def plot_2d_evo(popi):
magnet_dim = len(popi.get_x()[0])
ndf, dl, dc, ndl = pg.fast_non_dominated_sorting(popi.get_f())
print(pg.sort_population_mo(popi.get_f()))
ndf_champ = []
# for j in range(2,200):
print(pg.ideal(popi.get_f())[0])
x = np.linspace(pg.ideal(popi.get_f())[0],0)
y = np.zeros(50)+(1)
for j in range(2,100):
plt.cla()
plt.plot(x,y,linestyle="dashed",color="red")
print(ndf[0])
ndf_champ.append([popi.get_f()[i] for i in ndf[j]])
# ax = pg.plot_non_dominated_fronts(ndf_champ[0],comp=[0,j])
# ax.plot(color="C{}".format(j))
ax = pg.plot_non_dominated_fronts(popi.get_f()[0:j])
ax.set_xlabel('resolution')
ax.set_ylabel('xangle_e_min')
ax.set_ylim(1e-3,1000)
ax.set_yscale('log')
# print(ndf_champ, ndf[0])
# print(ndf)
plt.savefig("popi{}".format(j))
return
def findMinAndMaxPoints(objectivesList):
'''Returns the min and max points for a list of sets of objectives'''
minPoint = pg.ideal(objectivesList)
maxPoint = pg.nadir(objectivesList)
print(f"MinPoint {minPoint}")
print(f"MaxPoint {maxPoint}\n")
return minPoint, maxPoint
print('Running: ', filenameNPZ[:-4])
# algorithm
algo = po.algorithm(po.nsga2(gen=generations))
algo.set_verbosity(1)
# problem
prob = po.problem(myUDP.KAOnodesMultiObj())
# population
pop = po.population(prob=prob, size=sizePop)
# evolution
start = time.time()
popE = algo.evolve(pop)
print('time evolution: ', time.time() - start)
# save TXT fie with general description of the optimization
bestFstr = 'ideal found fit: ' + str(po.ideal(
popE.get_f())) + '; best fit possible: -1'
#bestChamp = 'champion decission vector'
#bestXstr = 'velocity: ' + str(popE.champion_x[0]) + ', kL:' + str(popE.champion_x[1]),', kG: ' + str(popE.champion_x[2])
popStr = popE.__str__()
algoStr = algo.__str__()
localtime = time.localtime(time.time())
dateStr = str(localtime)
with open(pathsave + filenameTXT, "w") as text_file:
print(dateStr, end='\n\n', file=text_file)
print(bestFstr, end='\n', file=text_file)
#print(bestChamp, end='\n', file=text_file)
#print(bestXstr, end='\n\n', file=text_file)
print(algoStr, end='\n', file=text_file)
print(popStr, end='\n', file=text_file)
# Get logs from the algorithm
def plot_2d(popi,filename):
magnet_dim = len(popi.get_x()[0])
hv = pg.hypervolume(popi)
ref_point = hv.refpoint()
best_point = (popi.get_f()[hv.greatest_contributor(ref_point)])
ndf, dl, dc, ndl = pg.fast_non_dominated_sorting(popi.get_f())
# print(pg.sort_population_mo(popi.get_f()))
ndf_champ = []
# for j in range(2,200):
# print(pg.select_best_N_mo(popi.get_f(),10))
best_10 = (pg.select_best_N_mo(popi.get_f(),10))
for i in best_10:
print(i, np.power(np.zeros(magnet_dim)+2,popi.get_x()[i]), popi.get_f()[i])
x = np.linspace(pg.ideal(popi.get_f())[0],0)
y = np.zeros(50)+(1)
plot_x, plot_y = 0,0
objs = len(popi.get_f()[0])
fig, axs = plt.subplots(objs-1,sharex=True)
fig.suptitle('ratios to Nom vs Resolution')
log_res, log_x = [], []
for i in ndf[0]:
log_res.append(np.log(popi.get_f()[i][0])/np.log(10))
log_x.append(np.log(popi.get_f()[i][1])/np.log(10))
if max(popi.get_f()[i]) < 1000000:
print(i, np.power(np.zeros(magnet_dim)+2,popi.get_x()[i]), popi.get_f()[i])
if objs == 2:
j = 1
axs.set_xlabel('resolution')
axs.axvline(x=fNom[0],linestyle="dashed",color="red")
axs.axvline(x=best_point[0],linestyle="dotted",color="blue")
axs.axhline(y=1.0,linestyle="dashed",color="red")
ndf_champ.append([popi.get_f()[i] for i in ndf[0]])
pg.plot_non_dominated_fronts(ndf_champ[0],comp=[0,j],axes=axs)
# ax.plot df = (color="C{}".format(j))
# ax = pg.plot_non_dominated_fronts(popi.get_f()[0:j])
axs.set_ylabel(fNames[2])
# axs.set_ylim(0.9,1.1)
axs.set_yscale('log')
# axs.set_xlim(0.8,1.2)
axs.set_xscale('log')
else:
axs[objs-2].set_xlabel('resolution')
for j in range(1,2):
