def set_parameters(self,
n=None,
alpha=0.1,
gamma=0.3,
rho=-0.2,
sigma=-0.2,
**ukwargs):
r"""Set the arguments of an algorithm.
Arguments:
n (Optional[int]): Number of individuals.
alpha (Optional[float]): Reflection coefficient parameter
gamma (Optional[float]): Expansion coefficient parameter
rho (Optional[float]): Contraction coefficient parameter
sigma (Optional[float]): Shrink coefficient parameter
See Also:
* :func:`NiaPy.algorithms.Algorithm.setParameters`
"""
Algorithm.set_parameters(self,
n=n,
init_pop_func=ukwargs.pop(
'init_pop_func', self.init_pop),
**ukwargs)
self.alpha, self.gamma, self.rho, self.sigma = alpha, gamma, rho, sigma
def set_parameters(self, **ukwargs): r"""Set the algorithm parameters/arguments. Args: ukwargs (dict): Additional keyword arguments. """ Algorithm.set_parameters(self, **ukwargs)
def set_parameters(self,
M=40,
NoLsTests=5,
NoLs=5,
NoLsBest=5,
NoEnabled=17,
BONUS1=10,
BONUS2=1,
LSs=(MTS_LS1, MTS_LS2, MTS_LS3),
**ukwargs):
r"""Set the arguments of the algorithm.
Arguments:
M (int): Number of individuals in population.
NoLsTests (int): Number of test runs on local search algorithms.
NoLs (int): Number of local search algorithm runs.
NoLsBest (int): Number of locals search algorithm runs on best solution.
NoEnabled (int): Number of best solution for testing.
BONUS1 (int): Bonus for improving global best solution.
BONUS2 (int): Bonus for improving self.
LSs (Iterable[Callable[[numpy.ndarray, float, numpy.ndarray, float, bool, numpy.ndarray, Task, Dict[str, Any]], Tuple[numpy.ndarray, float, numpy.ndarray, float, bool, int, numpy.ndarray]]]): Local searches to use.
See Also:
* :func:`NiaPy.algorithms.Algorithm.setParameters`
"""
Algorithm.set_parameters(self, n=ukwargs.pop('n', M), **ukwargs)
self.NoLsTests, self.NoLs, self.NoLsBest, self.NoEnabled, self.BONUS1, self.BONUS2 = NoLsTests, NoLs, NoLsBest, NoEnabled, BONUS1, BONUS2
self.LSs = LSs
def set_parameters(self,
n=100,
a=0.5,
epsilon=0.001,
alpha=1.0,
r=0.5,
qmin=0.0,
qmax=2.0,
**ukwargs):
r"""Set the parameters of the algorithm.
Args:
n (int): Number of individuals in population.
a (Optional[float]): Starting loudness.
epsilon (Optional[float]): Scaling factor.
alpha (Optional[float]): Constant for updating loudness.
r (Optional[float]): Pulse rate.
qmin (Optional[float]): Minimum frequency.
qmax (Optional[float]): Maximum frequency.
See Also:
* :func:`NiaPy.algorithms.Algorithm.setParameters`
"""
Algorithm.set_parameters(self, n=n, **ukwargs)
self.A, self.epsilon, self.alpha, self.r, self.Qmin, self.Qmax = a, epsilon, alpha, r, qmin, qmax
def test_init_population_numpy_fine(self):
r"""Test if custome generation initialization works ok."""
a = Algorithm(n=10, init_pop_func=init_pop_numpy)
t = Task(d=20, benchmark=Sphere())
self.assertTrue(
np.array_equal(np.full((10, t.D), 0.0),
a.init_population(t)[0]))
def set_parameters(self,
n=50,
F=1,
CR=0.8,
CrossMutt=cross_rand1,
**ukwargs):
r"""Set the algorithm parameters.
Args:
n (Optional[int]): Population size.
F (Optional[float]): Scaling factor.
CR (Optional[float]): Crossover rate.
CrossMutt (Optional[Callable[[numpy.ndarray, int, numpy.ndarray, float, float, mtrand.RandomState, list], numpy.ndarray]]): Crossover and mutation strategy.
ukwargs (Dict[str, Any]): Additional arguments.
