def test_validation(self):
with self.assertRaises(ValueError):
# More clusters than samples
nw = algorithms.RBFKMeans(n_clusters=1000, verbose=False)
nw.train(data, epsilon=1e-5)
with self.assertRaises(ValueError):
# Number of clusters the same as number of samples
nw = algorithms.RBFKMeans(n_clusters=data.shape[0], verbose=False)
nw.train(data, epsilon=1e-5)
with self.assertRaises(ValueError):
# One cluster
nw = algorithms.RBFKMeans(n_clusters=1, verbose=False)
nw.train(data, epsilon=1e-5)
def test_rbfk_predict_different_inputs(self):
kmnet = algorithms.RBFKMeans(verbose=False, n_clusters=2)
data = np.array([[1, 2, 10]]).T
target = np.array([[0, 0, 1]]).T
kmnet.train(data)
self.assertInvalidVectorPred(kmnet, data.ravel(), target, decimal=2)
def test_rbfk_classification(self):
expected_centers = np.array([
[0.228, 0.312],
[0.482, 0.767],
])
nw = algorithms.RBFKMeans(n_clusters=2, verbose=False)
nw.train(data, epsilon=1e-5)
np.testing.assert_array_almost_equal(expected_centers, nw.centers,
decimal=3)
def test_classification(self):
result = np.array([
[0.228, 0.312],
[0.48166667, 0.76666667],
])
nw = algorithms.RBFKMeans(n_clusters=2, verbose=False)
nw.train(self.data, epsilon=1e-5)
self.assertTrue(np.all(result == np.round(nw.centers, 8)))
if self.draw_plot:
classes = nw.predict(self.data)
for i, center in enumerate(nw.centers):
positions = np.argwhere(classes[:, 0] == i)
class_data = np.take(self.data, positions[:, 0], axis=0)
plt.plot(class_data[:, 0], class_data[:, 1], 'o')
for center in nw.centers:
plt.plot(center[0], center[1], 'kx')
plt.axis([0, 1, 0, 1])
plt.show()
def test_rbfk_means_assign_step_exception(self):
with self.assertRaises(ValueError):
algorithms.RBFKMeans(n_cluster=2, step=0.01)
def test_rbfk_train_different_inputs(self):
self.assertInvalidVectorTrain(
algorithms.RBFKMeans(n_clusters=2, verbose=False),
np.array([1, 2, 10]),
)
#confusion matrix
confusion_matrix(y1_test, y1_pnn_predicted)
# In[20]:
pnn_acc_score = accuracy_score(y1_test, y1_pnn_predicted)
print("Pnn accuracy score ", pnn_acc_score)
# ## 1c. RBF - [ Diabities Problem ]
#
#
# In[21]:
rbf_nw = algorithms.RBFKMeans(n_clusters=2, verbose=False)
# In[22]:
rbf_nw.train(X1_train, epsilon=1e-5)
# In[23]:
y1_rbf_predicted = rbf_nw.predict(X1_test)
# In[24]:
confusion_matrix(y1_test, y1_rbf_predicted)
# In[25]:
