def test_binary(self, mode):
"""Test QSVM on binary classification on BasicAer's QASM simulator."""
if mode == 'component':
warnings.filterwarnings('ignore', category=DeprecationWarning)
# data encoding using a FeatureMap type
data_preparation = SecondOrderExpansion(feature_dimension=2,
depth=2,
entangler_map=[[0, 1]])
elif mode == 'circuit':
data_preparation = QuantumCircuit(2).compose(self.data_preparation)
else:
data_preparation = self.data_preparation
svm = QSVM(data_preparation, self.training_data, self.testing_data, None)
if mode == 'component':
warnings.filterwarnings('always', category=DeprecationWarning)
try:
result = svm.run(self.qasm_simulator)
np.testing.assert_array_almost_equal(result['kernel_matrix_training'],
self.ref_kernel_training, decimal=1)
np.testing.assert_array_almost_equal(result['kernel_matrix_testing'],
self.ref_kernel_testing['qasm'], decimal=1)
self.assertEqual(len(result['svm']['support_vectors']), 4)
np.testing.assert_array_almost_equal(result['svm']['support_vectors'],
self.ref_support_vectors, decimal=4)
np.testing.assert_array_almost_equal(result['svm']['alphas'], self.ref_alpha, decimal=8)
np.testing.assert_array_almost_equal(result['svm']['bias'], self.ref_bias, decimal=8)
self.assertEqual(result['testing_accuracy'], 0.5)
except NameError as ex:
self.skipTest(str(ex))
def test_qsvm_multiclass_error_correcting_code(self):
""" QSVM Multiclass error Correcting Code test """
training_input = {'A': np.asarray([[0.6560706, 0.17605998], [0.25776033, 0.47628296],
[0.8690704, 0.70847635]]),
'B': np.asarray([[0.38857596, -0.33775802], [0.49946978, -0.48727951],
[0.49156185, -0.3660534]]),
'C': np.asarray([[-0.68088231, 0.46824423], [-0.56167659, 0.65270294],
[-0.82139073, 0.29941512]])}
test_input = {'A': np.asarray([[0.57483139, 0.47120732], [0.48372348, 0.25438544],
[0.48142649, 0.15931707]]),
'B': np.asarray([[-0.06048935, -0.48345293], [-0.01065613, -0.33910828],
[0.06183066, -0.53376975]]),
'C': np.asarray([[-0.74561108, 0.27047295], [-0.69942965, 0.11885162],
[-0.66489165, 0.1181712]])}
total_array = np.concatenate((test_input['A'], test_input['B'], test_input['C']))
aqua_globals.random_seed = self.random_seed
feature_map = SecondOrderExpansion(feature_dimension=get_feature_dimension(training_input),
depth=2,
entangler_map=[[0, 1]])
svm = QSVM(feature_map, training_input, test_input, total_array,
multiclass_extension=ErrorCorrectingCode(_QSVM_Estimator,
[feature_map], code_size=5))
quantum_instance = QuantumInstance(BasicAer.get_backend('qasm_simulator'), shots=self.shots,
seed_simulator=aqua_globals.random_seed,
seed_transpiler=aqua_globals.random_seed)
result = svm.run(quantum_instance)
self.assertAlmostEqual(result['testing_accuracy'], 0.444444444, places=4)
self.assertEqual(result['predicted_classes'], ['A', 'A', 'C', 'A',
'A', 'A', 'A', 'C', 'C'])
def test_qsvm_binary(self, data_preparation_type):
""" QSVM Binary test """
ref_kernel_training = np.array(
[[1., 0.85366667, 0.12341667, 0.36408333],
[0.85366667, 1., 0.11141667, 0.45491667],
[0.12341667, 0.11141667, 1., 0.667],
[0.36408333, 0.45491667, 0.667, 1.]])
ref_kernel_testing = np.array(
[[0.14316667, 0.18208333, 0.4785, 0.14441667],
[0.33608333, 0.3765, 0.02316667, 0.15858333]])
# ref_alpha = np.array([0.36064489, 1.49204209, 0.0264953, 1.82619169])
ref_alpha = np.array([0.34903335, 1.48325498, 0.03074852, 1.80153981])
# ref_bias = np.array([-0.03380763])
ref_bias = np.array([-0.03059226])
ref_support_vectors = np.array([[2.95309709, 2.51327412],
[3.14159265, 4.08407045],
[4.08407045, 2.26194671],
[4.46106157, 2.38761042]])
backend = BasicAer.get_backend('qasm_simulator')
data_preparation = self.data_preparation[data_preparation_type]
if data_preparation_type == 'wrapped':
warnings.filterwarnings('ignore', category=DeprecationWarning)
svm = QSVM(data_preparation, self.training_data, self.testing_data,
None)
if data_preparation_type == 'wrapped':
warnings.filterwarnings('always', category=DeprecationWarning)
quantum_instance = QuantumInstance(backend,
shots=self.shots,
seed_simulator=self.random_seed,
seed_transpiler=self.random_seed)
try:
result = svm.run(quantum_instance)
np.testing.assert_array_almost_equal(
result['kernel_matrix_training'],
ref_kernel_training,
decimal=1)
np.testing.assert_array_almost_equal(
result['kernel_matrix_testing'], ref_kernel_testing, decimal=1)
self.assertEqual(len(result['svm']['support_vectors']), 4)
np.testing.assert_array_almost_equal(
result['svm']['support_vectors'],
ref_support_vectors,
decimal=4)
np.testing.assert_array_almost_equal(result['svm']['alphas'],
ref_alpha,
decimal=8)
np.testing.assert_array_almost_equal(result['svm']['bias'],
ref_bias,
decimal=8)
self.assertEqual(result['testing_accuracy'], 0.5)
except NameError as ex:
self.skipTest(str(ex))
def test_binary(self, mode):
"""Test QSVM on binary classification on BasicAer's QASM simulator."""
if mode == 'circuit':
data_preparation = QuantumCircuit(2).compose(self.data_preparation)
else:
data_preparation = self.data_preparation
svm = QSVM(data_preparation, self.training_data, self.testing_data, None, lambda2=0)
try:
result = svm.run(self.qasm_simulator)
np.testing.assert_array_almost_equal(result['kernel_matrix_training'],
self.ref_kernel_training, decimal=1)
np.testing.assert_array_almost_equal(result['kernel_matrix_testing'],
self.ref_kernel_testing['qasm'], decimal=1)
self.assertEqual(len(result['svm']['support_vectors']), 4)
np.testing.assert_array_almost_equal(result['svm']['support_vectors'],
self.ref_support_vectors, decimal=4)
np.testing.assert_array_almost_equal(result['svm']['alphas'], self.ref_alpha, decimal=8)
np.testing.assert_array_almost_equal(result['svm']['bias'], self.ref_bias, decimal=8)
self.assertEqual(result['testing_accuracy'], 0.5)
except MissingOptionalLibraryError as ex:
self.skipTest(str(ex))
def test_qsvm_binary_directly_statevector(self):
""" QSVM Binary Directly Statevector test """
ref_kernel_testing = np. array([[0.1443953, 0.18170069, 0.47479649, 0.14691763],
[0.33041779, 0.37663733, 0.02115561, 0.16106199]])
ref_support_vectors = np.array([[2.95309709, 2.51327412], [3.14159265, 4.08407045],
[4.08407045, 2.26194671], [4.46106157, 2.38761042]])
backend = BasicAer.get_backend('statevector_simulator')
num_qubits = 2
feature_map = SecondOrderExpansion(feature_dimension=num_qubits,
depth=2,
entangler_map=[[0, 1]])
svm = QSVM(feature_map, self.training_data, self.testing_data, None)
quantum_instance = QuantumInstance(backend, seed_transpiler=self.random_seed,
seed_simulator=self.random_seed)
file_path = self.get_resource_path('qsvm_test.npz')
try:
result = svm.run(quantum_instance)
ori_alphas = result['svm']['alphas']
np.testing.assert_array_almost_equal(
result['kernel_matrix_testing'], ref_kernel_testing, decimal=4)
self.assertEqual(len(result['svm']['support_vectors']), 4)
np.testing.assert_array_almost_equal(
result['svm']['support_vectors'], ref_support_vectors, decimal=4)
self.assertEqual(result['testing_accuracy'], 0.5)
svm.save_model(file_path)
self.assertTrue(os.path.exists(file_path))
loaded_svm = QSVM(feature_map)
loaded_svm.load_model(file_path)
np.testing.assert_array_almost_equal(
loaded_svm.ret['svm']['support_vectors'], ref_support_vectors, decimal=4)
np.testing.assert_array_almost_equal(
loaded_svm.ret['svm']['alphas'], ori_alphas, decimal=4)
loaded_test_acc = loaded_svm.test(svm.test_dataset[0],
svm.test_dataset[1],
quantum_instance)
self.assertEqual(result['testing_accuracy'], loaded_test_acc)
np.testing.assert_array_almost_equal(
loaded_svm.ret['kernel_matrix_testing'], ref_kernel_testing, decimal=4)
except NameError as ex:
self.skipTest(str(ex))
finally:
if os.path.exists(file_path):
try:
os.remove(file_path)
except Exception: # pylint: disable=broad-except
pass
def test_binary_directly_statevector(self):
"""Test QSVM on binary classification on BasicAer's statevector simulator.
Also tests saving and loading models."""
data_preparation = self.data_preparation
svm = QSVM(data_preparation, self.training_data, self.testing_data,
None)
file_path = self.get_resource_path('qsvm_test.npz')
try:
result = svm.run(self.statevector_simulator)
ori_alphas = result['svm']['alphas']
np.testing.assert_array_almost_equal(
result['kernel_matrix_testing'],
self.ref_kernel_testing['statevector'],
decimal=4)
self.assertEqual(len(result['svm']['support_vectors']), 4)
np.testing.assert_array_almost_equal(
result['svm']['support_vectors'],
self.ref_support_vectors,
decimal=4)
self.assertEqual(result['testing_accuracy'], 0.5)
svm.save_model(file_path)
self.assertTrue(os.path.exists(file_path))
loaded_svm = QSVM(data_preparation)
loaded_svm.load_model(file_path)
np.testing.assert_array_almost_equal(
loaded_svm.ret['svm']['support_vectors'],
self.ref_support_vectors,
decimal=4)
np.testing.assert_array_almost_equal(
loaded_svm.ret['svm']['alphas'], ori_alphas, decimal=4)
loaded_test_acc = loaded_svm.test(svm.test_dataset[0],
svm.test_dataset[1],
self.statevector_simulator)
self.assertEqual(result['testing_accuracy'], loaded_test_acc)
np.testing.assert_array_almost_equal(
loaded_svm.ret['kernel_matrix_testing'],
self.ref_kernel_testing['statevector'],
decimal=4)
except MissingOptionalLibraryError as ex:
self.skipTest(str(ex))
finally:
if os.path.exists(file_path):
try:
os.remove(file_path)
except Exception: # pylint: disable=broad-except
pass
def test_matrix_psd(self):
""" Test kernel matrix positive semi-definite enforcement. """
try:
from cvxpy.error import DQCPError
except ImportError:
self.skipTest('cvxpy does not appeat to be installed')
seed = 10598
feature_dim = 2
_, training_input, _, _ = ad_hoc_data(
training_size=10,
test_size=5,
n=feature_dim,
gap=0.3
)
training_input, _ = split_dataset_to_data_and_labels(training_input)
training_data = training_input[0]
training_labels = training_input[1]
labels = training_labels * 2 - 1 # map label from 0 --> -1 and 1 --> 1
labels = labels.astype(float)
feature_map = ZZFeatureMap(feature_dimension=feature_dim, reps=2, entanglement='linear')
try:
with self.assertRaises(DQCPError):
# Sampling noise means that the kernel matrix will not quite be positive
# semi-definite which will cause the optimize svm to fail
backend = BasicAer.get_backend('qasm_simulator')
quantum_instance = QuantumInstance(backend, shots=1024, seed_simulator=seed,
seed_transpiler=seed)
kernel_matrix = QSVM.get_kernel_matrix(quantum_instance, feature_map=feature_map,
x1_vec=training_data, enforce_psd=False)
_ = optimize_svm(kernel_matrix, labels, lambda2=0)
except MissingOptionalLibraryError as ex:
self.skipTest(str(ex))
return
# This time we enforce that the matrix be positive semi-definite which runs logic to
# make it so.
backend = BasicAer.get_backend('qasm_simulator')
quantum_instance = QuantumInstance(backend, shots=1024, seed_simulator=seed,
seed_transpiler=seed)
kernel_matrix = QSVM.get_kernel_matrix(quantum_instance, feature_map=feature_map,
x1_vec=training_data, enforce_psd=True)
alpha, b, support = optimize_svm(kernel_matrix, labels, lambda2=0)
expected_alpha = [0.855861781, 2.59807482, 0, 0.962959215,
1.08141696, 0.217172547, 0, 0,
0.786462904, 0, 0.969727949, 1.98066946,
0, 0, 1.62049430, 0,
0.394212728, 0, 0.507740935, 1.02910286]
expected_b = [-0.17543365]
expected_support = [True, True, False, True, True, True, False, False, True, False,
True, True, False, False, True, False, True, False, True, True]
np.testing.assert_array_almost_equal(alpha, expected_alpha)
np.testing.assert_array_almost_equal(b, expected_b)
np.testing.assert_array_equal(support, expected_support)
def test_qsvm_binary(self):
""" QSVM Binary test """
ref_kernel_training = np.array(
[[1., 0.85366667, 0.12341667, 0.36408333],
[0.85366667, 1., 0.11141667, 0.45491667],
[0.12341667, 0.11141667, 1., 0.667],
[0.36408333, 0.45491667, 0.667, 1.]])
ref_kernel_testing = np.array(
[[0.14316667, 0.18208333, 0.4785, 0.14441667],
[0.33608333, 0.3765, 0.02316667, 0.15858333]])
# ref_alpha = np.array([0.36064489, 1.49204209, 0.0264953, 1.82619169])
ref_alpha = np.array([0.34903335, 1.48325498, 0.03074852, 1.80153981])
# ref_bias = np.array([-0.03380763])
ref_bias = np.array([-0.03059226])
ref_support_vectors = np.array([[2.95309709, 2.51327412],
[3.14159265, 4.08407045],
[4.08407045, 2.26194671],
[4.46106157, 2.38761042]])
backend = BasicAer.get_backend('qasm_simulator')
num_qubits = 2
feature_map = SecondOrderExpansion(feature_dimension=num_qubits,