See Also:
* :func:`WeOptPy.algorithms.Algorithm.setParameters`
"""
Algorithm.set_parameters(self,
n=n,
init_pop_func=ukwargs.pop(
'init_pop_func', default_individual_init),
itype=ukwargs.pop('itype', Individual),
**ukwargs)
self.F, self.CR, self.CrossMutt = F, CR, CrossMutt
def set_parameters(self, epsilon=1e-20, **ukwargs):
r"""Set core parameters of CovarianceMatrixAdaptionEvolutionStrategy algorithm.
Args:
epsilon (float): Small number.
ukwargs (Dict[str, Any]): Additional arguments.
"""
Algorithm.set_parameters(self, **ukwargs)
self.epsilon = epsilon
def set_parameters(self, delta=0.5, Neighborhood=neighborhood, **ukwargs):
r"""Set the algorithm parameters/arguments.
Args:
* delta (Optional[float]): Change for searching in neighborhood.
* Neighborhood (Optional[Callable[numpy.ndarray, float, Task], Tuple[numpy.ndarray, float]]]): Function for getting neighbours.
"""
Algorithm.set_parameters(self, n=1, **ukwargs)
self.delta, self.Neighborhood = delta, Neighborhood
def test_init_population_individual_fine(self):
r"""Test if custom generation initialization works ok."""
a = Algorithm(n=10,
init_pop_func=init_pop_individual,
itype=Individual)
t = Task(d=20, benchmark=Sphere())
i = Individual(x=np.full(t.D, 0.0), task=t)
pop, fpop, args, kwargs = a.init_population(t)
for e in pop:
self.assertEqual(i, e)
def set_parameters(self, n=25, a=3, Rmin=0, Rmax=2, **ukwargs):
r"""Set the arguments of an algorithm.
Args:
n (Optional[int]): Number of individual in population
a (Optional[float]): Parameter for control in :math:`r_1` value
Rmin (Optional[float]): Minimu value for :math:`r_3` value
Rmax (Optional[float]): Maximum value for :math:`r_3` value
See Also:
* :func:`NiaPy.algorithms.algorithm.Algorithm.setParameters`
"""
Algorithm.set_parameters(self, n=n, **ukwargs)
self.a, self.Rmin, self.Rmax = a, Rmin, Rmax
def set_parameters(self, n=25, p=0.35, beta=1.5, **ukwargs):
r"""Set core parameters of FlowerPollinationAlgorithm algorithm.
Args:
n (int): Population size.
p (float): Probability switch.
beta (float): Shape of the gamma distribution (should be greater than zero).
See Also:
* :func:`WeOptPy.algorithms.Algorithm.setParameters`
"""
Algorithm.set_parameters(self, n=n, **ukwargs)
self.p, self.beta = p, beta
self.S = np.zeros((n, 10))
def set_parameters(self, n=20, alpha=1, betamin=1, gamma=2, **ukwargs): r"""Set the parameters of the algorithm. Args: n (Optional[int]): Population size. alpha (Optional[float]): Alpha parameter. betamin (Optional[float]): Betamin parameter. gamma (Optional[flaot]): Gamma parameter. ukwargs (Dict[str, Any]): Additional arguments. See Also: * :func:`WeOptPy.algorithms.Algorithm.setParameters` """ Algorithm.set_parameters(self, n=n, **ukwargs) self.alpha, self.betamin, self.gamma = alpha, betamin, gamma
def set_parameters(self, N=50, pa=0.2, alpha=0.5, **ukwargs):
r"""Set the arguments of an algorithm.
Arguments:
N (int): Population size :math:`\in [1, \infty)`
pa (float): factor :math:`\in [0, 1]`
alpah (float): TODO
ukwargs (Dict[str, Any]): Additional arguments
See Also:
* :func:`WeOptPy.algorithms.Algorithm.setParameters`
"""
ukwargs.pop('n', None)
Algorithm.set_parameters(self, n=N, **ukwargs)
self.pa, self.alpha = pa, alpha
def init_population(self, task):
r"""Initialize first population and additional arguments.
