def setUp(self):
rng = np.random.RandomState(42)
Cluster.global_rng = rng
Genotype.global_rng = rng
setattr(Cluster, "num_dims", 2)
clust1 = Cluster(50)
clust1.mean = np.array([0, 0])
clust1.cov = np.array([[1, 0], [0, 1]])
clust2 = Cluster(30)
clust2.mean = np.array([5, 5])
clust2.cov = np.array([[5, 0], [0, 10]])
self.indiv1 = Genotype([clust1, clust2])
self.indiv1.create_views()
self.indiv1.resample_values()
clust3 = Cluster(50)
clust3.mean = np.array([2, 2])
clust3.cov = np.array([[2, 0], [0, 2]])
clust4 = Cluster(30)
clust4.mean = np.array([10, 10])
clust4.cov = np.array([[4, 0], [0, 2]])
self.indiv2 = Genotype([clust3, clust4])
self.indiv2.create_views()
self.indiv2.resample_values()
def test_eigenratio_eccentric(self):
clust1 = Cluster(50)
clust1.mean = np.array([0, 0])
clust1.cov = np.array([[10, 0], [0, 1]])
clust2 = Cluster(80)
clust2.mean = np.array([0, 0])
clust2.cov = np.array([[9.9, 0], [0, 1]])
indiv = Genotype([clust1, clust2])
eigen_ratio = hawks.constraints.eigenval_ratio(indiv)
self.assertEqual(eigen_ratio, 10)
def test_overlap_same(self):
clust1 = Cluster(4000)
clust1.mean = np.array([0, 0])
clust1.cov = np.array([[1, 0], [0, 1]])
clust2 = Cluster(4000)
clust2.mean = np.array([0, 0])
clust2.cov = np.array([[1, 0], [0, 1]])
indiv = Genotype([clust1, clust2])
indiv.create_views()
indiv.resample_values()
overlap = hawks.constraints.overlap(indiv)
self.assertAlmostEqual(overlap, 0.5, places=1)
def test_overlap_separated(self):
clust1 = Cluster(50)
clust1.mean = np.array([0, 0])
clust1.cov = np.array([[1, 0], [0, 1]])
clust2 = Cluster(80)
clust2.mean = np.array([10, 10])
clust2.cov = np.array([[1, 0], [0, 1]])
indiv = Genotype([clust1, clust2])
indiv.create_views()
indiv.resample_values()
overlap = hawks.constraints.overlap(indiv)
self.assertEqual(overlap, 0)
def generate_indiv(icls, dataset_obj):
# Create the individual
# Uses the DEAP wrapper around Genotype()
indiv = icls([Cluster(size) for size in dataset_obj.cluster_sizes])
# Create the views (each cluster.values is a view into genotype.all_values)
indiv.create_views()
# And sample some initial values
indiv.resample_values()
return indiv
def setUp(self):
# Whatever setup is needed
rng = np.random.RandomState(42)
Genotype.global_rng = rng
Cluster.global_rng = rng
sizes = [190, 20, 30, 110]
self.indiv = Genotype([Cluster(size) for size in sizes])
self.indiv.create_views()
self.indiv.resample_values()
hawks.objectives.Silhouette.setup_indiv(self.indiv)
def setUp(self):
# Whatever setup is needed
rng = np.random.RandomState(42)
Genotype.global_rng = rng
Cluster.global_rng = rng
sizes = [190, 20, 30, 110]
setattr(Cluster, "num_dims", 2)
setattr(Cluster, "initial_mean_upper", 1.0)
setattr(Cluster, "initial_cov_upper", 0.5)
self.indiv = Genotype([Cluster(size) for size in sizes])
self.indiv.create_views()
self.indiv.resample_values()
hawks.objectives.Silhouette.setup_indiv(self.indiv)
def test_silhouette_singleton_cluster(self):
rng = np.random.RandomState(42)
Genotype.global_rng = rng
Cluster.global_rng = rng
sizes = [1, 20, 30, 110]
self.indiv = Genotype([Cluster(size) for size in sizes])
self.indiv.create_views()
self.indiv.resample_values()
hawks.objectives.Silhouette.setup_indiv(self.indiv)
hawks.objectives.Silhouette.eval_objective(self.indiv)
close_to_sk = np.isclose(
silhouette_score(self.indiv.all_values,
self.indiv.labels,
metric="sqeuclidean"), self.indiv.silhouette)
self.assertTrue(close_to_sk)