depth=2,
entangler_map=[[0, 1]])
svm = QSVM(feature_map, self.training_data, self.testing_data, None)
quantum_instance = QuantumInstance(backend,
shots=self.shots,
seed_simulator=self.random_seed,
seed_transpiler=self.random_seed)
try:
result = svm.run(quantum_instance)
np.testing.assert_array_almost_equal(
result['kernel_matrix_training'],
ref_kernel_training,
decimal=1)
np.testing.assert_array_almost_equal(
result['kernel_matrix_testing'], ref_kernel_testing, decimal=1)
self.assertEqual(len(result['svm']['support_vectors']), 4)
np.testing.assert_array_almost_equal(
result['svm']['support_vectors'],
ref_support_vectors,
decimal=4)
np.testing.assert_array_almost_equal(result['svm']['alphas'],
ref_alpha,
decimal=8)
np.testing.assert_array_almost_equal(result['svm']['bias'],
ref_bias,
decimal=8)
self.assertEqual(result['testing_accuracy'], 0.5)
except NameError as ex:
self.skipTest(str(ex))
def test_qsvm_multiclass_error_correcting_code(self,
data_preparation_type):
""" QSVM Multiclass error Correcting Code test """
training_input = {
'A':
np.asarray([[0.6560706, 0.17605998], [0.25776033, 0.47628296],
[0.8690704, 0.70847635]]),
'B':
np.asarray([[0.38857596, -0.33775802], [0.49946978, -0.48727951],
[0.49156185, -0.3660534]]),
'C':
np.asarray([[-0.68088231, 0.46824423], [-0.56167659, 0.65270294],
[-0.82139073, 0.29941512]])
}
test_input = {
'A':
np.asarray([[0.57483139, 0.47120732], [0.48372348, 0.25438544],
[0.48142649, 0.15931707]]),
'B':
np.asarray([[-0.06048935, -0.48345293], [-0.01065613, -0.33910828],
[0.06183066, -0.53376975]]),
'C':
np.asarray([[-0.74561108, 0.27047295], [-0.69942965, 0.11885162],
[-0.66489165, 0.1181712]])
}
total_array = np.concatenate(
(test_input['A'], test_input['B'], test_input['C']))
aqua_globals.random_seed = self.random_seed
data_preparation = self.data_preparation[data_preparation_type]
try:
if data_preparation_type == 'wrapped':
warnings.filterwarnings('ignore', category=DeprecationWarning)
svm = QSVM(data_preparation,
training_input,
test_input,
total_array,
multiclass_extension=ErrorCorrectingCode(code_size=5))
if data_preparation_type == 'wrapped':
warnings.filterwarnings('always', category=DeprecationWarning)
quantum_instance = QuantumInstance(
BasicAer.get_backend('qasm_simulator'),
shots=self.shots,
seed_simulator=aqua_globals.random_seed,
seed_transpiler=aqua_globals.random_seed)
result = svm.run(quantum_instance)
self.assertAlmostEqual(result['testing_accuracy'],
0.555555555,
places=4)
self.assertEqual(result['predicted_classes'],
['A', 'A', 'A', 'A', 'A', 'A', 'A', 'C', 'C'])
except NameError as ex:
self.skipTest(str(ex))
def test_multiclass(self, multiclass_extension):
""" QSVM Multiclass One Against All test """
train_input = {'A': np.asarray([[0.6560706, 0.17605998],
[0.25776033, 0.47628296],
[0.8690704, 0.70847635]]),
'B': np.asarray([[0.38857596, -0.33775802],
[0.49946978, -0.48727951],
[0.49156185, -0.3660534]]),
'C': np.asarray([[-0.68088231, 0.46824423],
[-0.56167659, 0.65270294],
[-0.82139073, 0.29941512]])}
test_input = {'A': np.asarray([[0.57483139, 0.47120732],
[0.48372348, 0.25438544],
[0.48142649, 0.15931707]]),
'B': np.asarray([[-0.06048935, -0.48345293],
[-0.01065613, -0.33910828],
[0.06183066, -0.53376975]]),
'C': np.asarray([[-0.74561108, 0.27047295],
[-0.69942965, 0.11885162],
[-0.66489165, 0.1181712]])}
method = {'one_vs_all': OneAgainstRest(),
'all_vs_all': AllPairs(),
'error_correcting': ErrorCorrectingCode(code_size=5)}
accuracy = {'one_vs_all': 0.444444444,
'all_vs_all': 0.444444444,
'error_correcting': 0.555555555}
predicted_classes = {
'one_vs_all': ['A', 'A', 'C', 'A', 'A', 'A', 'A', 'C', 'C'],
'all_vs_all': ['A', 'A', 'C', 'A', 'A', 'A', 'A', 'C', 'C'],
'error_correcting': ['A', 'A', 'A', 'A', 'A', 'A', 'A', 'C', 'C']
}
total_array = np.concatenate((test_input['A'], test_input['B'], test_input['C']))
data_preparation = self.data_preparation
try:
svm = QSVM(data_preparation, train_input, test_input, total_array,
multiclass_extension=method[multiclass_extension], lambda2=0)
result = svm.run(self.qasm_simulator)
self.assertAlmostEqual(result['testing_accuracy'], accuracy[multiclass_extension],
places=4)
self.assertEqual(result['predicted_classes'], predicted_classes[multiclass_extension])
except MissingOptionalLibraryError as ex:
self.skipTest(str(ex))
def train_model(self):
backend = Aer.get_backend('qasm_simulator')
feature_expansion = SecondOrderExpansion(
feature_dimension=self.feature_dim,