# axs[plot_y].plot(x,y,linestyle="dashed",color="red")
axs[plot_y].axvline(x=fNom[0],linestyle="dashed",color="red")
axs[plot_y].axvline(x=best_point[0],linestyle="dotted",color="blue")
axs[plot_y].axhline(y=1.0,linestyle="dashed",color="red")
ndf_champ.append([popi.get_f()[i] for i in ndf[0]])
pg.plot_non_dominated_fronts(ndf_champ[0],comp=[0,j],axes=axs[plot_y])
# ax.plot(color="C{}".format(j))
# ax = pg.plot_non_dominated_fronts(popi.get_f()[0:j])
axs[plot_y].set_ylabel(fNames[2])
# axs[plot_y].set_ylim(1e-1,1e1)
axs[plot_y].set_yscale('log')
# axs[plot_y].set_xlim(0.1,10.0)
# axs[plot_y].set_xscale('log')
plot_y += 1
# print(ndf_champ, ndf[0])
# print(ndf)
fig.tight_layout()
fig.savefig(filename+"_ndf.png")
plt.clf()
# plt.plot(log_res, log_x,"o", linestyle="none", )
# fig.savefig(filename+"_logndf.png")
return
def plot_4d(popi, filename):
magnet_dim = len(popi.get_x()[0])
hv = pg.hypervolume(popi)
# ref_point = hv.refpoint()
ref_point = (1e10, 1e10, 1e10, 1e10)
best_point = (popi.get_f()[hv.greatest_contributor(ref_point)])
ndf, dl, dc, ndl = pg.fast_non_dominated_sorting(popi.get_f())
# print(pg.sort_population_mo(popi.get_f()))
ndf_champ = []
# for j in range(2,200):
# print(pg.select_best_N_mo(popi.get_f(),10))
best_10 = (pg.select_best_N_mo(popi.get_f(), 10))
# for i in best_10:
# print(i, np.power(np.zeros(magnet_dim)+2,popi.get_x()[i]), popi.get_f()[i])
x = np.linspace(pg.ideal(popi.get_f())[0], 0)
y = np.zeros(50) + (1)
plot_x, plot_y = 0, 0
fig, axs = plt.subplots(3, sharex=True)
fig.suptitle('Pareto Fronts of each parameter vs. BeamSpotSize at FP4')
axs[optimized_params - 2].set_xlabel(fNames[3])
# for i in ndf[0]:
# if max(popi.get_f()[i]) < 10:
# print(i, np.power(np.zeros(magnet_dim)+2,popi.get_x()[i]), popi.get_f()[i])
reduced_ndf = []
first = True
check_val = 1e9
for j in range(0, 3):
# axs[plot_y].plot(x,y,linestyle="dashed",color="red")
axs[plot_y].axvline(x=fNom[0], linestyle="dashed", color="red")
# axs[plot_y].axvline(x=best_point[0],linestyle="dotted",color="blue")
axs[plot_y].axhline(y=1.0, linestyle="dashed", color="red")
for i in ndf[0]:
if np.all(np.array(popi.get_f()[i]) < check_val) == True:
# if np.all(np.array(popi.get_f()[i]) < 1) == True and first:
ndf_champ.append(popi.get_f()[i])
reduced_ndf.append(i)
first = False
try:
pg.plot_non_dominated_fronts(ndf_champ,
comp=[3, j],
axes=axs[plot_y])
if j == 1:
print(filename[-6:-4], len(ndf_champ))
except:
print(filename[-6:-4], "no better than nominal solutions")
return
# ax.plot(color="C{}".format(j))
# ax = pg.plot_non_dominated_fronts(popi.get_f()[0:j])
axs[plot_y].set_ylabel(fNames[j])
# axs[plot_y].set_ylim(1e-1,1e1)
axs[plot_y].set_yscale('log')
# axs[plot_y].set_xlim(0.1,10.0)
axs[plot_y].set_xscale('log')
plot_y += 1
# print(ndf_champ, ndf[0])
# print(ndf)
fig.tight_layout()
fig.savefig(filename + "_ndf.png")
plt.cla()
fig2, axs2 = plt.subplots(3, 4)
plot_x, plot_y = 0, 0
reduced_qs = np.array(popi.get_x())[reduced_ndf]
# print(reduced_qs)
df = pd.DataFrame(reduced_qs,
columns=[
'y0', 'y1', 'y2', 'y3', 'y4', 'y5', 'y6', 'y7', 'y8',
'y9', 'y10'
])
qNom = np.zeros(magnet_dim)
for i in range(magnet_dim):
if plot_x > 3:
plot_x, plot_y = 0, plot_y + 1
axs2[plot_y, plot_x] = df['y{0}'.format(i)].plot.hist(ax=axs2[plot_y,
plot_x],
bins=20,
range=(-1, 1))
axs2[plot_y, plot_x].axvline(x=qNom[i],
ymin=0,
ymax=20,
color='red',
linestyle='dashed')
# axs[plot_y,plot_x].axvline( x = max_y[i], ymin=0,ymax=20,color='green',linestyle='dashed')
axs2[plot_y, plot_x].axes.yaxis.set_visible(False)
axs2[plot_y, plot_x].axes.set_xlim(-1, 1)
axs2[plot_y, plot_x].set_title("q{0}".format(i + 1))
plot_x += 1
fig2.delaxes(axs2[plot_y, plot_x])
fig2.tight_layout()
plt.savefig(filename + ".png")
return
