def get_learners(self, key, bounds, dview):
SystemInfo._validate_key(key)
self._Ebounds = bounds
def decomp(f):
def wrapper(E):
return SystemInfo.decomplexify(
f(E)) #adaptive does not work with complex matrices
return wrapper
funcs = {
'L': decomp(self.refl_L),
'N': decomp(self.smat_N),
'R': decomp(self.refl_R)
}
hashed_funcs = {k: quickle.quickle(v, dview) for k, v in funcs.items()}
return [
adaptive.Learner1D(hashed_funcs[k], bounds=bounds) for k in key
]
def setup(self):
self.learner = adaptive.Learner1D(f_1d, bounds=(-1, 1))
import json
import adaptive
from skopt import gp_minimize
from skopt.utils import dump
from openmc_model import objective
# Optimisation for 1D EXAMPLE
# Uses adaptive sampling methods from task 8 to obtain starting points for the optimiser
learner = adaptive.Learner1D(objective, bounds=(0, 100))
runner = adaptive.Runner(learner, ntasks=1, goal=lambda l: l.npoints > 7)
runner.ioloop.run_until_complete(runner.task)
# Gaussian Processes based optimisation that returns an SciPy optimisation object
res = gp_minimize(objective, # the function to minimize
[(0., 100.)], # the bounds on each dimension of x
n_calls=30, # the number of evaluations of f
n_random_starts=0, # the number of random initialization points
verbose=True,
x0=[[i] for i in list(learner.data.keys())], # initial data from the adaptive sampling method
y0=list(learner.data.values()) # initial data from the adaptive sampling method
)
# Saves the optimisation simulation reults to a file
dump(res, 'saved_optimisation_1d.dat')
def adaptive_scan(x_init,
fun=None,
fun_grad=None,
grad_lookup=None,
options={}):
"""
One dimensional scan of the function values around the initial point, using
adaptive sampling
Parameters
----------
x_init : float
Initial point
fun : callable
Goal function
fun_grad : callable
Function that computes the gradient of the goal function
grad_lookup : callable
Lookup a previously computed gradient
options : dict
Options include
accuracy_goal: float
Targeted accuracy for the sampling algorithm
probe_list : list
Points to definitely include in the sampling
init_point : boolean
Include the initial point in the sampling
"""
if "accuracy_goal" in options:
accuracy_goal = options["accuracy_goal"]
else:
accuracy_goal = 0.5
print("accuracy_goal: " + str(accuracy_goal))
probe_list = []
if "probe_list" in options:
for x in options["probe_list"]:
probe_list.append(eval(x))
if "init_point" in options:
init_point = bool(options.pop("init_point"))
if init_point:
probe_list.append(x_init)
# TODO make adaptive scan be able to do multidimensional scan
bounds = options["bounds"][0]
bound_min = bounds[0]
bound_max = bounds[1]
probe_list_min = min(probe_list)
probe_list_max = max(probe_list)
bound_min = min(bound_min, probe_list_min)
bound_max = max(bound_max, probe_list_max)
print(" ")
print("bound_min: " + str((bound_min) / (2e9 * np.pi)))
print("bound_max: " + str((bound_max) / (2e9 * np.pi)))
print(" ")
def fun1d(x):
return fun([x])
learner = adaptive.Learner1D(fun1d, bounds=(bound_min, bound_max))
if probe_list:
for x in probe_list:
print("from probe_list: " + str(x))
tmp = learner.function(x)
print("done\n")
learner.tell(x, tmp)
adaptive.runner.simple(
learner, goal=lambda learner_: learner_.loss() < accuracy_goal)
import random
import adaptive
import holoviews
import bokeh
import ipywidgets
import adaptive.notebook_integration
#from adaptive.learner.base_learner import BaseLearner
#from adaptive.notebook_integration import ensure_holoviews
#from adaptive.utils import cache_latest
adaptive.notebook_extension()
offset = random.uniform(-0.5, 0.5)
def f(x, offset=offset, wait=True):
from time import sleep
from random import random
a = 0.01
if wait:
sleep(random() / 10)
return x + a**2 / (a**2 + (x - offset)**2)
learner = adaptive.Learner1D(f, bounds=(-1, 1))
runner = adaptive.Runner(learner, goal=lambda l: l.loss() < 0.01)
runner.live_info()
runner.live_plot(update_interval=0.1)
