/usr/lib/python2.7/dist-packages/deap/tools/emo.py is in python-deap 1.0.2.post2-5.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 | from __future__ import division
import bisect
import math
import random
from itertools import chain
from operator import attrgetter, itemgetter
from collections import defaultdict
######################################
# Non-Dominated Sorting (NSGA-II) #
######################################
def selNSGA2(individuals, k):
"""Apply NSGA-II selection operator on the *individuals*. Usually, the
size of *individuals* will be larger than *k* because any individual
present in *individuals* will appear in the returned list at most once.
Having the size of *individuals* equals to *k* will have no effect other
than sorting the population according to their front rank. The
list returned contains references to the input *individuals*. For more
details on the NSGA-II operator see [Deb2002]_.
:param individuals: A list of individuals to select from.
:param k: The number of individuals to select.
:returns: A list of selected individuals.
.. [Deb2002] Deb, Pratab, Agarwal, and Meyarivan, "A fast elitist
non-dominated sorting genetic algorithm for multi-objective
optimization: NSGA-II", 2002.
"""
pareto_fronts = sortNondominated(individuals, k)
for front in pareto_fronts:
assignCrowdingDist(front)
chosen = list(chain(*pareto_fronts[:-1]))
k = k - len(chosen)
if k > 0:
sorted_front = sorted(pareto_fronts[-1], key=attrgetter("fitness.crowding_dist"), reverse=True)
chosen.extend(sorted_front[:k])
return chosen
def sortNondominated(individuals, k, first_front_only=False):
"""Sort the first *k* *individuals* into different nondomination levels
using the "Fast Nondominated Sorting Approach" proposed by Deb et al.,
see [Deb2002]_. This algorithm has a time complexity of :math:`O(MN^2)`,
where :math:`M` is the number of objectives and :math:`N` the number of
individuals.
:param individuals: A list of individuals to select from.
:param k: The number of individuals to select.
:param first_front_only: If :obj:`True` sort only the first front and
exit.
:returns: A list of Pareto fronts (lists), the first list includes
nondominated individuals.
.. [Deb2002] Deb, Pratab, Agarwal, and Meyarivan, "A fast elitist
non-dominated sorting genetic algorithm for multi-objective
optimization: NSGA-II", 2002.
"""
if k == 0:
return []
map_fit_ind = defaultdict(list)
for ind in individuals:
map_fit_ind[ind.fitness].append(ind)
fits = map_fit_ind.keys()
current_front = []
next_front = []
dominating_fits = defaultdict(int)
dominated_fits = defaultdict(list)
# Rank first Pareto front
for i, fit_i in enumerate(fits):
for fit_j in fits[i+1:]:
if fit_i.dominates(fit_j):
dominating_fits[fit_j] += 1
dominated_fits[fit_i].append(fit_j)
elif fit_j.dominates(fit_i):
dominating_fits[fit_i] += 1
dominated_fits[fit_j].append(fit_i)
if dominating_fits[fit_i] == 0:
current_front.append(fit_i)
fronts = [[]]
for fit in current_front:
fronts[-1].extend(map_fit_ind[fit])
pareto_sorted = len(fronts[-1])
# Rank the next front until all individuals are sorted or
# the given number of individual are sorted.
if not first_front_only:
N = min(len(individuals), k)
while pareto_sorted < N:
fronts.append([])
for fit_p in current_front:
for fit_d in dominated_fits[fit_p]:
dominating_fits[fit_d] -= 1
if dominating_fits[fit_d] == 0:
next_front.append(fit_d)
pareto_sorted += len(map_fit_ind[fit_d])
fronts[-1].extend(map_fit_ind[fit_d])
current_front = next_front
next_front = []
return fronts
def assignCrowdingDist(individuals):
"""Assign a crowding distance to each individual's fitness. The
crowding distance can be retrieve via the :attr:`crowding_dist`
attribute of each individual's fitness.