Args:
task (Task): Optimization task
Returns:
Tuple[numpy.ndarray, numpy.ndarray, list, dict]:
1. Initialized population
2. Initialized population fitness/function values
3. Additional arguments.
4. Additional keyword arguments:
* Xpb (numpy.ndarray): Initialized populations best positions.
* Xpb_f (numpy.ndarray): Initialized populations best positions function/fitness values.
* alpha (numpy.ndarray): TODO.
* gamma (numpy.ndarray): TODO.
* theta (numpy.ndarray): TODO.
* rs (float): Distance of search space.
See Also:
* :func:`WeOptPy.algorithms.Algorithm.initPopulation`
* :func:`WeOptPy.algorithms.AnarchicSocietyOptimization.init`
"""
X, X_f, args, d = Algorithm.init_population(self, task)
alpha, gamma, theta = self.init(task)
Xpb, Xpb_f = self.update_best_and_personal_best(X, X_f, np.full([self.NP, task.D], 0.0), np.full(self.NP, task.optType.value * np.inf))
d.update({'Xpb': Xpb, 'Xpb_f': Xpb_f, 'alpha': alpha, 'gamma': gamma, 'theta': theta, 'rs': euclidean(task.Upper, task.Lower)})
return X, X_f, args, d
def init_population(self, task):
r"""Initialize starting population.
Args:
task (Task): Optimization task.
Returns:
Tuple[numpy.ndarray, numpy.ndarray, list, dict]:
1. Initialized population.
2. Initialized populations function/fitness value.
3. Additional arguments:
4. Additional keyword arguments:
* enable (numpy.ndarray): If solution/individual is enabled.
* improve (numpy.ndarray): If solution/individual is improved.
* SR (numpy.ndarray): Search range.
* grades (numpy.ndarray): Grade of solution/individual.
"""
X, X_f, args, d = Algorithm.init_population(self, task)
enable, improve, SR, grades = np.full(self.NP, True), np.full(
self.NP, True), np.full([self.NP, task.D],
task.bRange / 2), np.full(self.NP, 0.0)
d.update({
'enable': enable,
'improve': improve,
'SR': SR,
'grades': grades
})
return X, X_f, args, d
def type_parameters():
r"""Get dictionary with functions for checking values of parameters.
Returns:
Dict[str, Callable[[Union[list, dict]], bool]]:
* alpha (Callable[[Union[float, int]], bool]): TODO.
* gamma (Callable[[Union[float, int]], bool]): TODO.
* theta (Callable[[Union[float, int]], bool]): TODO.
* nl (Callable[[Union[float, int]], bool]): TODO.
* F (Callable[[Union[float, int]], bool]): TODO.
* CR (Callable[[Union[float, int]], bool]): TODO.
See Also:
* :func:`WeOptPy.algorithms.Algorithm.typeParameters`
"""
d = Algorithm.type_parameters()
d.update({
'alpha': lambda x: True,
'gamma': lambda x: True,
'theta': lambda x: True,
'nl': lambda x: True,
'F': lambda x: isinstance(x, (int, float)) and x > 0,
'CR': lambda x: isinstance(x, float) and 0 <= x <= 1
})
return d
def init_population(self, task):
r"""Initialize the starting population.
Parameters:
task (Task): Optimization task
Returns:
Tuple[numpy.ndarray, numpy.ndarray, list, dict]:
1. New population.
2. New population fitness/function values.
3. Additional arguments.
4. Additional keyword arguments:
* a (float): Loudness.
* S (numpy.ndarray): TODO
* Q (numpy.ndarray): TODO
* v (numpy.ndarray): TODO
See Also:
* :func:`WeOptPy.algorithms.Algorithm.initPopulation`
"""
sol, fitness, args, d = Algorithm.init_population(self, task)
a, s, Q, v = np.full(self.NP,
self.A), np.full([self.NP, task.D], 0.0), np.full(
self.NP, 0.0), np.full([self.NP, task.D], 0.0)
d.update({'a': a, 'S': s, 'Q': Q, 'v': v})
return sol, fitness, args, d
def init_population(self, task):
r"""Initialize the starting population.
