macop.algorithms.Algorithm

Abstract Algorithm class used as basic algorithm implementation with some specific initialization

Classes

Algorithm(_initalizer, _evaluator, …[, …])

Algorithm class used as basic algorithm

class macop.algorithms.Algorithm.Algorithm(_initalizer, _evaluator, _operators, _policy, _validator, _maximise=True, _parent=None)

Algorithm class used as basic algorithm

initalizer

{function} – basic function strategy to initialize solution

evaluator

{function} – basic function in order to obtained fitness (mono or multiple objectives)

operators

{[Operator]} – list of operator to use when launching algorithm

policy

{Policy} – Policy class implementation strategy to select operators

validator

{function} – basic function to check if solution is valid or not under some constraints

maximise

{bool} – specify kind of optimization problem

currentSolution

{Solution} – current solution managed for current evaluation

bestSolution

{Solution} – best solution found so far during running algorithm

checkpoint

{Checkpoint} – Checkpoint class implementation to keep track of algorithm and restart

parent

{Algorithm} – parent algorithm reference in case of inner Algorithm instance (optional)

addCheckpoint(_class, _every, _filepath)

Add checkpoint to algorithm specifying usefull parameters

_class

{class} – Checkpoint class type

_every

{int} – checkpoint frequency based on evaluations

_filepath

{str} – file path where checkpoints will be saved

evaluate(solution)

Returns

fitness score of solution which is not already evaluated or changed

Note

if multi-objective problem this method can be updated using array of evaluator

getGlobalEvaluation()

Get the global number of evaluation (if inner algorithm)

Returns

{int} – current global number of evaluation

increaseEvaluation()

Increase number of evaluation once a solution is evaluated

initRun()

Method which initialiazes or re-initializes the whole algorithm context (operators, current solution, policy, best solution (by default current solution))

isBetter(solution)

Check if solution is better than best found

Returns

{bool} – True if better

resume()

Resume algorithm using checkpoint instance

Raises

ValueError – No checkpoint initialize (use addCheckpoint or setCheckpoint is you want to use this process)

run(_evaluations)

Run the specific algorithm following number of evaluations to find optima

setCheckpoint(_checkpoint)

Set checkpoint instance directly

_checkpoint

{Checkpoint} – checkpoint instance

stop()

Global stopping criteria (check for inner algorithm too)

update(solution)

Apply update function to solution using specific policy

Check if solution is valid after modification and returns it

Returns

{Solution} – updated solution obtained by the selected operator