeros(shape=(10, ), dtype=np.dtype([('event_number', '<i8'),
('frame', '<u1'),
('column', '<u2'),
('row', '<u2'),
('charge', '<u2'),
('cluster_ID', '<i2'),
('is_seed', '<u1'),
('cluster_size', '<u2'),
('n_cluster', '<u2')]))
expected_result['event_number'] = hits['event_number']
expected_result['frame'] = hits['frame']
expected_result['column'] = hits['column']
expected_result['row'] = hits['row']
expected_result['charge'] = hits['charge']
expected_result['is_seed'] = [0, 1, 0, 1, 0, 0, 0, 1, 0, 1]
expected_result['cluster_size'] = [3, 3, 3, 3, 3, 3, 3, 3, 3, 1]
expected_result['n_cluster'] = 1
# Test results
self.assertEqual(cluster_hits.shape[0], 10) # hit clustering activated, thus this array have 10 entries
self.assertTrue(np.array_equal(cluster_hits, expected_result))
def test_cluster_cuts(self):
# Create some fake data
hits = np.ones(shape=(2, ), dtype=np.dtype([('event_number', '<i8'),
('frame', '<u1'),
('column', '<u2'),
('row', '<u2'),
('charge', '<u2')]))
hits[0]['column'], hits[0]['row'], hits[0]['charge'], hits[0]['event_number'] = 17, 36, 30, 19
hits[1]['column'], hits[1]['row'], hits[1]['charge'], hits[1]['event_number'] = 18, 36, 6, 19
# Create clusterizer object
clusterizer = HitClusterizer(pure_python=self.pure_python)
clusterizer.create_cluster_hit_info_array(True)
# Case 1: Test max hit charge cut, accept all hits
clusterizer.set_max_hit_charge(30) # only add hits with charge <= 30
clusterizer.cluster_hits(hits) # cluster hits
# Check cluster
cluster = clusterizer.get_cluster()
expected_result = np.zeros(shape=(1, ), dtype=np.dtype([('event_number', '<i8'),
('ID', '<u2'),
('n_hits', '<u2'),
('charge', 'f4'),
('seed_column', '<u2'),
('seed_row', '<u2'),
('mean_column', 'f4'),
('mean_row', 'f4')]))
expected_result['event_number'] = [19]
expected_result['n_hits'] = [2]
expected_result['charge'] = [36]
expected_result['seed_column'] = [17]
expected_result['seed_row'] = [36]
expected_result['mean_column'] = [17.18420982]
expected_result['mean_row'] = [36.0]
self.assertTrue(np.array_equal(cluster, expected_result))
# Check cluster hit info
cluster_hits = clusterizer.get_hit_cluster()
expected_result = np.zeros(shape=(2, ), dtype=np.dtype([('event_number', '<i8'),
('frame', '<u1'),
('column', '<u2'),
('row', '<u2'),
('charge', '<u2'),
('cluster_ID', '<i2'),
('is_seed', '<u1'),
('cluster_size', '<u2'),
('n_cluster', '<u2')]))
expected_result['event_number'] = hits['event_number']
expected_result['frame'] = hits['frame']
expected_result['column'] = hits['column']
expected_result['row'] = hits['row']
expected_result['charge'] = hits['charge']
expected_result['is_seed'] = [1, 0]
expected_result['cluster_size'] = [2, 2]
expected_result['n_cluster'] = 1
self.assertTrue(np.array_equal(cluster_hits, expected_result))
# Case 2: Test max hit charge cut, omit charge > 29 hits
hits['event_number'] = 20
clusterizer.set_max_hit_charge(29) # only add hits with charge <= 30
clusterizer.cluster_hits(hits) # cluster hits
# Check cluster
cluster = clusterizer.get_cluster()
expected_result = np.zeros(shape=(1, ), dtype=np.dtype([('event_number', '<i8'),
('ID', '<u2'),
('n_hits', '<u2'),
('charge', 'f4'),
('seed_column', '<u2'),
('seed_row', '<u2'),
('mean_column', 'f4'),
('mean_row', 'f4')]))
expected_result['event_number'] = [20]
expected_result['n_hits'] = [1]
expected_result['charge'] = [6]
expected_result['seed_column'] = [18]
