Update GA operators and fix synthetic generator (#56)

- Fix synthetic generator The generator created graphs that had nodes, in addition to the final one, that did not have children. Now it is fixed. - Delete update_resource_borders_to_peak_values operator, because it can change chromosome such that corresponding schedule changes too, in cases when lag optimization is used. - Update scheduling order mutation operator. Now it uses in addition to information about node parents, information about children. New operator improves the performance of GA. - Use numpy in zones mutation operator - Delete borders update test
aimclub · Oct 23, 2023 · 78d2b66 · 78d2b66
1 parent c6602b1
commit 78d2b66
Show file tree

Hide file tree

Showing 8 changed files with 176 additions and 196 deletions.
diff --git a/sampo/generator/pipeline/project.py b/sampo/generator/pipeline/project.py
@@ -6,7 +6,7 @@
     MAX_BOREHOLES_PER_BLOCK, BRANCHING_PROBABILITY
 from sampo.generator.pipeline.cluster import get_cluster_works, _add_addition_work
 from sampo.generator.pipeline.types import SyntheticGraphType, StageType
-from sampo.generator.utils.graph_node_operations import count_node_ancestors
+from sampo.generator.utils.graph_node_operations import count_ancestors
 from sampo.schemas.graph import GraphNode, WorkGraph, EdgeType
 from sampo.schemas.utils import uuid_str
 from sampo.schemas.works import WorkUnit
@@ -109,18 +109,16 @@ def get_graph(mode: SyntheticGraphType | None = SyntheticGraphType.GENERAL,
 
         root_stage = get_root_stage(stages, branching_probability, rand)
         checkpoints, roads = _get_cluster_graph(root_stage, f'{cluster_name_prefix}{masters_clusters_ind}',
-                                            addition_cluster_probability=addition_cluster_probability, rand=rand)
-        tmp_finish = get_finish_stage(checkpoints)
-        count_works = count_node_ancestors(tmp_finish, root_stage)
+                                                addition_cluster_probability=addition_cluster_probability, rand=rand)
 
-        if 0 < top_border < (count_works + works_generated):
-            break
+        count_works = count_ancestors(checkpoints, root_stage)
 
         stages += [(c, roads) for c in checkpoints]
         masters_clusters_ind += 1
         works_generated += count_works
 
-        if 0 < bottom_border <= works_generated or 0 < cluster_counts <= (len(stages) - 1):
+        if (0 < bottom_border <= works_generated or top_border < (count_works + works_generated)
+                or 0 < cluster_counts <= (len(stages) - 1)):
             break
 
     if len(stages) == 1:

diff --git a/sampo/generator/utils/graph_node_operations.py b/sampo/generator/utils/graph_node_operations.py
@@ -1,28 +1,25 @@
-import queue
-
 from sampo.schemas.graph import GraphNode
 
 
-def count_node_ancestors(finish: GraphNode, root: GraphNode) -> int:
+def count_ancestors(first_ancestors: list[GraphNode], root: GraphNode) -> int:
     """
     Counts the number of ancestors of the whole graph.
 
-    :param finish: The node for which ancestors are to be counted.
+    :param first_ancestors: First ancestors of ancestors which must be counted.
     :param root: The root node of the graph.
     :return:
     """
-    q = queue.Queue()
-    count = 0
+    q = list(first_ancestors)
+    count = len(first_ancestors)
     used = set()
     used.add(root)
-    q.put(finish)
-    while not q.empty():
-        node = q.get()
+    while q:
+        node = q.pop()
         for parent in node.parents:
             if parent in used:
                 continue
             used.add(parent)
-            q.put(parent)
+            q.insert(0, parent)
             count += 1
 
     return count
diff --git a/sampo/scheduler/genetic/base.py b/sampo/scheduler/genetic/base.py
@@ -4,6 +4,7 @@
 from sampo.scheduler.base import Scheduler, SchedulerType
 from sampo.scheduler.genetic.operators import FitnessFunction, TimeFitness
 from sampo.scheduler.genetic.schedule_builder import build_schedule
+from sampo.scheduler.genetic.converter import ChromosomeType
 from sampo.scheduler.heft.base import HEFTScheduler, HEFTBetweenScheduler
 from sampo.scheduler.heft.prioritization import prioritization
 from sampo.scheduler.resource.average_req import AverageReqResourceOptimizer
@@ -38,7 +39,7 @@ def __init__(self,
                  seed: Optional[float or None] = None,
                  n_cpu: int = 1,
                  weights: list[int] = None,
-                 fitness_constructor: Callable[[Time | None], FitnessFunction] = TimeFitness,
+                 fitness_constructor: Callable[[Callable[[list[ChromosomeType]], list[Schedule]]], FitnessFunction] = TimeFitness,
                  scheduler_type: SchedulerType = SchedulerType.Genetic,
                  resource_optimizer: ResourceOptimizer = IdentityResourceOptimizer(),
                  work_estimator: WorkTimeEstimator = DefaultWorkEstimator(),
@@ -214,7 +215,6 @@ def schedule_with_cache(self,
 
         mutate_order, mutate_resources, mutate_zones, size_of_population = self.get_params(wg.vertex_count)
         worker_pool = get_worker_contractor_pool(contractors)
-        fitness_object = self.fitness_constructor(self._deadline)
         deadline = None if self._optimize_resources else self._deadline
 
         scheduled_works, schedule_start_time, timeline, order_nodes = build_schedule(wg,
@@ -229,7 +229,7 @@ def schedule_with_cache(self,
                                                                                      self.rand,
                                                                                      spec,
                                                                                      landscape,
-                                                                                     fitness_object,
+                                                                                     self.fitness_constructor,
                                                                                      self.work_estimator,
                                                                                      self._n_cpu,
                                                                                      assigned_parent_time,

diff --git a/sampo/scheduler/genetic/converter.py b/sampo/scheduler/genetic/converter.py
@@ -18,8 +18,7 @@
 ChromosomeType = tuple[np.ndarray, np.ndarray, np.ndarray, ScheduleSpec, np.ndarray]
 
 
-def convert_schedule_to_chromosome(wg: WorkGraph,
-                                   work_id2index: dict[str, int],
+def convert_schedule_to_chromosome(work_id2index: dict[str, int],
                                    worker_name2index: dict[str, int],
                                    contractor2index: dict[str, int],
                                    contractor_borders: np.ndarray,
@@ -30,7 +29,6 @@ def convert_schedule_to_chromosome(wg: WorkGraph,
     """
     Receive a result of scheduling algorithm and transform it to chromosome
 
-    :param wg:
     :param work_id2index:
     :param worker_name2index:
     :param contractor2index:
@@ -43,7 +41,7 @@ def convert_schedule_to_chromosome(wg: WorkGraph,
     """
 
     order: list[GraphNode] = order if order is not None else [work for work in schedule.works
-                                                              if not wg[work.work_unit.id].is_inseparable_son()]
+                                                              if work.work_unit.id in work_id2index]
 
     # order works part of chromosome
     order_chromosome: np.ndarray = np.array([work_id2index[work.work_unit.id] for work in order])