pyrimidine.local_search subpackage

pyrimidine.local_search.random_walk module

class pyrimidine.local_search.random_walk.RandomWalk

Bases: FitnessMixin

Random Walk Algo.

mutate(sigma)

params = {'sigma': 1}

transit(k, *args, **kwargs)

pyrimidine.local_search.simulated_annealing module

Simulated Annealing Algorithm

Ref S. Kirkpatrick, C. D. Gelatt, Jr., M. P. Vecchi. Optimization by Simulated Annealing. 1983: 220(4598): 671-679

class pyrimidine.local_search.simulated_annealing.SimulatedAnnealing(*args, **kwargs)

Bases: PhantomIndividual

Class for Simulated Annealing

params

parameters in SA

Type:

dict

alias = {'chromosomes': 'elements', 'n_chromosomes': 'n_elements'}

apply(f, *args, **kwargs)

property elements

isa(cls)

move(T)

Move phantom

Parameters:

temperature (T {number} --)

property n_elements

params = {'ext_c': 0.99, 'initT': 100, 'int_c': 0.99, 'max_iter': 100, 'n_epochs': 200, 'termT': 0.0001}

regester(name, key, force=True)

regester_map(name, key=None, force=True)

transition(*args, **kwargs)

The core method of the object.

This method transitions one state of the object to another state based on certain rules, such as crossing and mutating for individuals in GA, or the moving method in Simulated Annealing.

pyrimidine.local_search.tabu_search module

Tabu Search was created by Fred W. Glover in 1986 and formalized in 1989

References Glover, Fred W. and Manuel Laguna. “Tabu Search.” (1997). Glover, Fred W.. “Tabu Search - Part I.” INFORMS J. Comput. 1 (1989): 190-206. Glover, Fred W.. “Tabu Search - Part II.” INFORMS J. Comput. 2 (1989): 4-32.

class pyrimidine.local_search.tabu_search.BaseTabuSearch(*args, **kwargs)

Bases: BaseIndividual

Tabu Search algorithm

alias = {'chromosomes': 'elements', 'n_chromosomes': 'n_elements'}

apply(f, *args, **kwargs)

backup(check=True)

Backup the fitness and other information

Parameters:

check (bool, optional) – check whether the fitness increases.

copy(*args, **kwargs)

copy the object

Parameters:

• type – the type of new object

• element_class (None, optional) – the new element_class

Returns:

a new object copy the data but with new type

property elements

property fitness

get_neighbour(action)

to get a neighbour of an individual

e.g. mutate only one gene

init()

isa(cls)

property memory

property n_elements

params = {'actions': [], 'max_iter': 100, 'tabu_list': [], 'tabu_size': 10, 'value': 0}

regester(name, key, force=True)

regester_map(name, key=None, force=True)

set_memory(**d)

property solution

get the attribute from memory, where the best solution is stored

transition(*args, **kwargs)

The core method of the object.

This method transitions one state of the object to another state based on certain rules, such as crossing and mutating for individuals in GA, or the moving method in Simulated Annealing.

update_tabu_list()

class pyrimidine.local_search.tabu_search.SimpleTabuSearch(*args, **kwargs)

Bases: BaseTabuSearch

alias = {'chromosomes': 'elements', 'n_chromosomes': 'n_elements'}

apply(f, *args, **kwargs)

property elements

get_neighbour(action)

to get a neighbour of an individual

e.g. mutate only one gene

isa(cls)

property n_elements

params = {'actions': [], 'max_iter': 100, 'tabu_list': [], 'tabu_size': 10, 'value': 0}

regester(name, key, force=True)

regester_map(name, key=None, force=True)

pyrimidine.local_search.tabu_search.random() → x in the interval [0, 1).