"""
if len(individuals) == 0:
return
distances = [0.0] * len(individuals)
crowd = [(ind.fitness.values, i) for i, ind in enumerate(individuals)]
nobj = len(individuals[0].fitness.values)
for i in xrange(nobj):
crowd.sort(key=lambda element: element[0][i])
distances[crowd[0][1]] = float("inf")
distances[crowd[-1][1]] = float("inf")
if crowd[-1][0][i] == crowd[0][0][i]:
continue
norm = nobj * float(crowd[-1][0][i] - crowd[0][0][i])
for prev, cur, next in zip(crowd[:-2], crowd[1:-1], crowd[2:]):
distances[cur[1]] += (next[0][i] - prev[0][i]) / norm
for i, dist in enumerate(distances):
individuals[i].fitness.crowding_dist = dist
def selTournamentDCD(individuals, k):
"""Tournament selection based on dominance (D) between two individuals, if
the two individuals do not interdominate the selection is made
based on crowding distance (CD). The *individuals* sequence length has to
be a multiple of 4. Starting from the beginning of the selected
individuals, two consecutive individuals will be different (assuming all
individuals in the input list are unique). Each individual from the input
list won't be selected more than twice.
This selection requires the individuals to have a :attr:`crowding_dist`
attribute, which can be set by the :func:`assignCrowdingDist` function.
:param individuals: A list of individuals to select from.
:param k: The number of individuals to select.
:returns: A list of selected individuals.
"""
def tourn(ind1, ind2):
if ind1.fitness.dominates(ind2.fitness):
return ind1
elif ind2.fitness.dominates(ind1.fitness):
return ind2
if ind1.fitness.crowding_dist < ind2.fitness.crowding_dist:
return ind2
elif ind1.fitness.crowding_dist > ind2.fitness.crowding_dist:
return ind1
if random.random() <= 0.5:
return ind1
return ind2
individuals_1 = random.sample(individuals, len(individuals))
individuals_2 = random.sample(individuals, len(individuals))
chosen = []
for i in xrange(0, k, 4):
chosen.append(tourn(individuals_1[i], individuals_1[i+1]))
chosen.append(tourn(individuals_1[i+2], individuals_1[i+3]))
chosen.append(tourn(individuals_2[i], individuals_2[i+1]))
chosen.append(tourn(individuals_2[i+2], individuals_2[i+3]))
return chosen
#######################################
# Generalized Reduced runtime ND sort #
#######################################
def identity(obj):
"""Returns directly the argument *obj*.
"""
return obj
def isDominated(wvalues1, wvalues2):
"""Returns whether or not *wvalues1* dominates *wvalues2*.
:param wvalues1: The weighted fitness values that would be dominated.
:param wvalues2: The weighted fitness values of the dominant.
:returns: :obj:`True` if wvalues2 dominates wvalues1, :obj:`False`
otherwise.
"""
not_equal = False
for self_wvalue, other_wvalue in zip(wvalues1, wvalues2):
if self_wvalue > other_wvalue:
return False
elif self_wvalue < other_wvalue:
not_equal = True
return not_equal
def median(seq, key=identity):
"""Returns the median of *seq* - the numeric value separating the higher
half of a sample from the lower half. If there is an even number of
elements in *seq*, it returns the mean of the two middle values.
"""
sseq = sorted(seq, key=key)
length = len(seq)
if length % 2 == 1:
return key(sseq[(length - 1) // 2])
else:
return (key(sseq[(length - 1) // 2]) + key(sseq[length // 2])) / 2.0
def sortLogNondominated(individuals, k, first_front_only=False):
"""Sort *individuals* in pareto non-dominated fronts using the Generalized
Reduced Run-Time Complexity Non-Dominated Sorting Algorithm presented by
Fortin et al. (2013).
:param individuals: A list of individuals to select from.
:returns: A list of Pareto fronts (lists), with the first list being the
true Pareto front.
