pyanno4rt.optimization.methods

Optimization methods module.

This module aims to provide different types of optimization methods.

Overview

Classes
`LexicographicOptimization`	Lexicographic optimization problem class.
`ParetoOptimization`	Pareto problem class.
`WeightedSumOptimization`	Weighted-sum optimization problem class.

Attributes
`method_map`	-

Classes

class pyanno4rt.optimization.methods.LexicographicOptimization(backprojection, objectives, constraints)[source]

Lexicographic optimization problem class.

This class provides methods to perform lexicographic optimization. It features a component tracker and implements the respective objective, gradient, constraint and constraint jacobian functions.

Parameters:: backprojection (object of class)

:param DoseProjection ConstantRBEProjection: The object representing the type of backprojection. :param objectives: Dictionary with the internally configured objectives. :type objectives: dict :param constraints: Dictionary with the internally configured constraints. :type constraints: dict

backprojection

Type:: object of class

:class:`~pyanno4rt.optimization.projections._dose_projection.DoseProjection` :class:`~pyanno4rt.optimization.projections._constant_rbe_projection.ConstantRBEProjection`: See ‘Parameters’.

objectives

Dictionary with the rank-ordered objectives.

Type:: dict

constraints

Dictionary with the rank-ordered constraints.

Type:: dict

tracker

Dictionary with the iteration-wise component values.

Type:: dict

Overview

Methods
`objective`(fluence, layer, track)	Compute the objective function value.
`gradient`(fluence, layer)	Compute the gradient function value.
`constraint`(fluence, layer, track)	Compute the constraint function value(s).
`jacobian`(fluence, layer)	Compute the constraint jacobian function value.

Members

objective(fluence, layer, track=True)[source]

Compute the objective function value.

Parameters:

fluence (ndarray) – Fluence vector.
layer (int) – Current layer of the lexicographic order.
track (bool, default=True) – Indicator for tracking the single objective function values.

Returns:

Objective function value.

Return type:

float

gradient(fluence, layer)[source]

Compute the gradient function value.

Parameters:

fluence (ndarray) – Fluence vector.
layer (int) – Current layer of the lexicographic order.

Returns:

Gradient function value.

Return type:

ndarray

constraint(fluence, layer, track=True)[source]

Compute the constraint function value(s).

Parameters:

fluence (ndarray) – Fluence vector.
layer (int) – Current layer of the lexicographic order.
track (bool, default=True) – Indicator for tracking the constraint function value(s).

Returns:

Constraint function value(s).

Return type:

float

jacobian(fluence, layer)[source]

Compute the constraint jacobian function value.

Parameters:

fluence (ndarray) – Fluence vector.
layer (int) – Current layer of the lexicographic order.

Returns:

Constraint jacobian function value.

Return type:

ndarray

class pyanno4rt.optimization.methods.ParetoOptimization(backprojection, objectives, constraints)[source]

Pareto problem class.

This class provides methods to perform pareto optimization. It implements the respective objective and constraint functions.

Parameters:: backprojection (object of class)

:param DoseProjection ConstantRBEProjection: The object representing the type of backprojection. :param objectives: Dictionary with the internally configured objectives. :type objectives: dict :param constraints: Dictionary with the internally configured constraints. :type constraints: dict

backprojection

Type:: object of class

:class:`~pyanno4rt.optimization.projections._dose_projection.DoseProjection` :class:`~pyanno4rt.optimization.projections._constant_rbe_projection.ConstantRBEProjection`: See ‘Parameters’.

objectives

See ‘Parameters’.

Type:: dict

constraints

See ‘Parameters’.

Type:: dict

Overview

Methods
`objective`(fluence)	Compute the objective function value(s).
`constraint`(fluence)	Compute the constraint function value(s).

Members

objective(fluence)[source]

Compute the objective function value(s).

Parameters:: fluence (ndarray) – Fluence vector.
Returns:: Objective function value(s).
Return type:: list

constraint(fluence)[source]

Compute the constraint function value(s).

Parameters:: fluence (ndarray) – Fluence vector.
Returns:: Constraint function value(s).
Return type:: list

class pyanno4rt.optimization.methods.WeightedSumOptimization(backprojection, objectives, constraints)[source]

Weighted-sum optimization problem class.

This class provides methods to perform weighted-sum optimization. It features a component tracker and implements the respective objective, gradient, constraint and constraint jacobian functions.

Parameters:: backprojection (object of class)

:param DoseProjection ConstantRBEProjection: The object representing the type of backprojection. :param objectives: Dictionary with the internally configured objectives. :type objectives: dict :param constraints: Dictionary with the internally configured constraints. :type constraints: dict

backprojection

Type:: object of class

:class:`~pyanno4rt.optimization.projections._dose_projection.DoseProjection` :class:`~pyanno4rt.optimization.projections._constant_rbe_projection.ConstantRBEProjection`: See ‘Parameters’.

objectives

See ‘Parameters’.

Type:: dict

constraints

See ‘Parameters’.

Type:: dict

tracker

Dictionary with the iteration-wise component values.

Type:: dict

Overview

Methods
`objective`(fluence, track)	Compute the objective function value.
`gradient`(fluence)	Compute the gradient function value.
`constraint`(fluence, track)	Compute the constraint function value(s).
`jacobian`(fluence)	Compute the constraint jacobian function value.

Members

objective(fluence, track=True)[source]

Compute the objective function value.

Parameters:

fluence (ndarray) – Fluence vector.
track (bool, default=True) – Indicator for tracking the single objective function values.

Returns:

Objective function value.

Return type:

float

gradient(fluence)[source]

Compute the gradient function value.

Parameters:: fluence (ndarray) – Fluence vector.
Returns:: Gradient function value.
Return type:: ndarray

constraint(fluence, track=True)[source]

Compute the constraint function value(s).

Parameters:

fluence (ndarray) – Fluence vector.
track (bool, default=True) – Indicator for tracking the constraint function value(s).

Returns:

Constraint function value(s).

Return type:

float

jacobian(fluence)[source]

Compute the constraint jacobian function value.

Parameters:: fluence (ndarray) – Fluence vector.
Returns:: Constraint jacobian function value.
Return type:: ndarray

Attributes

pyanno4rt.optimization.methods.method_map