expected_result['seed_row'] = [36]
expected_result['mean_column'] = [18.0]
expected_result['mean_row'] = [36.0]
self.assertTrue(np.array_equal(cluster, expected_result))
# Check cluster hit info
cluster_hits = clusterizer.get_hit_cluster()
expected_result = np.zeros(shape=(2, ), dtype=np.dtype([('event_number', '<i8'),
('frame', '<u1'),
('column', '<u2'),
('row', '<u2'),
('charge', '<u2'),
('cluster_ID', '<i2'),
('is_seed', '<u1'),
('cluster_size', '<u2'),
('n_cluster', '<u2')]))
expected_result['event_number'] = hits['event_number']
expected_result['frame'] = hits['frame']
expected_result['column'] = hits['column']
expected_result['row'] = hits['row']
expected_result['charge'] = hits['charge']
expected_result['cluster_ID'] = [-1, 0]
expected_result['is_seed'] = [0, 1]
expected_result['cluster_size'] = [0, 1]
expected_result['n_cluster'] = [1, 1]
self.assertTrue(np.array_equal(cluster_hits, expected_result))
# Case 3: Add the same hit within an event
# Create some fake data
hits = np.ones(shape=(3, ), dtype=np.dtype([('event_number', '<i8'),
('frame', '<u1'),
('column', '<u2'),
('row', '<u2'),
('charge', '<u2')]))
hits[0]['column'], hits[0]['row'], hits[0]['charge'], hits[0]['event_number'] = 18, 36, 6, 19
hits[1]['column'], hits[1]['row'], hits[1]['charge'], hits[1]['event_number'] = 18, 36, 6, 19
hits[2]['column'], hits[2]['row'], hits[2]['charge'], hits[2]['event_number'] = 18, 38, 6, 19
expected_hit_result = np.zeros(shape=(3, ), dtype=np.dtype([('event_number', '<i8'),
('frame', '<u1'),
('column', '<u2'),
('row', '<u2'),
('charge', '<u2'),
('cluster_ID', '<i2'),
('is_seed', '<u1'),
('cluster_size', '<u2'),
('n_cluster', '<u2')]))
expected_cluster_result = np.zeros(shape=(1, ), dtype=np.dtype([('event_number', '<i8'),
('ID', '<u2'),
('n_hits', '<u2'),
('charge', 'f4'),
('seed_column', '<u2'),
('seed_row', '<u2'),
('mean_column', 'f4'),
('mean_row', 'f4')]))
expected_hit_result['event_number'] = hits['event_number']
expected_hit_result['frame'] = hits['frame']
expected_hit_result['column'] = hits['column']
expected_hit_result['row'] = hits['row']
expected_hit_result['charge'] = hits['charge']
expected_hit_result['cluster_ID'] = [0, -2, 0]
expected_hit_result['is_seed'] = [1, 0, 0]
expected_hit_result['cluster_size'] = [2, 0, 2]
expected_hit_result['n_cluster'] = [1, 1, 1]
expected_cluster_result['event_number'] = [19]
expected_cluster_result['n_hits'] = [2]
expected_cluster_result['charge'] = [12]
expected_cluster_result['seed_column'] = [18]
expected_cluster_result['seed_row'] = [36]
expected_cluster_result['mean_column'] = [18.0]
expected_cluster_result['mean_row'] = [37.0]
clusterizer.ignore_same_hits(True) # If a hit occured 2 times in an event it is ignored and gets the cluster index -2
cluster_hits, cluster = clusterizer.cluster_hits(hits) # Cluster hits
self.assertTrue(np.array_equal(cluster_hits, expected_hit_result))
self.assertTrue(np.array_equal(cluster, expected_cluster_result))
clusterizer.ignore_same_hits(False) # If a hit occured 2 times in an event it is used as a normal hit
cluster_hits, cluster = clusterizer.cluster_hits(hits) # Cluster hits
expected_hit_result['cluster_ID'] = [0, 0, 0]
expected_hit_result['is_seed'] = [1, 0, 0]
expected_hit_result['cluster_size'] = [3, 3, 3]
expected_hit_result['n_cluster'] = [1, 1, 1]
self.assertTrue(np.array_equal(cluster_hits, expected_hit_result))