"""
if k == 0:
return []
#Separate individuals according to unique fitnesses
unique_fits = defaultdict(list)
for i, ind in enumerate(individuals):
unique_fits[ind.fitness.wvalues].append(ind)
#Launch the sorting algorithm
obj = len(individuals[0].fitness.wvalues)-1
fitnesses = unique_fits.keys()
front = dict.fromkeys(fitnesses, 0)
# Sort the fitnesses lexicographically.
fitnesses.sort(reverse=True)
sortNDHelperA(fitnesses, obj, front)
#Extract individuals from front list here
nbfronts = max(front.values())+1
pareto_fronts = [[] for i in range(nbfronts)]
for fit in fitnesses:
index = front[fit]
pareto_fronts[index].extend(unique_fits[fit])
# Keep only the fronts required to have k individuals.
if not first_front_only:
count = 0
for i, front in enumerate(pareto_fronts):
count += len(front)
if count >= k:
return pareto_fronts[:i+1]
return pareto_fronts
else:
return pareto_fronts[0]
def sortNDHelperA(fitnesses, obj, front):
"""Create a non-dominated sorting of S on the first M objectives"""
if len(fitnesses) < 2:
return
elif len(fitnesses) == 2:
# Only two individuals, compare them and adjust front number
s1, s2 = fitnesses[0], fitnesses[1]
if isDominated(s2[:obj+1], s1[:obj+1]):
front[s2] = max(front[s2], front[s1] + 1)
elif obj == 1:
sweepA(fitnesses, front)
elif len(frozenset(map(itemgetter(obj), fitnesses))) == 1:
#All individuals for objective M are equal: go to objective M-1
sortNDHelperA(fitnesses, obj-1, front)
else:
# More than two individuals, split list and then apply recursion
best, worst = splitA(fitnesses, obj)
sortNDHelperA(best, obj, front)
sortNDHelperB(best, worst, obj-1, front)
sortNDHelperA(worst, obj, front)
def splitA(fitnesses, obj):
"""Partition the set of fitnesses in two according to the median of
the objective index *obj*. The values equal to the median are put in
the set containing the least elements.
"""
median_ = median(fitnesses, itemgetter(obj))
best_a, worst_a = [], []
best_b, worst_b = [], []
for fit in fitnesses:
if fit[obj] > median_:
best_a.append(fit)
best_b.append(fit)
elif fit[obj] < median_:
worst_a.append(fit)
worst_b.append(fit)
else:
best_a.append(fit)
worst_b.append(fit)
balance_a = abs(len(best_a) - len(worst_a))
balance_b = abs(len(best_b) - len(worst_b))
if balance_a <= balance_b:
return best_a, worst_a
else:
return best_b, worst_b
def sweepA(fitnesses, front):
"""Update rank number associated to the fitnesses according
to the first two objectives using a geometric sweep procedure.
"""
stairs = [-fitnesses[0][1]]
fstairs = [fitnesses[0]]
for fit in fitnesses[1:]:
idx = bisect.bisect_right(stairs, -fit[1])
if 0 < idx <= len(stairs):
fstair = max(fstairs[:idx], key=front.__getitem__)
front[fit] = max(front[fit], front[fstair]+1)
for i, fstair in enumerate(fstairs[idx:], idx):
if front[fstair] == front[fit]:
del stairs[i]
del fstairs[i]
break
stairs.insert(idx, -fit[1])
fstairs.insert(idx, fit)
def sortNDHelperB(best, worst, obj, front):
"""Assign front numbers to the solutions in H according to the solutions
in L. The solutions in L are assumed to have correct front numbers and the
solutions in H are not compared with each other, as this is supposed to
happen after sortNDHelperB is called."""
