def get_parameters(self):
"""
This function creates some parameters to be used with DBScan.
@return: A tuple with the generated parameters and an empty list corresponding to the clusterings.
"""
run_parameters = []
# (minpts, eps tuples)
if "max" in self.parameters["clustering"]["algorithms"]["dbscan"]:
max_eps_tries = self.parameters["clustering"]["algorithms"]["dbscan"]["max"]
else:
max_eps_tries = 10
num_elements = self.distance_matrix.row_length
klist = k_scale_gen(math.log(num_elements))
buffer = numpy.empty(num_elements)
kdist_matrix = k_dist(klist, buffer, self.distance_matrix)
dbscan_param_pairs = dbscanTools.dbscan_param_space_search(self.parameters["clustering"]["evaluation"]["maximum_noise"],
max_eps_tries,
num_elements,
klist,
kdist_matrix) +\
zhou_adaptative_determination(kdist_matrix, self.distance_matrix)
for (minpts, eps) in dbscan_param_pairs:
run_parameter = ParametersGenerator.get_base_parameters()
run_parameter["minpts"] = minpts
run_parameter["eps"] = eps
run_parameters.append(run_parameter)
return run_parameters, []
def test_dbscan_param_space_search(self):
distances = CondensedMatrix(
[0., 0., 2., 2., 2., 0., 2., 2., 3., 2., 2., 3., 4., 4., 0.])
k_list = numpy.array([2, 4])
N = distances.row_length #5
kdist_matrix = numpy.array([[1., 2., 3., 4., 5., 6.],
[5., 6., 7., 8., 9., 7.]])
param_pairs = dbscan_param_space_search(
90, # 90# noise
2,
N,
k_list,
kdist_matrix)
self.assertItemsEqual(param_pairs, [(2, 1.0), (4, 5.0), (2, 3.0),
(4, 7.0), (2, 5.0), (4, 9.0)])
def test_dbscan_param_space_search(self):
distances = CondensedMatrix([ 0., 0., 2., 2., 2.,
0., 2., 2., 3.,
2., 2., 3.,
4., 4.,
0.])
k_list = numpy.array([2,4])
N = distances.row_length #5
kdist_matrix = numpy.array([[1.,2.,3.,4.,5.,6.],
[5.,6.,7.,8.,9.,7.]])
param_pairs = dbscan_param_space_search( 90, # 90# noise
2,
N,
k_list,
kdist_matrix)
self.assertItemsEqual(param_pairs, [(2, 1.0), (4, 5.0), (2, 3.0), (4, 7.0), (2, 5.0), (4, 9.0)])