depth=self.feature_depth,
entangler_map=[[0, 1]])
#feature_expansion = FirstOrderExpansion(feature_dimension=self.feature_dim)
# Model definition
svm = QSVM(feature_expansion, self.train, self.test)
#svm.random_seed = self.seed
q_inst = QuantumInstance(backend, shots=self.copies)
# Train the SVM
result = svm.run(q_inst)
return svm, result
def test_qsvm_setup_data(self):
""" QSVM Setup Data test """
ref_kernel_testing = np. array([[0.1443953, 0.18170069, 0.47479649, 0.14691763],
[0.33041779, 0.37663733, 0.02115561, 0.16106199]])
ref_support_vectors = np.array([[2.95309709, 2.51327412], [3.14159265, 4.08407045],
[4.08407045, 2.26194671], [4.46106157, 2.38761042]])
backend = BasicAer.get_backend('statevector_simulator')
num_qubits = 2
feature_map = SecondOrderExpansion(feature_dimension=num_qubits,
depth=2,
entangler_map=[[0, 1]])
svm = QSVM(feature_map)
svm.setup_training_data(self.training_data)
svm.setup_test_data(self.testing_data)
quantum_instance = QuantumInstance(backend, seed_transpiler=self.random_seed,
seed_simulator=self.random_seed)
result = svm.run(quantum_instance)
np.testing.assert_array_almost_equal(
result['kernel_matrix_testing'], ref_kernel_testing, decimal=4)
self.assertEqual(len(result['svm']['support_vectors']), 4)
np.testing.assert_array_almost_equal(
result['svm']['support_vectors'], ref_support_vectors, decimal=4)
self.assertEqual(result['testing_accuracy'], 0.5)
def test_qsvm_setup_data(self, data_preparation_type):
""" QSVM Setup Data test """
ref_kernel_testing = np. array([[0.1443953, 0.18170069, 0.47479649, 0.14691763],
[0.33041779, 0.37663733, 0.02115561, 0.16106199]])
ref_support_vectors = np.array([[2.95309709, 2.51327412], [3.14159265, 4.08407045],
[4.08407045, 2.26194671], [4.46106157, 2.38761042]])
backend = BasicAer.get_backend('statevector_simulator')
data_preparation = self.data_preparation[data_preparation_type]
try:
if data_preparation_type == 'wrapped':
warnings.filterwarnings('ignore', category=DeprecationWarning)
svm = QSVM(data_preparation)
if data_preparation_type == 'wrapped':
warnings.filterwarnings('always', category=DeprecationWarning)
svm.setup_training_data(self.training_data)
svm.setup_test_data(self.testing_data)
quantum_instance = QuantumInstance(backend, seed_transpiler=self.random_seed,
seed_simulator=self.random_seed)
result = svm.run(quantum_instance)
np.testing.assert_array_almost_equal(
result['kernel_matrix_testing'], ref_kernel_testing, decimal=4)
self.assertEqual(len(result['svm']['support_vectors']), 4)
np.testing.assert_array_almost_equal(
result['svm']['support_vectors'], ref_support_vectors, decimal=4)
self.assertEqual(result['testing_accuracy'], 0.5)
except NameError as ex:
self.skipTest(str(ex))
def test_qsvm_multiclass_all_pairs(self, use_circuits):
""" QSVM Multiclass All Pairs test """
training_input = {'A': np.asarray([[0.6560706, 0.17605998], [0.25776033, 0.47628296],
[0.8690704, 0.70847635]]),
'B': np.asarray([[0.38857596, -0.33775802], [0.49946978, -0.48727951],
[0.49156185, -0.3660534]]),
'C': np.asarray([[-0.68088231, 0.46824423], [-0.56167659, 0.65270294],
[-0.82139073, 0.29941512]])}
test_input = {'A': np.asarray([[0.57483139, 0.47120732], [0.48372348, 0.25438544],
[0.48142649, 0.15931707]]),
'B': np.asarray([[-0.06048935, -0.48345293], [-0.01065613, -0.33910828],
[0.06183066, -0.53376975]]),
'C': np.asarray([[-0.74561108, 0.27047295], [-0.69942965, 0.11885162],
[-0.66489165, 0.1181712]])}
total_array = np.concatenate((test_input['A'], test_input['B'], test_input['C']))
aqua_globals.random_seed = self.random_seed
feature_map = SecondOrderExpansion(feature_dimension=get_feature_dimension(training_input),
depth=2,
entangler_map=[[0, 1]])
if use_circuits:
x = ParameterVector('x', feature_map.feature_dimension)
feature_map = feature_map.construct_circuit(x)
feature_map.ordered_parameters = list(x)
try:
svm = QSVM(feature_map, training_input, test_input, total_array,
multiclass_extension=AllPairs())
quantum_instance = QuantumInstance(BasicAer.get_backend('qasm_simulator'),
shots=self.shots,
seed_simulator=aqua_globals.random_seed,
seed_transpiler=aqua_globals.random_seed)
result = svm.run(quantum_instance)
self.assertAlmostEqual(result['testing_accuracy'], 0.444444444, places=4)
self.assertEqual(result['predicted_classes'], ['A', 'A', 'C', 'A',
'A', 'A', 'A', 'C', 'C'])
except NameError as ex:
self.skipTest(str(ex))
def test_setup_data(self):
"""Test the setup_*_data methods of QSVM."""
