def test_500x2(self):
"""
This test is based on statistics, that if we run kmeans, on a normal distributed dataset, centered around 0
and use 4 clusters then they will be located in each one corner.
"""
features = self.generate_matrices_for_k_means((500, 2), seed=1304)
res = kmeans(features, k=4).compute()
corners = set()
for x in res:
if x[0] > 0 and x[1] > 0:
corners.add("pp")
elif x[0] > 0 and x[1] < 0:
corners.add("pn")
elif x[0] < 0 and x[1] > 0:
corners.add("np")
else:
corners.add("nn")
self.assertTrue(len(corners) == 4)
def test_500x2(self):
"""
This test is based on statistics, that if we run kmeans, on a normal distributed dataset, centered around 0
and use 4 clusters then they will be located in each one corner.
This test uses the prediction builtin.
"""
features = self.generate_matrices_for_k_means((500, 2), seed=1304)
[c, _] = kmeans(features, k=4).compute()
C = Matrix(self.sds, c)
elm = Matrix(self.sds, np.array([[1, 1], [-1, 1], [-1, -1], [1, -1]]))
res = kmeansPredict(elm, C).compute()
corners = set()
for x in res:
if x == 1:
corners.add("pp")
elif x == 2:
corners.add("pn")
elif x == 3:
corners.add("np")
else:
corners.add("nn")
self.assertTrue(len(corners) == 4)
def test_invalid_input_2(self):
features = Matrix(self.sds, np.array([1]))
with self.assertRaises(ValueError) as context:
kmeans(features, k=-1)