Parameters:
task (Task): Optimization task
Returns:
Tuple[numpy.ndarray, numpy.ndarray[float], Dict[str, Any]]:
1. New population.
2. New population fitness/function values.
3. Additional arguments.
4. Additional keyword arguments:
* S (numpy.ndarray): TODO
* Q (numpy.ndarray): TODO
* v (numpy.ndarray): TODO
See Also:
* :func:`WeOptPy.algorithms.Algorithm.initPopulation`
"""
Sol, Fitness, args, d = Algorithm.init_population(self, task)
S, Q, v = np.full([self.NP, task.D],
0.0), np.full(self.NP,
0.0), np.full([self.NP, task.D], 0.0)
d.update({'S': S, 'Q': Q, 'v': v})
return Sol, Fitness, args, d
def set_parameters(self, n=10, limit=100, **ukwargs):
r"""Set the parameters of Artificial Bee Colony Algorithm.
Args:
n (int): Number of individuals in population.
limit (Optional[Union[float, numpy.ndarray[float]]]): Limit.
ukwargs (dict): Additional arguments.
See Also:
* :func:`WeOptPy.algorithms.Algorithm.setParameters`
"""
Algorithm.set_parameters(self,
n=n,
init_pop_func=default_individual_init,
itype=SolutionABC,
**ukwargs)
self.FoodNumber, self.Limit = int(self.NP / 2), limit
def get_parameters(self):
r"""Get parameters of the algorithm.
Returns:
Dict[str, Any]:
* Parameter name: Represents a parameter name
* Value of parameter: Represents the value of the parameter
"""
d = Algorithm.get_parameters(self)
d.update({'delta': self.delta, 'Neighborhood': self.Neighborhood})
return d
def set_parameters(self,
n=40,
A=0.5,
r=0.5,
Qmin=0.0,
Qmax=2.0,
**ukwargs):
r"""Set the parameters of the algorithm.
Args:
A (Optional[float]): Loudness.
r (Optional[float]): Pulse rate.
Qmin (Optional[float]): Minimum frequency.
Qmax (Optional[float]): Maximum frequency.
See Also:
* :func:`WeOptPy.algorithms.Algorithm.setParameters`
"""
Algorithm.set_parameters(self, n=n, **ukwargs)
self.A, self.r, self.Qmin, self.Qmax = A, r, Qmin, Qmax
def get_parameters(self):
r"""Get algorithm parameters values.
Returns:
Dict[str, Any]: TODO.
See Also:
* :func:`NiaPy.algorithms.algorithm.Algorithm.getParameters`
"""
d = Algorithm.get_parameters(self)
d.update({'a': self.a, 'Rmin': self.Rmin, 'Rmax': self.Rmax})
return d
def get_parameters(self):
r"""Get parameters values of the algorithm.
Returns:
Dict[str, Any]: TODO
See Also:
* :func:`WeOptPy.algorithms.interfaces.Algorithm.getParameters`
"""
d = Algorithm.get_parameters(self)
d.update({'F': self.F, 'CR': self.CR, 'CrossMutt': self.CrossMutt})
return d
def set_parameters(self,
delta=0.5,
T=2000,
deltaT=0.8,
coolingMethod=coolDelta,
epsilon=1e-23,
**ukwargs):
r"""Set the algorithm parameters/arguments.
Arguments:
delta (Optional[float]): Movement for neighbour search.
T (Optional[float]); Starting temperature.
deltaT (Optional[float]): Change in temperature.
coolingMethod (Optional[Callable]): Neighbourhood function.
epsilon (Optional[float]): Error value.
See Also
* :func:`NiaPy.algorithms.Algorithm.setParameters`
"""
ukwargs.pop('n', None)
Algorithm.set_parameters(self, n=1, **ukwargs)
self.delta, self.T, self.deltaT, self.cool, self.epsilon = delta, T, deltaT, coolingMethod, epsilon
def type_parameters():
r"""Return functions for checking values of parameters.
