def __search(sync_net, ini, fin, cost_function, skip, ret_tuple_as_trans_desc=False,
max_align_time_trace=sys.maxsize):
start_time = time.time()
decorate_transitions_prepostset(sync_net)
decorate_places_preset_trans(sync_net)
closed = set()
ini_state = utils.DijkstraSearchTuple(0, ini, None, None, 0)
open_set = [ini_state]
heapq.heapify(open_set)
visited = 0
queued = 0
traversed = 0
trans_empty_preset = set(t for t in sync_net.transitions if len(t.in_arcs) == 0)
while not len(open_set) == 0:
if (time.time() - start_time) > max_align_time_trace:
return None
curr = heapq.heappop(open_set)
current_marking = curr.m
already_closed = current_marking in closed
if already_closed:
continue
if current_marking == fin:
# from pympler.asizeof import asizeof
# from pm4py.util import measurements
# measurements.Measurements.ALIGN_TIME.append(asizeof(open_set))
return utils.__reconstruct_alignment(curr, visited, queued, traversed,
ret_tuple_as_trans_desc=ret_tuple_as_trans_desc)
closed.add(current_marking)
visited += 1
enabled_trans = copy(trans_empty_preset)
for p in current_marking:
for t in p.ass_trans:
if t.sub_marking <= current_marking:
enabled_trans.add(t)
trans_to_visit_with_cost = [(t, cost_function[t]) for t in enabled_trans if not (
t is not None and utils.__is_log_move(t, skip) and utils.__is_model_move(t, skip))]
for t, cost in trans_to_visit_with_cost:
traversed += 1
new_marking = utils.add_markings(current_marking, t.add_marking)
if new_marking in closed:
continue
queued += 1
tp = utils.DijkstraSearchTuple(curr.g + cost, new_marking, curr, t, curr.l + 1)
heapq.heappush(open_set, tp)
def __search_without_synchr(net,
ini,
fin,
log_trace,
skip=utils.SKIP,
ret_tuple_as_trans_desc=True,
max_align_time_trace=sys.maxsize,
expo=2):
'''
In this function that can be called with the following way:
alignment.algorithm.apply(trace, net, marking, fmarking,variant=ali.VERSION_DIJKSTRA_EXPONENTIAL_HEURISTIC,
parameters={ali.Parameters.SYNCHRONOUS:False})
we compute the distance at each marking. However there is a question:
Should we keep the entire trace or cut it?
Notice that the heuristic on marking reachability is ON
'''
trace = [log_trace[i]["concept:name"] for i in range(len(log_trace))]
start_time = time.time()
decorate_transitions_prepostset(net)
decorate_places_preset_trans(net)
closed = {}
# a node in this version contains the marking state.m[Ø] and the position in the trace state.m[1]
ini_state = utils.DijkstraSearchTuple(0, (ini, 0), None, None, 0)
open_set = [ini_state]
heapq.heapify(open_set)
visited = 0
queued = 0
traversed = 0
def cost_function(t, l, expo):
if t == utils.SKIP:
return expo**(-l)
else:
return 0
trans_empty_preset = set(t for t in net.transitions if len(t.in_arcs) == 0)
while not len(open_set) == 0:
if (time.time() - start_time) > max_align_time_trace:
return None
curr = heapq.heappop(open_set)
current_marking = curr.m
already_closed = current_marking in closed.keys()
if already_closed:
# if marking has already been visited, we don't visit it again
# it's a heuristic
continue
if current_marking[0] == fin and current_marking[1] == len(trace):
return utils.__reconstruct_alignment(
curr,
visited,
queued,
traversed,
ret_tuple_as_trans_desc=ret_tuple_as_trans_desc)
closed[current_marking] = curr.l
visited += 1
# ----- either we try to move in model
possible_enabling_transitions = copy(trans_empty_preset)
for p in current_marking[0]:
for t in p.ass_trans:
possible_enabling_transitions.add(t)
enabled_trans = [
t for t in possible_enabling_transitions
if t.sub_marking <= current_marking[0]
]
