def _create_evaluation_order(self, pattern: Pattern):
if pattern.statistics_type == StatisticsTypes.SELECTIVITY_MATRIX_AND_ARRIVAL_RATES:
(selectivityMatrix, arrivalRates) = pattern.statistics
else:
raise MissingStatisticsException()
return DynamicProgrammingLeftDeepTreeBuilder.find_order(
selectivityMatrix, arrivalRates, pattern.window.total_seconds())
def build_single_pattern_eval_mechanism(self, pattern: Pattern):
if pattern.statistics_type == StatisticsTypes.SELECTIVITY_MATRIX_AND_ARRIVAL_RATES:
(selectivityMatrix, arrivalRates) = pattern.statistics
else:
raise MissingStatisticsException()
tree_structure = self._find_tree(selectivityMatrix, arrivalRates,
pattern.window.total_seconds())
return TreeBasedEvaluationMechanism(pattern, tree_structure)
def get_plan_cost(self, pattern: Pattern, plan: TreePlanNode):
if pattern.statistics_type == StatisticsTypes.SELECTIVITY_MATRIX_AND_ARRIVAL_RATES:
(selectivity_matrix, arrival_rates) = pattern.statistics
else:
raise MissingStatisticsException()
_, _, cost = IntermediateResultsTreeCostModel.__get_plan_cost_aux(
plan, selectivity_matrix, arrival_rates,
pattern.window.total_seconds())
return cost
def _create_evaluation_order(self, pattern: Pattern):
if pattern.statistics_type == StatisticsTypes.SELECTIVITY_MATRIX_AND_ARRIVAL_RATES:
(selectivityMatrix, arrivalRates) = pattern.statistics
else:
raise MissingStatisticsException()
order = None
if self.__initType == IterativeImprovementInitType.RANDOM:
order = self.__get_random_order(len(arrivalRates))
elif self.__initType == IterativeImprovementInitType.GREEDY:
order = GreedyLeftDeepTreeBuilder.calculate_greedy_order(
selectivityMatrix, arrivalRates)
get_cost_callback = lambda o: self._get_order_cost(pattern, o)
return self.__iterative_improvement.execute(self.__step_limit, order,
get_cost_callback)
def _create_evaluation_order(self, pattern: Pattern):
if pattern.statistics_type == StatisticsTypes.FREQUENCY_DICT:
frequency_dict = pattern.statistics
order = get_order_by_occurrences(pattern.positive_structure.args,
frequency_dict)
elif pattern.statistics_type == StatisticsTypes.ARRIVAL_RATES:
arrival_rates = pattern.statistics
# create an index-arrival rate binding and sort according to arrival rate.
sorted_order = sorted([(i, arrival_rates[i])
for i in range(len(arrival_rates))],
key=lambda x: x[1])
order = [x for x, y in sorted_order
] # create order from sorted binding.
else:
raise MissingStatisticsException()
return order
def _create_evaluation_order(self, pattern: Pattern):
if pattern.statistics_type == StatisticsTypes.SELECTIVITY_MATRIX_AND_ARRIVAL_RATES:
(selectivity_matrix, arrival_rates) = pattern.statistics
else:
raise MissingStatisticsException()
args_num = len(selectivity_matrix)
if args_num == 1: # boring extreme case
return [0]
items = frozenset(range(args_num))
# Save subsets' optimal orders, the cost and the left to add items.
sub_orders = {
frozenset({i}):
([i], self._get_order_cost(pattern, [i]), items.difference({i}))
for i in items
}
for i in range(2, args_num + 1):
# for each subset of size i, we will find the best order for each subset
next_orders = {}
for subset in sub_orders.keys():
order, _, left_to_add = sub_orders[subset]
for item in left_to_add:
# calculate for optional order for set of size i
new_subset = frozenset(subset.union({item}))
new_cost = self._get_order_cost(pattern, order)
# check if it is not the first order for that set
if new_subset in next_orders.keys():
_, t_cost, t_left = next_orders[new_subset]
if new_cost < t_cost: # check if it is the current best order for that set
new_order = order + [item]
next_orders[
new_subset] = new_order, new_cost, t_left
else: # if it is the first order for that set
new_order = order + [item]
next_orders[
new_subset] = new_order, new_cost, left_to_add.difference(
{item})
# update subsets for next iteration
sub_orders = next_orders
return list(sub_orders.values())[0][
0] # return the order (at index 0 in the tuple) of item 0, the only item in subsets of size n.
