def test_vqc_statevector(self, mode): """ vqc statevector test """ aqua_globals.random_seed = 10598 optimizer = COBYLA() data_preparation = self.data_preparation[mode] wavefunction = self.ryrz_wavefunction[mode] if mode == 'wrapped': warnings.filterwarnings('ignore', category=DeprecationWarning) # set up algorithm vqc = VQC(optimizer, data_preparation, wavefunction, self.training_data, self.testing_data) if mode in ['circuit', 'library']: vqc._feature_map_params = self._sorted_data_params vqc._var_form_params = self._sorted_wavefunction_params else: warnings.filterwarnings('always', category=DeprecationWarning) quantum_instance = QuantumInstance( BasicAer.get_backend('statevector_simulator'), seed_simulator=aqua_globals.random_seed, seed_transpiler=aqua_globals.random_seed) result = vqc.run(quantum_instance) ref_train_loss = 0.1059404 np.testing.assert_array_almost_equal(result['training_loss'], ref_train_loss, decimal=4) self.assertEqual(result['testing_accuracy'], 0.5)
def test_vqc_minibatching_with_gradient_support(self, mode): """ vqc minibatching with gradient support test """ n_dim = 2 # dimension of each data point seed = 1024 aqua_globals.random_seed = seed _, training_input, test_input, _ = ad_hoc_data(training_size=4, test_size=2, n=n_dim, gap=0.3, plot_data=False) backend = BasicAer.get_backend('statevector_simulator') optimizer = L_BFGS_B(maxfun=30) # set up data encoding circuit data_preparation = self.data_preparation[mode] # set up wavefunction if mode == 'wrapped': warnings.filterwarnings('ignore', category=DeprecationWarning) wavefunction = RYRZ(2, depth=1) else: wavefunction = TwoLocal(2, ['ry', 'rz'], 'cz', reps=1, insert_barriers=True) theta = ParameterVector('theta', wavefunction.num_parameters) resorted = [] for i in range(4): layer = wavefunction.ordered_parameters[4 * i:4 * (i + 1)] resorted += layer[::2] resorted += layer[1::2] wavefunction.assign_parameters(dict(zip(resorted, theta)), inplace=True) if mode == 'circuit': wavefunction = QuantumCircuit(2).compose(wavefunction) # set up algorithm vqc = VQC(optimizer, data_preparation, wavefunction, training_input, test_input, minibatch_size=2) if mode in ['circuit', 'library']: vqc._feature_map_params = self._sorted_data_params vqc._var_form_params = list(theta) else: warnings.filterwarnings('always', category=DeprecationWarning) quantum_instance = QuantumInstance(backend, seed_simulator=seed, seed_transpiler=seed) result = vqc.run(quantum_instance) vqc_accuracy = 0.5 self.log.debug(result['testing_accuracy']) self.assertAlmostEqual(result['testing_accuracy'], vqc_accuracy, places=3)
def test_vqc_on_wine(self, mode): """Test VQE on the wine test using circuits as feature map and variational form.""" feature_dim = 4 # dimension of each data point training_dataset_size = 6 testing_dataset_size = 3 _, training_input, test_input, _ = wine( training_size=training_dataset_size, test_size=testing_dataset_size, n=feature_dim, plot_data=False) aqua_globals.random_seed = self.seed if mode == 'wrapped': warnings.filterwarnings('ignore', category=DeprecationWarning) data_preparation = SecondOrderExpansion(feature_dim) wavefunction = RYRZ(feature_dim, depth=1) else: data_preparation = ZZFeatureMap(feature_dim) x = data_preparation.ordered_parameters wavefunction = TwoLocal(feature_dim, ['ry', 'rz'], 'cz', reps=1, insert_barriers=True) theta = ParameterVector('theta', wavefunction.num_parameters) resorted = [] for i in range(2 * feature_dim): layer = wavefunction.ordered_parameters[2 * feature_dim * i:2 * feature_dim * (i + 1)] resorted += layer[::2] resorted += layer[1::2] wavefunction.assign_parameters(dict(zip(resorted, theta)), inplace=True) if mode == 'circuit': data_preparation = QuantumCircuit(feature_dim).compose( data_preparation) wavefunction = QuantumCircuit(feature_dim).compose(wavefunction) vqc = VQC(COBYLA(maxiter=100), data_preparation, wavefunction, training_input, test_input) # sort parameters for reproducibility if mode in ['circuit', 'library']: vqc._feature_map_params = list(x) vqc._var_form_params = list(theta) else: warnings.filterwarnings('always', category=DeprecationWarning) result = vqc.run( QuantumInstance(BasicAer.get_backend('statevector_simulator'), shots=1024, seed_simulator=aqua_globals.random_seed, seed_transpiler=aqua_globals.random_seed)) self.log.debug(result['testing_accuracy']) self.assertLess(result['testing_accuracy'], 0.6)
def test_vqc_callback(self, mode): """ vqc callback test """ history = { 'eval_count': [], 'parameters': [], 'cost': [], 'batch_index': [] } def store_intermediate_result(eval_count, parameters, cost, batch_index): history['eval_count'].append(eval_count) history['parameters'].append(parameters) history['cost'].append(cost) history['batch_index'].append(batch_index) aqua_globals.random_seed = self.seed backend = BasicAer.get_backend('qasm_simulator') optimizer = COBYLA(maxiter=3) data_preparation = self.data_preparation[mode] wavefunction = self.ryrz_wavefunction[mode] if mode == 'wrapped': warnings.filterwarnings('ignore', category=DeprecationWarning) # set up algorithm vqc = VQC(optimizer, data_preparation, wavefunction, self.training_data, self.testing_data, callback=store_intermediate_result) if mode in ['circuit', 'library']: vqc._feature_map_params = self._sorted_data_params vqc._var_form_params = self._sorted_wavefunction_params else: warnings.filterwarnings('always', category=DeprecationWarning) quantum_instance = QuantumInstance(backend, shots=1024, seed_simulator=self.seed, seed_transpiler=self.seed) vqc.run(quantum_instance) self.assertTrue( all(isinstance(count, int) for count in history['eval_count'])) self.assertTrue( all(isinstance(cost, float) for cost in history['cost'])) self.assertTrue( all(isinstance(index, int) for index in history['batch_index'])) for params in history['parameters']: self.assertTrue(all(isinstance(param, float) for param in params))
def test_vqc_with_max_evals_grouped(self, use_circuits): """ vqc with max evals grouped test """ aqua_globals.random_seed = self.seed optimizer = SPSA(max_trials=10, save_steps=1, c0=4.0, c1=0.1, c2=0.602, c3=0.101, c4=0.0, skip_calibration=True) feature_map = SecondOrderExpansion( feature_dimension=get_feature_dimension(self.training_data), depth=2) var_form = RYRZ(num_qubits=feature_map.num_qubits, depth=3) # convert to circuit if circuits should be used if use_circuits: x = ParameterVector('x', feature_map.feature_dimension) feature_map = feature_map.construct_circuit(x) theta = ParameterVector('theta', var_form.num_parameters) var_form = var_form.construct_circuit(theta) # set up algorithm vqc = VQC(optimizer, feature_map, var_form, self.training_data, self.testing_data, max_evals_grouped=2) # sort parameters for reproducibility if use_circuits: vqc._feature_map_params = list(x) vqc._var_form_params = list(theta) quantum_instance = QuantumInstance( BasicAer.get_backend('qasm_simulator'), shots=1024, seed_simulator=aqua_globals.random_seed, seed_transpiler=aqua_globals.random_seed) result = vqc.run(quantum_instance) np.testing.assert_array_almost_equal(result['opt_params'], self.ref_opt_params, decimal=8) np.testing.assert_array_almost_equal(result['training_loss'], self.ref_train_loss, decimal=8) self.assertEqual(1.0, result['testing_accuracy'])
