qiskit.chemistry.algorithms.pes_samplers.PCAExtrapolator¶

class PCAExtrapolator(extrapolator=None, kernel=None, window=2)[source]¶

A wrapper extrapolator which reduces the points” dimensionality with PCA, performs extrapolation in the transformed pca space, and inverse transforms the results before returning. A user specifies the kernel within how the PCA transformation should be done.

Constructor.

Paramètres

extrapolator (Union[PolynomialExtrapolator, DifferentialExtrapolator, None]) – “internal” extrapolator that performs extrapolation on variational parameters based on data window.
kernel (Optional[str]) – Kernel (from sklearn) that specifies how dimensionality reduction should be done for PCA. Default value is None, and switches the extrapolation to standard PCA.
window (int) – Number of previous points to use for extrapolation.

Lève

AquaError – if kernel is not defined in sklearn module.

__init__(extrapolator=None, kernel=None, window=2)[source]¶

Constructor.

Paramètres

extrapolator (Union[PolynomialExtrapolator, DifferentialExtrapolator, None]) – “internal” extrapolator that performs extrapolation on variational parameters based on data window.
kernel (Optional[str]) – Kernel (from sklearn) that specifies how dimensionality reduction should be done for PCA. Default value is None, and switches the extrapolation to standard PCA.
window (int) – Number of previous points to use for extrapolation.

Lève

AquaError – if kernel is not defined in sklearn module.

Methods

`__init__`([extrapolator, kernel, window])	Constructor.
`extrapolate`(points, param_dict)	Extrapolate at specified point of interest given a set of variational parameters.
`factory`(mode, **kwargs)	Factory method for constructing extrapolators.

extrapolate(points, param_dict)[source]¶

Extrapolate at specified point of interest given a set of variational parameters. This method transforms the parameters in PCA space before performing the internal extrapolation. The parameters are transformed back to regular space after extrapolation.

Paramètres

points (List[float]) – List of point(s) to be used for extrapolation. Can represent some degree of freedom, ex, interatomic distance.
param_dict (Optional[Dict[float, List[float]]]) – Dictionary of variational parameters. Each key is the point
the value is a list of the variational parameters. (and) –

Type renvoyé

Dict[float, List[float]]

Renvoie

Dictionary of variational parameters for extrapolated point(s).

static factory(mode, **kwargs)¶

Factory method for constructing extrapolators.

Paramètres

mode (str) – Extrapolator to instantiate. Can be one of: - “window” - “poly” - “diff_model” - “pca” - “l1”
kwargs – arguments to be passed to the constructor of an extrapolator

Type renvoyé

Extrapolator

Renvoie

A newly created extrapolator instance.

Lève

AquaError – if specified mode is unknown.