trans_to_visit_with_cost = [(t, cost_function(utils.SKIP, curr.l,
expo))
for t in enabled_trans if t is not None]
for t, cost in trans_to_visit_with_cost:
traversed += 1
new_marking = (utils.add_markings(current_marking[0],
t.add_marking),
current_marking[1])
if new_marking in closed.keys():
# if marking has already been visited, we don't visit it again
# it's a heuristic
continue
queued += 1
tp = utils.DijkstraSearchTuple(curr.g + cost, new_marking, curr,
(">>", t), curr.l + 1)
heapq.heappush(open_set, tp)
# ------ either we try to move in log
if current_marking[1] < len(trace):
traversed += 1
new_marking = (current_marking[0], current_marking[1] + 1)
if new_marking in closed.keys():
# if marking has already been visited, we don't visit it again
# it's a heuristic
continue
queued += 1
tp = utils.DijkstraSearchTuple(
curr.g + cost_function(utils.SKIP, curr.l, expo), new_marking,
curr, (trace[current_marking[1]], ">>"), curr.l + 1)
heapq.heappush(open_set, tp)
# ------ either we try to move in both (synchronous moves)
trans_to_visit_with_cost = [
(t, cost_function(t, curr.l, expo)) for t in enabled_trans
if t is not None and str(t) == trace[current_marking[1]]
]
for t, cost in trans_to_visit_with_cost:
traversed += 1
new_marking = (utils.add_markings(current_marking[0],
t.add_marking),
current_marking[1] + 1)
if new_marking in closed.keys():
# if marking has already been visited, we don't visit it again
# it's a heuristic
continue
queued += 1
tp = utils.DijkstraSearchTuple(curr.g + cost, new_marking,
curr,
(trace[current_marking[1]], t),
curr.l + 1)
heapq.heappush(open_set, tp)
def __search(sync_net, ini, fin, cost_function, skip, ret_tuple_as_trans_desc=False,
max_align_time_trace=sys.maxsize):
start_time = time.time()
decorate_transitions_prepostset(sync_net)
decorate_places_preset_trans(sync_net)
incidence_matrix = inc_mat_construct(sync_net)
ini_vec, fin_vec, cost_vec = utils.__vectorize_initial_final_cost(incidence_matrix, ini, fin, cost_function)
closed = set()
a_matrix = np.asmatrix(incidence_matrix.a_matrix).astype(np.float64)
g_matrix = -np.eye(len(sync_net.transitions))
h_cvx = np.matrix(np.zeros(len(sync_net.transitions))).transpose()
cost_vec = [x * 1.0 for x in cost_vec]
use_cvxopt = False
if lp_solver.DEFAULT_LP_SOLVER_VARIANT == lp_solver.CVXOPT_SOLVER_CUSTOM_ALIGN or lp_solver.DEFAULT_LP_SOLVER_VARIANT == lp_solver.CVXOPT_SOLVER_CUSTOM_ALIGN_ILP:
use_cvxopt = True
if use_cvxopt:
# not available in the latest version of PM4Py
from cvxopt import matrix
a_matrix = matrix(a_matrix)
g_matrix = matrix(g_matrix)
h_cvx = matrix(h_cvx)
cost_vec = matrix(cost_vec)
h, x = utils.__compute_exact_heuristic_new_version(sync_net, a_matrix, h_cvx, g_matrix, cost_vec, incidence_matrix,
ini,
fin_vec, lp_solver.DEFAULT_LP_SOLVER_VARIANT,
use_cvxopt=use_cvxopt)
ini_state = utils.SearchTuple(0 + h, 0, h, ini, None, None, x, True)
open_set = [ini_state]
heapq.heapify(open_set)
visited = 0
queued = 0
traversed = 0
lp_solved = 1
trans_empty_preset = set(t for t in sync_net.transitions if len(t.in_arcs) == 0)
while not len(open_set) == 0:
if (time.time() - start_time) > max_align_time_trace:
return None
curr = heapq.heappop(open_set)
current_marking = curr.m
while not curr.trust:
if (time.time() - start_time) > max_align_time_trace:
return None
already_closed = current_marking in closed
if already_closed:
curr = heapq.heappop(open_set)
current_marking = curr.m
continue
h, x = utils.__compute_exact_heuristic_new_version(sync_net, a_matrix, h_cvx, g_matrix, cost_vec,
incidence_matrix, curr.m,
fin_vec, lp_solver.DEFAULT_LP_SOLVER_VARIANT,
use_cvxopt=use_cvxopt)
