def obj_f_c(X):
try:
y = np.asarray([0.4655, 0., 0.])
array_type = ct.c_double * y.size
n = len(X)
for i in range(n):
if X[i] == 0:
continue
# bang-bang type switches starting with w(t) = 1.
w = (i + 1) % 2
ry = integrateF8_C(array_type(*y), w, X[i], 0.1)
y = np.array(np.fromiter(ry, dtype=np.float64, count=y.size))
freemem(ry)
val0 = np.sum(X)
penalty = np.sum(np.abs(y))
# estimated fixed weight for penalty
val = 0.1 * val0 + penalty
global f_evals
f_evals.value += 1
global best_f
if best_f.value > val:
best_f.value = val
# monitor value and constraint violation
print(
"val = {0:.8f} penalty = {1:.8f} f(xmin) = {2:.5f} nfev = {3}".
format(val0, penalty, val, f_evals.value))
return val
except Exception as e:
return 1E10 # fail
def minimize(fun,
dim=None,
bounds=None,
popsize=None,
max_evaluations=100000,
stop_fitness=None,
keep=200,
f=0.5,
cr=0.9,
rg=Generator(MT19937()),
runid=0):
"""Minimization of a scalar function of one or more variables using a
C++ Differential Evolution implementation called via ctypes.
Parameters
----------
fun : callable
The objective function to be minimized.
``fun(x, *args) -> float``
where ``x`` is an 1-D array with shape (n,) and ``args``
is a tuple of the fixed parameters needed to completely
specify the function.
dim : int
dimension of the argument of the objective function
bounds : sequence or `Bounds`, optional
Bounds on variables. There are two ways to specify the bounds:
1. Instance of the `scipy.Bounds` class.
2. Sequence of ``(min, max)`` pairs for each element in `x`. None
is used to specify no bound.
popsize : int, optional
Population size.
max_evaluations : int, optional
Forced termination after ``max_evaluations`` function evaluations.
stop_fitness : float, optional
Limit for fitness value. If reached minimize terminates.
keep = float, optional
changes the reinitialization probability of individuals based on their age. Higher value
means lower probablity of reinitialization.
f = float, optional
The mutation constant. In the literature this is also known as differential weight,
being denoted by F. Should be in the range [0, 2].
cr = float, optional
The recombination constant. Should be in the range [0, 1].
In the literature this is also known as the crossover probability.
rg = numpy.random.Generator, optional
Random generator for creating random guesses.
runid : int, optional
id used to identify the run for debugging / logging.
Returns
-------
res : scipy.OptimizeResult
The optimization result is represented as an ``OptimizeResult`` object.
Important attributes are: ``x`` the solution array,
``fun`` the best function value,
``nfev`` the number of function evaluations,
``nit`` the number of iterations,
``success`` a Boolean flag indicating if the optimizer exited successfully. """
n, lower, upper = de._check_bounds(bounds, dim)
if popsize is None:
popsize = 31
if lower is None:
lower = [0] * n
upper = [0] * n
if stop_fitness is None:
stop_fitness = math.inf
array_type = ct.c_double * n
c_callback = call_back_type(callback(fun))
seed = int(rg.uniform(0, 2**32 - 1))
try:
res = optimizeDE_C(runid, c_callback, n, seed, array_type(*lower),
array_type(*upper), max_evaluations, keep,
stop_fitness, popsize, f, cr)
x = np.array(np.fromiter(res, dtype=np.float64, count=n))
val = res[n]
evals = int(res[n + 1])
iterations = int(res[n + 2])
stop = int(res[n + 3])
freemem(res)
return OptimizeResult(x=x,
fun=val,
nfev=evals,
nit=iterations,
status=stop,
success=True)
except Exception as ex:
return OptimizeResult(x=None,
fun=sys.float_info.max,
nfev=0,
nit=0,
status=-1,
success=False)
def minimize(fun,
dim = None,
bounds = None,
popsize = None,
max_evaluations = 100000,
stop_fitness = None,
pbest = 0.7,
f0 = 0.0,
cr0 = 0.0,
rg = Generator(MT19937()),
runid=0,
workers = None):
"""Minimization of a scalar function of one or more variables using a
C++ GCL Differential Evolution implementation called via ctypes.