key = itemgetter(obj)
if len(worst) == 0 or len(best) == 0:
#One of the lists is empty: nothing to do
return
elif len(best) == 1 or len(worst) == 1:
#One of the lists has one individual: compare directly
for hi in worst:
for li in best:
if isDominated(hi[:obj+1], li[:obj+1]) or hi[:obj+1] == li[:obj+1]:
front[hi] = max(front[hi], front[li] + 1)
elif obj == 1:
sweepB(best, worst, front)
elif key(min(best, key=key)) >= key(max(worst, key=key)):
#All individuals from L dominate H for objective M:
#Also supports the case where every individuals in L and H
#has the same value for the current objective
#Skip to objective M-1
sortNDHelperB(best, worst, obj-1, front)
elif key(max(best, key=key)) >= key(min(worst, key=key)):
best1, best2, worst1, worst2 = splitB(best, worst, obj)
sortNDHelperB(best1, worst1, obj, front)
sortNDHelperB(best1, worst2, obj-1, front)
sortNDHelperB(best2, worst2, obj, front)
def splitB(best, worst, obj):
"""Split both best individual and worst sets of fitnesses according
to the median of objective *obj* computed on the set containing the
most elements. The values equal to the median are attributed so as
to balance the four resulting sets as much as possible.
"""
median_ = median(best if len(best) > len(worst) else worst, itemgetter(obj))
best1_a, best2_a, best1_b, best2_b = [], [], [], []
for fit in best:
if fit[obj] > median_:
best1_a.append(fit)
best1_b.append(fit)
elif fit[obj] < median_:
best2_a.append(fit)
best2_b.append(fit)
else:
best1_a.append(fit)
best2_b.append(fit)
worst1_a, worst2_a, worst1_b, worst2_b = [], [], [], []
for fit in worst:
if fit[obj] > median_:
worst1_a.append(fit)
worst1_b.append(fit)
elif fit[obj] < median_:
worst2_a.append(fit)
worst2_b.append(fit)
else:
worst1_a.append(fit)
worst2_b.append(fit)
balance_a = abs(len(best1_a) - len(best2_a) + len(worst1_a) - len(worst2_a))
balance_b = abs(len(best1_b) - len(best2_b) + len(worst1_b) - len(worst2_b))
if balance_a <= balance_b:
return best1_a, best2_a, worst1_a, worst2_a
else:
return best1_b, best2_b, worst1_b, worst2_b
def sweepB(best, worst, front):
"""Adjust the rank number of the worst fitnesses according to
the best fitnesses on the first two objectives using a sweep
procedure.
"""
stairs, fstairs = [], []
iter_best = iter(best)
next_best = next(iter_best, False)
for h in worst:
while next_best and h[:2] <= next_best[:2]:
insert = True
for i, fstair in enumerate(fstairs):
if front[fstair] == front[next_best]:
if fstair[1] > next_best[1]:
insert = False
else:
del stairs[i], fstairs[i]
break
if insert:
idx = bisect.bisect_right(stairs, -next_best[1])
stairs.insert(idx, -next_best[1])
fstairs.insert(idx, next_best)
next_best = next(iter_best, False)
idx = bisect.bisect_right(stairs, -h[1])
if 0 < idx <= len(stairs):
fstair = max(fstairs[:idx], key=front.__getitem__)
front[h] = max(front[h], front[fstair]+1)
######################################
# Strength Pareto (SPEA-II) #
######################################
def selSPEA2(individuals, k):
"""Apply SPEA-II selection operator on the *individuals*. Usually, the
size of *individuals* will be larger than *n* because any individual
present in *individuals* will appear in the returned list at most once.
Having the size of *individuals* equals to *n* will have no effect other
than sorting the population according to a strength Pareto scheme. The
list returned contains references to the input *individuals*. For more
details on the SPEA-II operator see [Zitzler2001]_.
:param individuals: A list of individuals to select from.
:param k: The number of individuals to select.
:returns: A list of selected individuals.
.. [Zitzler2001] Zitzler, Laumanns and Thiele, "SPEA 2: Improving the
strength Pareto evolutionary algorithm", 2001.