data_preparation = self.data_preparation
try:
svm = QSVM(data_preparation)
svm.setup_training_data(self.training_data)
svm.setup_test_data(self.testing_data)
result = svm.run(self.statevector_simulator)
np.testing.assert_array_almost_equal(result['kernel_matrix_testing'],
self.ref_kernel_testing['statevector'], decimal=4)
self.assertEqual(len(result['svm']['support_vectors']), 4)
np.testing.assert_array_almost_equal(result['svm']['support_vectors'],
self.ref_support_vectors, decimal=4)
self.assertEqual(result['testing_accuracy'], 0.5)
except MissingOptionalLibraryError as ex:
self.skipTest(str(ex))
test = np.append(X_test, y_test, axis=1)
train = pd.DataFrame(data=train[:, :])
test = pd.DataFrame(data=test[:, :])
train = train.sample(frac=1).reset_index(drop=True)
test = test.sample(frac=1).reset_index(drop=True)
train = {k: np.asarray(g.iloc[:, :-1]) for k, g in train.groupby(10)}
test = {k: np.asarray(g.iloc[:, :-1]) for k, g in test.groupby(10)}
backend = BasicAer.get_backend('qasm_simulator')
#IBMQ.enable_account(HERE)
#provider = IBMQ.get_provider(hub='ibm-q')
#backend = provider.get_backend('ibmq_16_melbourne') # Specifying Quantum device
seed = 11111
feature_dim = 10
feature_map = ZZFeatureMap(feature_dimension=feature_dim,
reps=2,
entanglement='linear')
qsvm = QSVM(feature_map, train, test)
quantum_instance = QuantumInstance(backend,
shots=1024,
seed_simulator=seed,
seed_transpiler=seed,
skip_qobj_validation=False)
result = qsvm.run(quantum_instance)
print("Quantum accuracy on test set: {0}%".format(
round(result['testing_accuracy'] * 100, 2)))
testing_dataset_size = 10
random_seed = 10598
shots = 1024
sample_Total, training_input, test_input, class_labels = ad_hoc_data(
training_size=training_dataset_size,
test_size=testing_dataset_size,
n=feature_dim, gap=0.3, plot_data=False
)
datapoints, class_to_label = split_dataset_to_data_and_labels(test_input)
print(class_to_label)
backend = BasicAer.get_backend('qasm_simulator')
feature_map = ZZFeatureMap(feature_dim, reps=2)
svm = QSVM(feature_map, training_input, test_input, None)# the data for prediction can be fed later.
svm.random_seed = random_seed
quantum_instance = QuantumInstance(backend, shots=shots, seed_simulator=random_seed, seed_transpiler=random_seed)
result = svm.run(quantum_instance)
print("kernel matrix during the training:")
kernel_matrix = result['kernel_matrix_training']
img = plt.imshow(np.asmatrix(kernel_matrix),interpolation='nearest',origin='upper',cmap='bone_r')
plt.show()
print("testing success ratio: ", result['testing_accuracy'])
predicted_labels = svm.predict(datapoints[0])
'B': np.asarray([[1.777], [1.341], [1.514], [1.204], [1.135]])
}
IBMQ.enable_account('ENTER API KEY HERE')
provider = IBMQ.get_provider(hub='ibm-q')
backend = provider.get_backend(
'ibmq_qasm_simulator') # Specifying Quantum device
num_qubits = 1
feature_map = SecondOrderExpansion(feature_dimension=num_qubits,
depth=2,
entanglement='full')
svm = QSVM(feature_map, training_data, testing_data) # Creation of QSVM
quantum_instance = QuantumInstance(backend,
shots=shots,
skip_qobj_validation=False)
print('Running....\n')
result = svm.run(quantum_instance) # Running the QSVM and getting the accuracy
data = np.array([[1.453], [1.023], [0.135], [0.266]]) #Unlabelled data
prediction = svm.predict(data,
quantum_instance) # Predict using unlabelled data
print(
feature_dim = 2
sample_total, training_input, test_input, class_labels = ad_hoc_data(
training_size=50,
test_size=10,
n=feature_dim,
gap=0.3,
# plot_data=True
plot_data=False)
extra_test_data = sample_ad_hoc_data(sample_total, 10, n=feature_dim)
datapoints, class_to_label = split_dataset_to_data_and_labels(extra_test_data)
print(class_to_label)
feature_map = ZZFeatureMap(feature_dimension=feature_dim,
reps=2,
entanglement='linear')
qsvm = QSVM(feature_map, training_input, test_input, datapoints[0])
backend = BasicAer.get_backend('qasm_simulator')
quantum_instance = QuantumInstance(backend,
shots=1024,
seed_simulator=seed,
seed_transpiler=seed)
result = qsvm.run(quantum_instance)
print(f'Testing success ratio: {result["testing_accuracy"]}')
print()
print('Prediction from datapoints set:')
print(
f' ground truth: {map_label_to_class_name(datapoints[1], qsvm.label_to_class)}'
)
array_train = []
array_test= []
for i in (range(len(training_input[key]))):
if (i%2==0):
array_train += [training_input[key][i]]
else:
array_test += [training_input[key][i]]
new_training_input.update({key: array_train})
new_test_input.update({key: array_train})
multi_ext_classical = OneAgainstRest(_RBF_SVC_Estimator)
svm = SVM_Classical(new_training_input, new_test_input, multiclass_extension=multi_ext_classical)
feature_map = PauliExpansion(feature_dimension=feature_dim, depth=2, paulis=['Z', 'ZZ'], entanglement='linear')
multi_ext_quantum = OneAgainstRest(_QSVM_Estimator, [feature_map])
qsvm = QSVM(feature_map, new_training_input, new_test_input, multiclass_extension=multi_ext_quantum)
