Merge pull request #74 from APLA-Toolbox/add-pddl-examples-limit

Add pddl examples limit

Author: guilyx

README.md

@@ -59,8 +59,8 @@ If you want to use it by cloning the project:
 ```shell
 $ git clone https://github.com/APLA-Toolbox/PythonPDDL
 $ cd PythonPDDL
-$ git submodule init
-$ git submodule update
+$ python3 -m pip install -r requirements.txt
+$ git submodule update --init
 ```
 
 You should have a `pddl-examples` folder containing PDDL instances.

jupyddl/data_analyst.py

@@ -21,19 +21,25 @@ def __init__(self):
         logging.info("Instantiating data analyst...")
         self.available_heuristics = ["goal_count", "zero"]
 
-    def __get_all_pddl_from_data(self):
+    def __get_all_pddl_from_data(self, max_pddl_instances=-1):
         tested_files = []
         domains_problems = []
         i = 0
         if "DISPLAY" in os.environ:
             for root, _, files in os.walk("pddl-examples/", topdown=False):
                 for name in files:
-                    # if ".gitkeep" in name:
+                    # if "README" in name:
+                    #    continue
+                    # if "LICENSE" in name:
+                    #    continue
+                    # if ".gitignore" in name:
                     #    continue
                     tested_files.append(os.getcwd() + "/" + os.path.join(root, name))
                     if i % 2 != 0:
                         domains_problems.append((tested_files[i - 1], tested_files[i]))
                     i += 1
+                    if max_pddl_instances != -1 and i >= max_pddl_instances*2:
+                        return domains_problems
             return domains_problems
         return [
             ("pddl-examples/flip/problem.pddl", "pddl-examples/flip/domain.pddl"),
@@ -66,12 +72,12 @@ def __scatter_data(self, times, total_nodes, plot_title):
         plt.show(block=False)
 
     def __gather_data_astar(
-        self, domain_path="", problem_path="", heuristic_key="goal_count"
+        self, domain_path="", problem_path="", heuristic_key="goal_count", max_pddl_instances=-1
     ):
         has_multiple_files_tested = True
         if not domain_path or not problem_path:
             metrics = dict()
-            for problem, domain in self.__get_all_pddl_from_data():
+            for problem, domain in self.__get_all_pddl_from_data(max_pddl_instances=max_pddl_instances):
                 logging.debug("Loading new PDDL instance planned with A*...")
                 logging.debug("Domain: " + domain)
                 logging.debug("Problem: " + problem)
@@ -111,26 +117,26 @@ def __gather_data_astar(
             return [total_time], [opened_nodes], has_multiple_files_tested
         return [0], [0], has_multiple_files_tested
 
-    def plot_astar(self, heuristic_key="goal_count", domain="", problem=""):
+    def plot_astar(self, heuristic_key="goal_count", domain="", problem="", max_pddl_instances=-1):
         if bool(not problem) != bool(not domain):
             logging.warning(
                 "Either problem or domain wasn't provided, testing all files in data folder"
             )
             problem = domain = ""
         times, total_nodes, has_multiple_files_tested = self.__gather_data_astar(
-            heuristic_key=heuristic_key, problem_path=problem, domain_path=domain
+            heuristic_key=heuristic_key, problem_path=problem, domain_path=domain, max_pddl_instances=max_pddl_instances
         )
         title = "A* Statistics" + "[Heuristic: " + heuristic_key + "]"
         if has_multiple_files_tested:
             self.__plot_data(times, total_nodes, title)
         else:
             self.__scatter_data(times, total_nodes, title)
 
-    def __gather_data_bfs(self, domain_path="", problem_path=""):
+    def __gather_data_bfs(self, domain_path="", problem_path="", max_pddl_instances=-1):
         has_multiple_files_tested = True
         if not domain_path or not problem_path:
             metrics = dict()
-            for problem, domain in self.__get_all_pddl_from_data():
+            for problem, domain in self.__get_all_pddl_from_data(max_pddl_instances=max_pddl_instances):
                 logging.debug("Loading new PDDL instance planned with BFS...")
                 logging.debug("Domain: " + domain)
                 logging.debug("Problem: " + problem)
@@ -154,26 +160,26 @@ def __gather_data_bfs(self, domain_path="", problem_path=""):
             return [total_time], [opened_nodes], has_multiple_files_tested
         return [0], [0], has_multiple_files_tested
 
-    def plot_bfs(self, domain="", problem=""):
+    def plot_bfs(self, domain="", problem="", max_pddl_instances=-1):
         title = "BFS Statistics"
         if bool(not problem) != bool(not domain):
             logging.warning(
                 "Either problem or domain wasn't provided, testing all files in data folder"
             )
             problem = domain = ""
         times, total_nodes, has_multiple_files_tested = self.__gather_data_bfs(
-            problem_path=problem, domain_path=domain
+            problem_path=problem, domain_path=domain, max_pddl_instances=max_pddl_instances
         )
         if has_multiple_files_tested:
             self.__plot_data(times, total_nodes, title)
         else:
             self.__scatter_data(times, total_nodes, title)
 