def test_vqc_minibatching_with_gradient_support(self, use_circuits): """ vqc minibatching with gradient support test """ n_dim = 2 # dimension of each data point seed = 1024 aqua_globals.random_seed = seed _, training_input, test_input, _ = ad_hoc_data(training_size=4, test_size=2, n=n_dim, gap=0.3, plot_data=False) backend = BasicAer.get_backend('statevector_simulator') num_qubits = n_dim optimizer = L_BFGS_B(maxfun=30) feature_map = SecondOrderExpansion(feature_dimension=num_qubits, depth=2) var_form = RYRZ(num_qubits=num_qubits, depth=1) # convert to circuit if circuits should be used if use_circuits: x = ParameterVector('x', feature_map.feature_dimension) feature_map = feature_map.construct_circuit(x) theta = ParameterVector('theta', var_form.num_parameters) var_form = var_form.construct_circuit(theta) # set up algorithm vqc = VQC(optimizer, feature_map, var_form, training_input, test_input, minibatch_size=2) # sort parameters for reproducibility if use_circuits: vqc._feature_map_params = list(x) vqc._var_form_params = list(theta) quantum_instance = QuantumInstance(backend, seed_simulator=seed, seed_transpiler=seed) result = vqc.run(quantum_instance) vqc_accuracy = 0.5 self.log.debug(result['testing_accuracy']) self.assertAlmostEqual(result['testing_accuracy'], vqc_accuracy, places=3)
def test_vqc_with_max_evals_grouped(self, mode): """ vqc with max evals grouped test """ aqua_globals.random_seed = self.seed optimizer = SPSA(max_trials=10, save_steps=1, c0=4.0, c1=0.1, c2=0.602, c3=0.101, c4=0.0, skip_calibration=True) data_preparation = self.data_preparation[mode] wavefunction = self.ryrz_wavefunction[mode] if mode == 'wrapped': warnings.filterwarnings('ignore', category=DeprecationWarning) # set up algorithm vqc = VQC(optimizer, data_preparation, wavefunction, self.training_data, self.testing_data, max_evals_grouped=2) if mode in ['circuit', 'library']: vqc._feature_map_params = self._sorted_data_params vqc._var_form_params = self._sorted_wavefunction_params else: warnings.filterwarnings('always', category=DeprecationWarning) quantum_instance = QuantumInstance( BasicAer.get_backend('qasm_simulator'), shots=1024, seed_simulator=aqua_globals.random_seed, seed_transpiler=aqua_globals.random_seed) result = vqc.run(quantum_instance) np.testing.assert_array_almost_equal(result['opt_params'], self.ref_opt_params, decimal=8) np.testing.assert_array_almost_equal(result['training_loss'], self.ref_train_loss, decimal=8) self.assertEqual(1.0, result['testing_accuracy'])
def test_vqc_minibatching_no_gradient_support(self, mode): """ vqc minibatching with no gradient support test """ n_dim = 2 # dimension of each data point seed = 1024 aqua_globals.random_seed = seed _, training_input, test_input, _ = ad_hoc_data(training_size=6, test_size=3, n=n_dim, gap=0.3, plot_data=False) backend = BasicAer.get_backend('statevector_simulator') optimizer = COBYLA(maxiter=40) data_preparation = self.data_preparation[mode] wavefunction = self.ryrz_wavefunction[mode] if mode == 'wrapped': warnings.filterwarnings('ignore', category=DeprecationWarning) # set up algorithm vqc = VQC(optimizer, data_preparation, wavefunction, training_input, test_input, minibatch_size=2) if mode in ['circuit', 'library']: vqc._feature_map_params = self._sorted_data_params vqc._var_form_params = self._sorted_wavefunction_params else: warnings.filterwarnings('always', category=DeprecationWarning) quantum_instance = QuantumInstance(backend, seed_simulator=seed, seed_transpiler=seed, optimization_level=0) result = vqc.run(quantum_instance) self.log.debug(result['testing_accuracy']) self.assertGreaterEqual(result['testing_accuracy'], 0.5)