Returns:
Dict[str, Callable]:
* Limit (Callable[Union[float, numpy.ndarray[float]]]): TODO
See Also:
* :func:`WeOptPy.algorithms.Algorithm.typeParameters`
"""
d = Algorithm.type_parameters()
d.update({'Limit': lambda x: isinstance(x, int) and x > 0})
return d
def get_parameters(self):
r"""Get parameters of the algorithm.
Returns:
Dict[str, Any]
"""
d = Algorithm.get_parameters(self)
d.update({
'a': self.A,
'r': self.r,
'Qmin': self.Qmin,
'Qmax': self.Qmax
})
return d
def set_parameters(self,
mu=1,
k=10,
c_a=1.1,
c_r=0.5,
epsilon=1e-20,
**ukwargs):
r"""Set the arguments of an algorithm.
Args:
mu (Optional[int]): Number of parents
k (Optional[int]): Number of iterations before checking and fixing rho
c_a (Optional[float]): Search range amplification factor
c_r (Optional[float]): Search range reduction factor
See Also:
* :func:`WeOptPy.algorithms.Algorithm.setParameters`
"""
Algorithm.set_parameters(self,
n=mu,
itype=ukwargs.pop('itype', IndividualES),
**ukwargs)
self.mu, self.k, self.c_a, self.c_r, self.epsilon = mu, k, c_a, c_r, epsilon
def init_population(self, task):
r"""Initialize the individuals.
Args:
task (Task): Optimization task
Returns:
Tuple[numpy.ndarray, numpy.ndarray, list, dict]:
1. Initialized population of individuals
2. Function/fitness values for individuals
3. Additional arguments
4. Additional keyword arguments
"""
return Algorithm.init_population(self, task)
def set_parameters(self, n=43, alpha=(1, 0.83), gamma=(1.17, 0.56), theta=(0.932, 0.832), d=euclidean, dn=euclidean, nl=1, F=1.2, CR=0.25, Combination=elitism, **ukwargs): r"""Set the parameters for the algorithm. Args: n (int): Number of individuals in population. alpha (Optional[List[float]]): Factor for fickleness index function :math:`\in [0, 1]`. gamma (Optional[List[float]]): Factor for external irregularity index function :math:`\in [0, \infty)`. theta (Optional[List[float]]): Factor for internal irregularity index function :math:`\in [0, \infty)`. d (Optional[Callable[[float, float], float]]): function that takes two arguments that are function values and calcs the distance between them. dn (Optional[Callable[[numpy.ndarray, numpy.ndarray], float]]]): function that takes two arguments that are points in function landscape and calcs the distance between them. nl (Optional[float]): Normalized range for neighborhood search :math:`\in (0, 1]`. F (Optional[float]): Mutation parameter. CR (Optional[float]): Crossover parameter :math:`\in [0, 1]`. Combination (Optional[Callable[[numpy.ndarray, numpy.ndarray, numpy.ndarray, numpy.ndarray, float, float, float, float, float, float, Task, mtrand.RandomState], Tuple[numpy.ndarray, float]]]): Function for combining individuals to get new position/individual. See Also: * :func:`WeOptPy.algorithms.Algorithm.setParameters` * Combination methods: * :func:`WeOptPy.algorithms.other.Elitism` * :func:`WeOptPy.algorithms.other.Crossover` * :func:`WeOptPy.algorithms.other.Sequential` """ Algorithm.set_parameters(self, n=n, **ukwargs) self.alpha, self.gamma, self.theta, self.d, self.dn, self.nl, self.F, self.CR, self.Combination = alpha, gamma, theta, d, dn, nl, F, CR, Combination
def get_parameters(self):
r"""Get parameters of the algorithm.
Returns:
Dict[str, Any]:
* Parameter name: Represents a parameter name
* Value of parameter: Represents the value of the parameter
"""
d = Algorithm.get_parameters(self)
d.update({
'alpha': self.alpha,
'gamma': self.gamma,
'rho': self.rho,
'sigma': self.sigma
})
return d