"""
N = len(individuals)
L = len(individuals[0].fitness.values)
K = math.sqrt(N)
strength_fits = [0] * N
fits = [0] * N
dominating_inds = [list() for i in xrange(N)]
for i, ind_i in enumerate(individuals):
for j, ind_j in enumerate(individuals[i+1:], i+1):
if ind_i.fitness.dominates(ind_j.fitness):
strength_fits[i] += 1
dominating_inds[j].append(i)
elif ind_j.fitness.dominates(ind_i.fitness):
strength_fits[j] += 1
dominating_inds[i].append(j)
for i in xrange(N):
for j in dominating_inds[i]:
fits[i] += strength_fits[j]
# Choose all non-dominated individuals
chosen_indices = [i for i in xrange(N) if fits[i] < 1]
if len(chosen_indices) < k: # The archive is too small
for i in xrange(N):
distances = [0.0] * N
for j in xrange(i + 1, N):
dist = 0.0
for l in xrange(L):
val = individuals[i].fitness.values[l] - \
individuals[j].fitness.values[l]
dist += val * val
distances[j] = dist
kth_dist = _randomizedSelect(distances, 0, N - 1, K)
density = 1.0 / (kth_dist + 2.0)
fits[i] += density
next_indices = [(fits[i], i) for i in xrange(N)
if not i in chosen_indices]
next_indices.sort()
#print next_indices
chosen_indices += [i for _, i in next_indices[:k - len(chosen_indices)]]
elif len(chosen_indices) > k: # The archive is too large
N = len(chosen_indices)
distances = [[0.0] * N for i in xrange(N)]
sorted_indices = [[0] * N for i in xrange(N)]
for i in xrange(N):
for j in xrange(i + 1, N):
dist = 0.0
for l in xrange(L):
val = individuals[chosen_indices[i]].fitness.values[l] - \
individuals[chosen_indices[j]].fitness.values[l]
dist += val * val
distances[i][j] = dist
distances[j][i] = dist
distances[i][i] = -1
# Insert sort is faster than quick sort for short arrays
for i in xrange(N):
for j in xrange(1, N):
l = j
while l > 0 and distances[i][j] < distances[i][sorted_indices[i][l - 1]]:
sorted_indices[i][l] = sorted_indices[i][l - 1]
l -= 1
sorted_indices[i][l] = j
size = N
to_remove = []
while size > k:
# Search for minimal distance
min_pos = 0
for i in xrange(1, N):
for j in xrange(1, size):
dist_i_sorted_j = distances[i][sorted_indices[i][j]]
dist_min_sorted_j = distances[min_pos][sorted_indices[min_pos][j]]
if dist_i_sorted_j < dist_min_sorted_j:
min_pos = i
break
elif dist_i_sorted_j > dist_min_sorted_j:
break
# Remove minimal distance from sorted_indices
for i in xrange(N):
distances[i][min_pos] = float("inf")
distances[min_pos][i] = float("inf")
for j in xrange(1, size - 1):
if sorted_indices[i][j] == min_pos:
sorted_indices[i][j] = sorted_indices[i][j + 1]
sorted_indices[i][j + 1] = min_pos
# Remove corresponding individual from chosen_indices
to_remove.append(min_pos)
size -= 1
for index in reversed(sorted(to_remove)):
del chosen_indices[index]
return [individuals[i] for i in chosen_indices]
def _randomizedSelect(array, begin, end, i):
"""Allows to select the ith smallest element from array without sorting it.
Runtime is expected to be O(n).
"""
if begin == end:
return array[begin]
q = _randomizedPartition(array, begin, end)
k = q - begin + 1
if i < k:
return _randomizedSelect(array, begin, q, i)
else:
return _randomizedSelect(array, q + 1, end, i - k)
def _randomizedPartition(array, begin, end):
i = random.randint(begin, end)
array[begin], array[i] = array[i], array[begin]
return _partition(array, begin, end)
def _partition(array, begin, end):
x = array[begin]
i = begin - 1
j = end + 1
while True:
j -= 1
while array[j] > x:
j -= 1
i += 1
while array[i] < x:
i += 1
if i < j:
array[i], array[j] = array[j], array[i]
else:
return j
__all__ = ['selNSGA2', 'selSPEA2', 'sortNondominated', 'sortLogNondominated',
'selTournamentDCD']
|