seed = 1001
backend = Aer.get_backend('qasm_simulator')
#device = IBMQ.get_provider().get_backend('ibmqx2')
classical_instance = QuantumInstance(backend, shots=1024, seed=seed, seed_transpiler=seed)
quantum_instance = QuantumInstance(backend, shots=1024, seed=seed, seed_transpiler=seed, circuit_caching=False, skip_qobj_validation=False)
#start_classical = timeit.default_timer()
#result_classical = svm.run(classical_instance)
#elapsed_classical = timeit.default_timer() - start_classical
start_quantum = timeit.default_timer()
result_quant = qsvm.run(quantum_instance)
elapsed_quantum = timeit.default_timer() - start_quantum
}
if config['local']:
config['server'] = 'qasm_simulator'
else:
config['qbits'] = servers[config['server']]
data = json.load(open('data' + str(config['qbits']) + '.json', 'r'))
IBMQ.save_account(config['token'])
if config['local']:
IBMQ.load_accounts(hub=None)
feature_map = SecondOrderExpansion(feature_dimension=config['qbits'],
depth=config['depth'],
entanglement=config['entanglement'])
qsvm = QSVM(feature_map, data["train"], data["test"])
backend = BasicAer.get_backend(config['server'])
quantum_instance = QuantumInstance(backend,
shots=config['shots'],
seed_transpiler=config['seed'])
result = qsvm.run(quantum_instance)
print(result)
else:
IBMQ.load_accounts(hub=None)
feature_map = SecondOrderExpansion(feature_dimension=config['qbits'],
depth=config['depth'],
entanglement=config['entanglement'])
qsvm = QSVM(feature_map, data["train"], data["test"])
provider = IBMQ.get_provider()
backend = provider.get_backend(config['server'])
quantum_instance = QuantumInstance(backend,
training_size=20, test_size=10, n=feature_dim, gap=0.3, plot_data=False)
# Using the statevector simulator
backend = BasicAer.get_backend('statevector_simulator')
random_seed = 10598
quantum_instance = QuantumInstance(backend,
seed_simulator=random_seed,
seed_transpiler=random_seed)
# Generate the feature map
feature_map = ZFeatureMap(feature_dimension=feature_dim, reps=2)
# Run the Quantum Kernel Estimator and classify the test data
qsvm = QSVM(feature_map=feature_map,
training_dataset=training_dataset,
test_dataset=test_dataset)
result = qsvm.run(quantum_instance)
print("testing success ratio: ", result['testing_accuracy'])
feature_map = ZZFeatureMap(feature_dimension=feature_dim, reps=2)
qsvm = QSVM(feature_map=feature_map,
training_dataset=training_dataset,
test_dataset=test_dataset)
result = qsvm.run(quantum_instance)
print("testing success ratio: ", result['testing_accuracy'])
#Divide dataset into training and testing with a 7:3 ratio
p_train, p_test, notp_train, notp_test = train_test_split(p_now, notp, test_size=0.3, random_state=12)
#Combine training/testing arrays
training_data={'A': p_train, 'B': notp_train}
testing_data = {'A' : p_test, 'B': notp_test}
num_qubits=9
feature_map = SecondOrderExpansion(feature_dimension=num_qubits, depth = 2, entanglement = 'full')
svm = QSVM(feature_map,training_data,testing_data)
quantum_instance=QuantumInstance(backend, shots=shots, skip_qobj_validation=False)
#Run the QSVM for accuracy results
result = svm.run(quantum_instance)
#Unlabelled data
data = np.array([[0, 0.80766, 0.73961, 0.20569, 445, 444, 0.004334704, 2.43E-05, 0.00072],
[1, 0.83967, 0.80944, 0.45038, 259, 257, 0.007310325, 0.00251383, 0.00534],
[1, 0.81525, 0.73462, 0.64849, 303, 302, 0.006381791, 0.000149359, 0.00292],
[1, 0.79163, 0.80358, 0.43866, 330, 329, 0.005844644, 8.21E-05, 0.00278],
[0, 0.7594, 0.68265, 0.39428, 443, 442, 0.004354498, 6.69E-05, 0.00076],
# from qiskit import IBMQ
# provider = IBMQ.load_account()
feature_dim = 2 # we support feature_dim 2 or 3
sample_Total, training_input, test_input, class_labels = ad_hoc_data(
training_size=20, test_size=10, n=feature_dim, gap=0.3, plot_data=True)
extra_test_data = sample_ad_hoc_data(sample_Total, 10, n=feature_dim)
datapoints, class_to_label = split_dataset_to_data_and_labels(extra_test_data)
print(class_to_label)
seed = 10598
feature_map = ZZFeatureMap(feature_dimension=feature_dim,
reps=2,
entanglement='linear')
qsvm = QSVM(feature_map, training_input, test_input, datapoints[0])
backend = BasicAer.get_backend('qasm_simulator')
quantum_instance = QuantumInstance(backend,
shots=1024,
seed_simulator=seed,
seed_transpiler=seed)
result = qsvm.run(quantum_instance)
print("testing success ratio: {}".format(result['testing_accuracy']))
print("preduction of datapoints:")
print("ground truth: {}".format(
map_label_to_class_name(datapoints[1], qsvm.label_to_class)))
print("prediction: {}".format(result['predicted_classes']))
def compareMethods(class1, class2, class3 = None, backend=BasicAer.get_backend('qasm_simulator'), name = "",
include_unscaled=False, include_QSVM = True, include_VQC = True, feature_dimension = 2, gamma = 'auto', C = 1.0):
#Define header and chart data
data = []
header = ["Algorithm", "Backend", "Time", "Accuracy", "Only one Class Predicted?"]