Parameters
----------
fun : callable
The objective function to be minimized.
``fun(x, *args) -> float``
where ``x`` is an 1-D array with shape (n,) and ``args``
is a tuple of the fixed parameters needed to completely
specify the function.
dim : int
dimension of the argument of the objective function
bounds : sequence or `Bounds`
Bounds on variables. There are two ways to specify the bounds:
1. Instance of the `scipy.Bounds` class.
2. Sequence of ``(min, max)`` pairs for each element in `x`.
popsize : int, optional
Population size.
max_evaluations : int, optional
Forced termination after ``max_evaluations`` function evaluations.
stop_fitness : float, optional
Limit for fitness value. If reached minimize terminates.
pbest = float, optional
use low value 0 < pbest <= 1 to narrow search.
f0 = float, optional
The initial mutation constant. In the literature this is also known as differential weight,
being denoted by F. Should be in the range [0, 2].
cr0 = float, optional
The initial recombination constant. Should be in the range [0, 1].
In the literature this is also known as the crossover probability.
rg = numpy.random.Generator, optional
Random generator for creating random guesses.
runid : int, optional
id used to identify the run for debugging / logging.
workers : int or None, optional
If not workers is None, function evaluation is performed in parallel for the whole population.
Useful for costly objective functions but is deactivated for parallel retry.
Returns
-------
res : scipy.OptimizeResult
The optimization result is represented as an ``OptimizeResult`` object.
Important attributes are: ``x`` the solution array,
``fun`` the best function value,
``nfev`` the number of function evaluations,
``nit`` the number of iterations,
``success`` a Boolean flag indicating if the optimizer exited successfully. """
n, lower, upper = de._check_bounds(bounds, dim)
if popsize is None:
popsize = int(n*8.5+150)
if lower is None:
lower = [0]*n
upper = [0]*n
if stop_fitness is None:
stop_fitness = math.inf
parfun = None if workers is None else parallel(fun, workers)
array_type = ct.c_double * n
c_callback_par = call_back_par(callback_par(fun, parfun))
seed = int(rg.uniform(0, 2**32 - 1))
try:
res = optimizeGCLDE_C(runid, c_callback_par, n, seed,
array_type(*lower), array_type(*upper),
max_evaluations, pbest, stop_fitness,
popsize, f0, cr0)
x = np.array(np.fromiter(res, dtype=np.float64, count=n))
val = res[n]
evals = int(res[n+1])
iterations = int(res[n+2])
stop = int(res[n+3])
freemem(res)
if not parfun is None:
parfun.stop() # stop all parallel evaluation processes
return OptimizeResult(x=x, fun=val, nfev=evals, nit=iterations, status=stop, success=True)
except Exception as ex:
if not workers is None:
fun.stop() # stop all parallel evaluation processes
return OptimizeResult(x=None, fun=sys.float_info.max, nfev=0, nit=0, status=-1, success=False)
def minimize(fun,
bounds=None,
x0=None,
input_sigma=0.166,
popsize=0,
max_evaluations=100000,
stop_fittness=None,
rg=Generator(MT19937()),
runid=0):
"""Minimization of a scalar function of one or more variables using a
C++ SCMA implementation called via ctypes.
Parameters
----------
fun : callable
The objective function to be minimized.
``fun(x, *args) -> float``
where ``x`` is an 1-D array with shape (n,) and ``args``
is a tuple of the fixed parameters needed to completely
specify the function.
bounds : sequence or `Bounds`, optional
Bounds on variables. There are two ways to specify the bounds:
1. Instance of the `scipy.Bounds` class.
2. Sequence of ``(min, max)`` pairs for each element in `x`. None
is used to specify no bound.
x0 : ndarray, shape (n,)
Initial guess. Array of real elements of size (n,),
where 'n' is the number of independent variables.
input_sigma : ndarray, shape (n,) or scalar
Initial step size for each dimension.
popsize = int, optional
CMA-ES population size.
max_evaluations : int, optional
Forced termination after ``max_evaluations`` function evaluations.
stop_fittness : float, optional
Limit for fitness value. If reached minimize terminates.
rg = numpy.random.Generator, optional
Random generator for creating random guesses.
runid : int, optional
id used to identify the run for debugging / logging.