def test_vqc_on_wine(self, use_circuits): """Test VQE on the wine test using circuits as feature map and variational form.""" feature_dim = 4 # dimension of each data point training_dataset_size = 6 testing_dataset_size = 3 _, training_input, test_input, _ = wine( training_size=training_dataset_size, test_size=testing_dataset_size, n=feature_dim, plot_data=False) aqua_globals.random_seed = self.seed feature_map = SecondOrderExpansion(feature_dimension=feature_dim) var_form = RYRZ(feature_map.num_qubits, depth=1) # convert to circuit if circuits should be used if use_circuits: x = ParameterVector('x', feature_map.feature_dimension) feature_map = feature_map.construct_circuit(x) theta = ParameterVector('theta', var_form.num_parameters) var_form = var_form.construct_circuit(theta) vqc = VQC(COBYLA(maxiter=100), feature_map, var_form, training_input, test_input) # sort parameters for reproducibility if use_circuits: vqc._feature_map_params = list(x) vqc._var_form_params = list(theta) result = vqc.run( QuantumInstance(BasicAer.get_backend('statevector_simulator'), shots=1024, seed_simulator=aqua_globals.random_seed, seed_transpiler=aqua_globals.random_seed)) self.log.debug(result['testing_accuracy']) self.assertLess(result['testing_accuracy'], 0.6)
def test_vqc_statevector(self, use_circuits): """ vqc statevector test """ aqua_globals.random_seed = 10598 optimizer = COBYLA() feature_map = SecondOrderExpansion( feature_dimension=get_feature_dimension(self.training_data), depth=2) var_form = RYRZ(num_qubits=feature_map.num_qubits, depth=3) # convert to circuit if circuits should be used if use_circuits: x = ParameterVector('x', feature_map.feature_dimension) feature_map = feature_map.construct_circuit(x) theta = ParameterVector('theta', var_form.num_parameters) var_form = var_form.construct_circuit(theta) # set up algorithm vqc = VQC(optimizer, feature_map, var_form, self.training_data, self.testing_data) # sort parameters for reproducibility if use_circuits: vqc._feature_map_params = list(x) vqc._var_form_params = list(theta) quantum_instance = QuantumInstance( BasicAer.get_backend('statevector_simulator'), seed_simulator=aqua_globals.random_seed, seed_transpiler=aqua_globals.random_seed) result = vqc.run(quantum_instance) ref_train_loss = 0.1059404 np.testing.assert_array_almost_equal(result['training_loss'], ref_train_loss, decimal=4) self.assertEqual(result['testing_accuracy'], 0.5)
def test_save_and_load_model(self, mode): """ save and load model test """ aqua_globals.random_seed = self.seed backend = BasicAer.get_backend('qasm_simulator') optimizer = SPSA(max_trials=10, save_steps=1, c0=4.0, skip_calibration=True) data_preparation = self.data_preparation[mode] wavefunction = self.ryrz_wavefunction[mode] if mode == 'wrapped': warnings.filterwarnings('ignore', category=DeprecationWarning) # set up algorithm vqc = VQC(optimizer, data_preparation, wavefunction, self.training_data, self.testing_data) if mode in ['circuit', 'library']: vqc._feature_map_params = self._sorted_data_params vqc._var_form_params = self._sorted_wavefunction_params quantum_instance = QuantumInstance(backend, shots=1024, seed_simulator=self.seed, seed_transpiler=self.seed) result = vqc.run(quantum_instance) np.testing.assert_array_almost_equal(result['opt_params'], self.ref_opt_params, decimal=4) np.testing.assert_array_almost_equal(result['training_loss'], self.ref_train_loss, decimal=8) self.assertEqual(1.0, result['testing_accuracy']) file_path = self.get_resource_path('vqc_test.npz') vqc.save_model(file_path) self.assertTrue(os.path.exists(file_path)) loaded_vqc = VQC(optimizer, data_preparation, wavefunction, self.training_data, None) # sort parameters for reproducibility if mode in ['circuit', 'library']: loaded_vqc._feature_map_params = self._sorted_data_params loaded_vqc._var_form_params = self._sorted_wavefunction_params else: warnings.filterwarnings('always', category=DeprecationWarning) loaded_vqc.load_model(file_path) np.testing.assert_array_almost_equal(loaded_vqc.ret['opt_params'], self.ref_opt_params, decimal=4) loaded_test_acc = loaded_vqc.test(vqc.test_dataset[0], vqc.test_dataset[1], quantum_instance) self.assertEqual(result['testing_accuracy'], loaded_test_acc) predicted_probs, predicted_labels = loaded_vqc.predict( self.testing_data['A'], quantum_instance) np.testing.assert_array_almost_equal(predicted_probs, self.ref_prediction_a_probs, decimal=8) np.testing.assert_array_equal(predicted_labels, self.ref_prediction_a_label) if os.path.exists(file_path): try: os.remove(file_path) except Exception: # pylint: disable=broad-except pass
def test_save_and_load_model(self, use_circuits): """ save and load model test """ aqua_globals.random_seed = self.seed backend = BasicAer.get_backend('qasm_simulator') num_qubits = 2 optimizer = SPSA(max_trials=10, save_steps=1, c0=4.0, skip_calibration=True) feature_map = SecondOrderExpansion(feature_dimension=num_qubits, depth=2) var_form = RYRZ(num_qubits=num_qubits, depth=3) # convert to circuit if circuits should be used if use_circuits: x = ParameterVector('x', feature_map.feature_dimension) feature_map = feature_map.construct_circuit(x) theta = ParameterVector('theta', var_form.num_parameters) var_form = var_form.construct_circuit(theta) # set up algorithm vqc = VQC(optimizer, feature_map, var_form, self.training_data, self.testing_data) # sort parameters for reproducibility if use_circuits: vqc._feature_map_params = list(x) vqc._var_form_params = list(theta) quantum_instance = QuantumInstance(backend, shots=1024, seed_simulator=self.seed, seed_transpiler=self.seed) result = vqc.run(quantum_instance) np.testing.assert_array_almost_equal(result['opt_params'], self.ref_opt_params, decimal=4) np.testing.assert_array_almost_equal(result['training_loss'], self.ref_train_loss, decimal=8) self.assertEqual(1.0, result['testing_accuracy']) file_path = self.get_resource_path('vqc_test.npz') vqc.save_model(file_path) self.assertTrue(os.path.exists(file_path)) loaded_vqc = VQC(optimizer, feature_map, var_form, self.training_data, None) # sort parameters for reproducibility if use_circuits: loaded_vqc._feature_map_params = list(x) loaded_vqc._var_form_params = list(theta) loaded_vqc.load_model(file_path) np.testing.assert_array_almost_equal(loaded_vqc.ret['opt_params'], self.ref_opt_params, decimal=4) loaded_test_acc = loaded_vqc.test(vqc.test_dataset[0], vqc.test_dataset[1], quantum_instance) self.assertEqual(result['testing_accuracy'], loaded_test_acc) predicted_probs, predicted_labels = loaded_vqc.predict( self.testing_data['A'], quantum_instance) np.testing.assert_array_almost_equal(predicted_probs, self.ref_prediction_a_probs, decimal=8) np.testing.assert_array_equal(predicted_labels, self.ref_prediction_a_label) if os.path.exists(file_path): try: os.remove(file_path) except Exception: # pylint: disable=broad-except pass