qxmt.models.base module#

class qxmt.models.base.BaseKernelModel(kernel)

Bases: BaseMLModel

Base class for kernel-based quantum machine learning models. This class is an abstract class for kernel-based quantum machine learning models. If you want to implement a new kernel-based quantum machine learning model, you should inherit this class. This class requires a kernel instance of BaseKernel class. The user can use any Feature Map or Kernel to be used, as long as it follows the interface of the BaseKernel class.

Parameters:: kernel (BaseKernel)

__init__(kernel)

Initialize the kernel model.

Parameters:: kernel (BaseKernel) – kernel instance of BaseKernel class
Return type:: None

get_feature_map()

Get the feature map of the model.

Returns:: feature map instance
Return type:: BaseFeatureMap

get_kernel_matrix(x_array_1, x_array_2, n_jobs=3)

Get the kernel matrix of the given data. This method is alias of kernel.compute_matrix().

Parameters:

x_array_1 (np.ndarray) – array of samples (ex: training data)
x_array_2 (np.ndarray) – array of samples (ex: test data)
n_jobs (int)

Returns:

kernel matrix

Return type:

np.ndarray

plot_kernel_matrix(x_array_1, x_array_2, n_jobs=3)

Plot the kernel matrix of the given data. This method is alias of kernel.plot_matrix().

Parameters:

x_array_1 (np.ndarray) – array of samples (ex: training data)
x_array_2 (np.ndarray) – array of samples (ex: test data)
n_jobs (int)

Return type:

None

plot_train_test_kernel_matrix(x_train, x_test, n_jobs=3)

Plot the kernel matrix of training and testing data. This method is alias of kernel.plot_train_test_matrix().

Parameters:

x_train (np.ndarray) – array of training samples
x_test (np.ndarray) – array of testing samples
n_jobs (int)

Return type:

None

class qxmt.models.base.BaseMLModel

Bases: ABC

Base class for quantum machine learning models. This class is an abstract class for qunatum machine learning models. If you want to implement a new quantum machine learning model, you should inherit this class. For compatibility with QXMT framework, you should implement some methods such as fit, predict, save, load, get_params, and set_params.

abstract fit(X, y, **kwargs)

Fit the model with given data.

Parameters:

X (np.ndarray) – array of features
y (np.ndarray) – array of target value
kwargs (Any)

Return type:

None

abstract get_params()

Get the parameters of the model.

Returns:: dictionary of parameters
Return type:: dict

abstract load(path)

Load the model from the given path. [TODO]: standardize the save/load method using same library

Parameters:: path (str | Path) – path to load the model
Return type:: BaseMLModel

abstract predict(X)

Predict the target value with given features.

Parameters:: X (np.ndarray) – array of features
Returns:: array of predicted value
Return type:: np.ndarray

abstract save(path)

Save the model to the given path. [TODO]: standardize the save/load method using same library

Parameters:: path (str | Path) – path to save the model
Return type:: None

abstract set_params(params)

Set the parameters of the model.

Parameters:: params (dict) – dictionary of parameters
Return type:: None