Returns
-------
res : scipy.OptimizeResult
The optimization result is represented as an ``OptimizeResult`` object.
Important attributes are: ``x`` the solution array,
``fun`` the best function value,
``nfev`` the number of function evaluations,
``nit`` the number of CMA-ES iterations,
``status`` the stopping critera and
``success`` a Boolean flag indicating if the optimizer exited successfully. """
lower, upper, guess = _check_bounds(bounds, x0, rg)
n = guess.size
if lower is None:
lower = [0] * n
upper = [0] * n
if np.ndim(input_sigma) == 0:
input_sigma = [input_sigma] * n
if stop_fittness is None:
stop_fittness = -math.inf
array_type = ct.c_double * n
c_callback = call_back_type(callback(fun))
try:
res = optimizeCsma_C(runid, c_callback, n,
int(rg.uniform(0, 2**32 - 1)), array_type(*guess),
array_type(*lower), array_type(*upper),
array_type(*input_sigma), max_evaluations,
stop_fittness, popsize)
x = np.array(np.fromiter(res, dtype=np.float64, count=n))
val = res[n]
evals = int(res[n + 1])
iterations = int(res[n + 2])
stop = int(res[n + 3])
freemem(res)
return OptimizeResult(x=x,
fun=val,
nfev=evals,
nit=iterations,
status=stop,
success=True)
except Exception as ex:
return OptimizeResult(x=None,
fun=sys.float_info.max,
nfev=0,
nit=0,
status=-1,
success=False)
def minimize(fun,
dim,
bounds=None,
popsize=None,
max_evaluations=100000,
stop_fitness=None,
rg=Generator(MT19937()),
runid=0):
"""Minimization of a scalar function of one or more variables using a
C++ Harris hawks implementation called via ctypes.
Parameters
----------
fun : callable
The objective function to be minimized.
``fun(x, *args) -> float``
where ``x`` is an 1-D array with shape (n,) and ``args``
is a tuple of the fixed parameters needed to completely
specify the function.
dim : int
dimension of the argument of the objective function
bounds : sequence or `Bounds`, optional
Bounds on variables. There are two ways to specify the bounds:
1. Instance of the `scipy.Bounds` class.
2. Sequence of ``(min, max)`` pairs for each element in `x`. None
is used to specify no bound.
max_evaluations : int, optional
Forced termination after ``max_evaluations`` function evaluations.
stop_fitness : float, optional
Limit for fitness value. If reached minimize terminates.
rg = numpy.random.Generator, optional
Random generator for creating random guesses.
runid : int, optional
id used to identify the run for debugging / logging.
Returns
-------
res : scipy.OptimizeResult
The optimization result is represented as an ``OptimizeResult`` object.
Important attributes are: ``x`` the solution array,
``fun`` the best function value,
``nfev`` the number of function evaluations,
``nit`` the number of iterations,
``success`` a Boolean flag indicating if the optimizer exited successfully. """
lower = np.asarray(bounds.lb)
upper = np.asarray(bounds.ub)
n = dim
if popsize is None:
popsize = 31
if lower is None:
lower = [0] * n
upper = [0] * n
if stop_fitness is None:
stop_fitness = math.inf
array_type = ct.c_double * n
c_callback = call_back_type(callback(fun))
seed = int(rg.uniform(0, 2**32 - 1))
try:
res = optimizeHH_C(runid, c_callback, n, seed, array_type(*lower),
array_type(*upper), max_evaluations, stop_fitness,
popsize)
x = np.array(np.fromiter(res, dtype=np.float64, count=n))
val = res[n]
evals = int(res[n + 1])
iterations = int(res[n + 2])
stop = int(res[n + 3])
freemem(res)
return OptimizeResult(x=x,
fun=val,
nfev=evals,
nit=iterations,
status=stop,
success=True)
except Exception as ex:
return OptimizeResult(x=None,
fun=sys.float_info.max,
nfev=0,
nit=0,
status=-1,
success=False)