lp_solved += 1
# 11/10/19: shall not a state for which we compute the exact heuristics be
# by nature a trusted solution?
tp = utils.SearchTuple(curr.g + h, curr.g, h, curr.m, curr.p, curr.t, x, True)
# 11/10/2019 (optimization ZA) heappushpop is slightly more efficient than pushing
# and popping separately
curr = heapq.heappushpop(open_set, tp)
current_marking = curr.m
# max allowed heuristics value (27/10/2019, due to the numerical instability of some of our solvers)
if curr.h > lp_solver.MAX_ALLOWED_HEURISTICS:
continue
# 12/10/2019: do it again, since the marking could be changed
already_closed = current_marking in closed
if already_closed:
continue
# 12/10/2019: the current marking can be equal to the final marking only if the heuristics
# (underestimation of the remaining cost) is 0. Low-hanging fruits
if curr.h < 0.01:
if current_marking == fin:
return utils.__reconstruct_alignment(curr, visited, queued, traversed,
ret_tuple_as_trans_desc=ret_tuple_as_trans_desc,
lp_solved=lp_solved)
closed.add(current_marking)
visited += 1
enabled_trans = copy(trans_empty_preset)
for p in current_marking:
for t in p.ass_trans:
if t.sub_marking <= current_marking:
enabled_trans.add(t)
trans_to_visit_with_cost = [(t, cost_function[t]) for t in enabled_trans if not (
t is not None and utils.__is_log_move(t, skip) and utils.__is_model_move(t, skip))]
for t, cost in trans_to_visit_with_cost:
traversed += 1
new_marking = utils.add_markings(current_marking, t.add_marking)
if new_marking in closed:
continue
g = curr.g + cost
queued += 1
h, x = utils.__derive_heuristic(incidence_matrix, cost_vec, curr.x, t, curr.h)
trustable = utils.__trust_solution(x)
new_f = g + h
tp = utils.SearchTuple(new_f, g, h, new_marking, curr, t, x, trustable)
heapq.heappush(open_set, tp)
def __search_with_synchr(sync_net,
ini,
fin,
skip,
ret_tuple_as_trans_desc=False,
max_align_time_trace=sys.maxsize,
expo=2):
'''
In this function that can be called with the following way:
alignment.algorithm.apply(trace, net, marking, fmarking,variant=ali.VERSION_DIJKSTRA_EXPONENTIAL_HEURISTIC,
parameters={ali.Parameters.SYNCHRONOUS:True})
Cost of transition depends on the run of the synchronous product.
Other parameters:
ali.Parameters.EXPONENT:2 (change the base of the log)
'''
start_time = time.time()
decorate_transitions_prepostset(sync_net)
decorate_places_preset_trans(sync_net)
closed = {}
ini_state = utils.DijkstraSearchTuple(0, ini, None, None, 0)
open_set = [ini_state]
heapq.heapify(open_set)
visited = 0
queued = 0
traversed = 0
def cost_function(t, l, expo):
if t.label is None:
return expo**(-l)
if t.label[1] == utils.SKIP or t.label[0] == utils.SKIP:
return expo**(-l)
else:
return 0
trans_empty_preset = set(t for t in sync_net.transitions
if len(t.in_arcs) == 0)
while not len(open_set) == 0:
if (time.time() - start_time) > max_align_time_trace:
return None
curr = heapq.heappop(open_set)
current_marking = curr.m
already_closed = current_marking in closed.keys()
if already_closed:
continue
if current_marking == fin:
return utils.__reconstruct_alignment(
curr,
visited,
queued,
traversed,
ret_tuple_as_trans_desc=ret_tuple_as_trans_desc)
closed[current_marking] = curr.l
visited += 1
possible_enabling_transitions = copy(trans_empty_preset)
for p in current_marking:
for t in p.ass_trans:
possible_enabling_transitions.add(t)
enabled_trans = [
t for t in possible_enabling_transitions
if t.sub_marking <= current_marking
]
trans_to_visit_with_cost = [(t, cost_function(t, curr.l, expo))
for t in enabled_trans if t is not None]
for t, cost in trans_to_visit_with_cost:
traversed += 1
new_marking = utils.add_markings(current_marking, t.add_marking)
already_closed = new_marking in closed.keys()
if already_closed:
continue
queued += 1
tp = utils.DijkstraSearchTuple(curr.g + cost, new_marking, curr, t,
curr.l + 1)
heapq.heappush(open_set, tp)