scikit_quri.qsvm package

scikit_quri.qsvm package#

Submodules#

scikit_quri.qsvm.base_qsv module#

class scikit_quri.qsvm.base_qsv.SVMethodType(value)[source]#

Bases: Enum

An enumeration.

SVC = 1#
SVR = 2#
class scikit_quri.qsvm.base_qsv.BaseQSV(circuit, sv_method_type)[source]#

Bases: object

Base class for Quantum Support Vector Machine.

Parameters:
fit(x, y, sampler, n_shots=1000, max_iter=10000000, verbose=False)[source]#

Fit the model to the training data.

Parameters:

  • x (ndarray[tuple[int, ...], dtype[float64]]) – Training feature matrix of shape (n_samples, n_features).

  • y (ndarray[tuple[int, ...], dtype[float64]]) – Training labels.

  • sampler (BaseSampler) – Sampling backend (e.g. QulacsSampler or OqtopusSampler).

  • n_shots (int) – Number of shots per circuit execution. Defaults to 1000.

  • max_iter (int) – Maximum number of iterations for the SVM solver. Defaults to 1e7.

  • verbose (bool) – Whether to print the SVM training progress. Defaults to False.

Return type:

None

predict(xs)[source]#

Predict outcomes for the given test data.

Parameters:

xs (ndarray[tuple[int, ...], dtype[float64]]) – Test feature matrix of shape (n_samples, n_features).

Returns:

Predicted values of shape (n_samples,).

Return type:

pred

class scikit_quri.qsvm.base_qsv.QSVC(circuit)[source]#

Bases: BaseQSV

Quantum Support Vector Classifier.

Parameters:

circuit (LearningCircuit) – LearningCircuit

class scikit_quri.qsvm.base_qsv.QSVR(circuit)[source]#

Bases: BaseQSV

Quantum Support Vector Regressor.

Parameters:

circuit (LearningCircuit) – LearningCircuit

Module contents#

class scikit_quri.qsvm.QSVC(circuit)[source]

Bases: BaseQSV

Quantum Support Vector Classifier.

Parameters:

circuit (LearningCircuit) – LearningCircuit

class scikit_quri.qsvm.QSVR(circuit)[source]

Bases: BaseQSV

Quantum Support Vector Regressor.

Parameters:

circuit (LearningCircuit) – LearningCircuit

Contents