data.append(header)
#Split data into train and test
class1_train, class1_test = train_test_split(class1, test_size=0.33, random_state=42)
class2_train, class2_test = train_test_split(class2, test_size=0.33, random_state=42)
feature_dim = feature_dimension
if class3 is not None:
class3_train, class3_test = train_test_split(class3, test_size=0.33, random_state=42)
#Get input data for quantum
training_data = {'A': np.asarray(class1_train), 'B': np.asarray(class2_train)}
test_data = {'A': np.asarray(class1_test), 'B': np.asarray(class2_test)}
total_array = np.concatenate((test_data['A'], test_data['B']))
if class3 is not None:
training_data["C"] = class3_train
test_data["C"] = class3_test
total_array = np.concatenate((total_array, test_data['C']))
#Get input data for classical
X_train, x_test, Y_train, y_test = convertFromQS(training_data, test_data)
#Classical SVM, linear kernel (scaled and unscaled)
if include_unscaled:
start = time.time()
clf = svm.SVC(kernel='linear') # Linear Kernel
model = clf.fit(X_train, Y_train)
y_pred = clf.predict(x_test)
end = time.time()
data.append(["SVM, Linear Kernel", "Local Processor", round(end-start), str(round(100*metrics.accuracy_score(y_test, y_pred), 2)),checkAllSame(y_pred)])
start = time.time()
scaler = StandardScaler()
X_train_std = scaler.fit_transform(X_train)
x_test_std = scaler.fit_transform(x_test)
clf = svm.SVC(kernel='linear') # Linear Kernel
model = clf.fit(X_train_std, Y_train)
y_pred = clf.predict(x_test_std)
end = time.time()
data.append(["SVM, Linear Kernel, scaled", "Local Processor", round(end-start), str(round(100*metrics.accuracy_score(y_test, y_pred), 2)),checkAllSame(y_pred)])
#Classical SVM, rbf kernel (scaled and unscaled)
if include_unscaled:
start = time.time()
clf = svm.SVC(C=C, kernel='rbf', gamma = gamma) # rbf Kernel
model = clf.fit(X_train, Y_train)
y_pred = clf.predict(x_test)
end = time.time()
data.append(["SVM, RBF Kernel", "Local Processor", round(end-start), str(round(100*metrics.accuracy_score(y_test, y_pred), 2)),checkAllSame(y_pred)])
start = time.time()
scaler = StandardScaler()
X_train_std = scaler.fit_transform(X_train)
x_test_std = scaler.fit_transform(x_test)
clf = svm.SVC(C=C, kernel='rbf', gamma = gamma) # rbf Kernel
model = clf.fit(X_train_std, Y_train)
y_pred = clf.predict(x_test_std)
end = time.time()
data.append(["SVM, RBF Kernel, scaled", "Local Processor", round(end-start), str(round(100*metrics.accuracy_score(y_test, y_pred), 2)),checkAllSame(y_pred)])
#QSVM run
if include_QSVM:
start = time.time()
feature_map = ZZFeatureMap(feature_dimension=feature_dim, reps=2, entanglement='linear')
if class3 is None:
qsvm = QSVM(feature_map, training_data, test_data, total_array)
else:
qsvm = QSVM(feature_map, training_data, test_data, total_array, multiclass_extension=AllPairs())
quantum_instance = QuantumInstance(backend, shots=1024, seed_simulator=10598, seed_transpiler=10598)
resultSVM = qsvm.run(quantum_instance)
end = time.time()
QSVM_Summary = ["QSVM", backend.name(), round(end-start), str(round(100*resultSVM['testing_accuracy'], 2)), checkAllSame(resultSVM['predicted_classes'])]
data.append(QSVM_Summary)
path = 'C:\\Users\\admin\\Desktop\\QQML\\Code\\Saved_SVMs\\' + name + "_" + backend.name() + "_QSVM"
if class3 is None: #Bug in package prevents saving Multiclass svms. Will find workaround or submit bug report if time.
qsvm.save_model(path)
#VQC run
if include_VQC:
start = time.time()
optimizer = SPSA(max_trials=100, c0=4.0, skip_calibration=True)
optimizer.set_options(save_steps=1)
feature_map = ZZFeatureMap(feature_dimension=feature_dim, reps=2)
var_form = TwoLocal(feature_dim, ['ry', 'rz'], 'cz', reps=3)
vqc = VQC(optimizer, feature_map, var_form, training_data, test_data, total_array)
quantum_instance = QuantumInstance(backend, shots=1024, seed_simulator=10589, seed_transpiler=10598)
resultVQC = vqc.run(quantum_instance)
end = time.time()
VQC_Summary = ["VQC", backend.name(), round(end-start), str(round(100*resultVQC['testing_accuracy'], 2)), checkAllSame(resultVQC['predicted_classes'])]
data.append(VQC_Summary)
path = 'C:\\Users\\admin\\Desktop\\QQML\\Code\\Saved_SVMs\\' + name + "_" + backend.name() + "_VQC"
vqc.save_model(path)
display(HTML(tabulate.tabulate(data, tablefmt='html')))
return data