def _create_tree_topology(self, pattern: Pattern):
if pattern.statistics_type == StatisticsTypes.SELECTIVITY_MATRIX_AND_ARRIVAL_RATES:
(selectivity_matrix, arrival_rates) = pattern.statistics
else:
raise MissingStatisticsException()
args_num = len(selectivity_matrix)
if args_num == 1:
return [0]
items = frozenset(range(args_num))
# Save subsets' optimal topologies, the cost and the left to add items.
sub_trees = {frozenset({i}): (TreePlanLeafNode(i),
self._get_plan_cost(pattern, TreePlanLeafNode(i)),
items.difference({i}))
for i in items}
# for each subset of size i, find optimal topology for these subsets according to size (i-1) subsets.
for i in range(2, args_num + 1):
for tSubset in combinations(items, i):
subset = frozenset(tSubset)
disjoint_sets_iter = get_all_disjoint_sets(subset) # iterator for all disjoint splits of a set.
# use first option as speculative best.
set1_, set2_ = next(disjoint_sets_iter)
tree1_, _, _ = sub_trees[set1_]
tree2_, _, _ = sub_trees[set2_]
new_tree_ = TreePlanBuilder._instantiate_binary_node(pattern, tree1_, tree2_)
new_cost_ = self._get_plan_cost(pattern, new_tree_)
new_left_ = items.difference({subset})
sub_trees[subset] = new_tree_, new_cost_, new_left_
# find the best topology based on previous topologies for smaller subsets.
for set1, set2 in disjoint_sets_iter:
tree1, _, _ = sub_trees[set1]
tree2, _, _ = sub_trees[set2]
new_tree = TreePlanBuilder._instantiate_binary_node(pattern, tree1, tree2)
new_cost = self._get_plan_cost(pattern, new_tree)
_, cost, left = sub_trees[subset]
# if new subset's topology is better, then update to it.
if new_cost < cost:
sub_trees[subset] = new_tree, new_cost, left
return sub_trees[items][0] # return the best topology (index 0 at tuple) for items - the set of all arguments.
def _create_tree_topology(self, pattern: Pattern):
if pattern.statistics_type == StatisticsTypes.SELECTIVITY_MATRIX_AND_ARRIVAL_RATES:
(selectivity_matrix, arrival_rates) = pattern.statistics
else:
raise MissingStatisticsException()
order = self._get_initial_order(selectivity_matrix, arrival_rates)
args_num = len(order)
items = tuple(order)
suborders = {
(i,): (TreePlanLeafNode(i), self._get_plan_cost(pattern, TreePlanLeafNode(i)))
for i in items
}
# iterate over suborders' sizes
for i in range(2, args_num + 1):
# iterate over suborders of size i
for j in range(args_num - i + 1):
# create the suborder (slice) to find its optimum.
suborder = tuple(order[t] for t in range(j, j + i))
# use first split of suborder as speculative best.
order1_, order2_ = suborder[:1], suborder[1:]
tree1_, _ = suborders[order1_]
tree2_, _ = suborders[order2_]
tree = TreePlanBuilder._instantiate_binary_node(pattern, tree1_, tree2_)
cost = self._get_plan_cost(pattern, tree)
suborders[suborder] = tree, cost
# iterate over splits of suborder
for k in range(2, i):
# find the optimal topology of this split, according to optimal topologies of subsplits.
order1, order2 = suborder[:k], suborder[k:]
tree1, _ = suborders[order1]
tree2, _ = suborders[order2]
_, prev_cost = suborders[suborder]
new_tree = TreePlanBuilder._instantiate_binary_node(pattern, tree1, tree2)
new_cost = self._get_plan_cost(pattern, new_tree)
if new_cost < prev_cost:
suborders[suborder] = new_tree, new_cost
return suborders[items][0] # return the topology (index 0 at tuple) of the entire order, indexed to 'items'.
def _create_evaluation_order(self, pattern: Pattern):
if pattern.statistics_type == StatisticsTypes.SELECTIVITY_MATRIX_AND_ARRIVAL_RATES:
(selectivityMatrix, arrivalRates) = pattern.statistics
else:
raise MissingStatisticsException()
return self.calculate_greedy_order(selectivityMatrix, arrivalRates)