-    def __gather_data_dfs(self, domain_path="", problem_path=""):
+    def __gather_data_dfs(self, domain_path="", problem_path="", max_pddl_instances=-1):
         has_multiple_files_tested = True
         if not domain_path or not problem_path:
             metrics = dict()
-            for problem, domain in self.__get_all_pddl_from_data():
+            for problem, domain in self.__get_all_pddl_from_data(max_pddl_instances=max_pddl_instances):
                 logging.debug("Loading new PDDL instance planned with DFS...")
                 logging.debug("Domain: " + domain)
                 logging.debug("Problem: " + problem)
@@ -197,26 +203,26 @@ def __gather_data_dfs(self, domain_path="", problem_path=""):
             return [total_time], [opened_nodes], has_multiple_files_tested
         return [0], [0], has_multiple_files_tested
 
-    def plot_dfs(self, problem="", domain=""):
+    def plot_dfs(self, problem="", domain="", max_pddl_instances=-1):
         title = "DFS Statistics"
         if bool(not problem) != bool(not domain):
             logging.warning(
                 "Either problem or domain wasn't provided, testing all files in data folder"
             )
             problem = domain = ""
         times, total_nodes, has_multiple_files_tested = self.__gather_data_dfs(
-            problem_path=problem, domain_path=domain
+            problem_path=problem, domain_path=domain, max_pddl_instances=max_pddl_instances
         )
         if has_multiple_files_tested:
             self.__plot_data(times, total_nodes, title)
         else:
             self.__scatter_data(times, total_nodes, title)
 
-    def __gather_data_dijkstra(self, domain_path="", problem_path=""):
+    def __gather_data_dijkstra(self, domain_path="", problem_path="", max_pddl_instances=-1):
         has_multiple_files_tested = True
         if not domain_path or not problem_path:
             metrics = dict()
-            for problem, domain in self.__get_all_pddl_from_data():
+            for problem, domain in self.__get_all_pddl_from_data(max_pddl_instances=max_pddl_instances):
                 logging.debug("Loading new PDDL instance planned with Dijkstra...")
                 logging.debug("Domain: " + domain)
                 logging.debug("Problem: " + problem)
@@ -240,15 +246,15 @@ def __gather_data_dijkstra(self, domain_path="", problem_path=""):
             return [total_time], [opened_nodes], has_multiple_files_tested
         return [0], [0], has_multiple_files_tested
 
-    def plot_dijkstra(self, problem="", domain=""):
+    def plot_dijkstra(self, problem="", domain="", max_pddl_instances=-1):
         title = "Dijkstra Statistics"
         if bool(not problem) != bool(not domain):
             logging.warning(
                 "Either problem or domain wasn't provided, testing all files in data folder"
             )
             problem = domain = ""
         times, total_nodes, has_multiple_files_tested = self.__gather_data_dijkstra(
-            problem_path=problem, domain_path=domain
+            problem_path=problem, domain_path=domain, max_pddl_instances=max_pddl_instances
         )
         if has_multiple_files_tested:
             self.__plot_data(times, total_nodes, title)
@@ -264,6 +270,7 @@ def __gather_data(
         dijkstra=True,
         domain="",
         problem="",
+        max_pddl_instances=-1
     ):
         gatherers = []
         xdata = dict()
@@ -287,21 +294,22 @@ def __gather_data(
                     domain_path=domain,
                     problem_path=problem,
                     heuristic_key=heuristic_key,
+                    max_pddl_instances=max_pddl_instances
                 )
             else:
-                times, nodes, _ = g(domain_path=domain, problem_path=problem)
+                times, nodes, _ = g(domain_path=domain, problem_path=problem, max_pddl_instances=max_pddl_instances)
             ydata[name] = times
             xdata[name] = nodes
         return xdata, ydata
 
-    def comparative_astar_heuristic_plot(self, domain="", problem=""):
+    def comparative_astar_heuristic_plot(self, domain="", problem="", max_pddl_instances=-1):
         _, ax = plt.subplots()
         plt.xlabel("Number of opened nodes")
         plt.ylabel("Planning computation time (s)")
 
         for h in self.available_heuristics:
             times, nodes, _ = self.__gather_data_astar(
-                domain_path=domain, problem_path=problem, heuristic_key=h
+                domain_path=domain, problem_path=problem, heuristic_key=h, max_pddl_instances=max_pddl_instances
             )
             data = dict()
             for i, val in enumerate(nodes):
@@ -334,6 +342,7 @@ def comparative_data_plot(
         problem="",
         heuristic_key="goal_count",
         collect_new_data=True,
+        max_pddl_instances=-1
     ):
         json_dict = {}
         if collect_new_data:
@@ -345,6 +354,7 @@ def comparative_data_plot(
                 dijkstra=dijkstra,
                 domain=domain,
                 problem=problem,
+                max_pddl_instances=max_pddl_instances
             )
             json_dict["xdata"] = xdata
             json_dict["ydata"] = ydata
@@ -363,6 +373,7 @@ def comparative_data_plot(
                     dijkstra=dijkstra,
                     domain=domain,
                     problem=problem,
+                    max_pddl_instances=max_pddl_instances
                 )
                 json_dict["xdata"] = xdata
                 json_dict["ydata"] = ydata

tests/test_data_analyst.py

@@ -84,6 +84,29 @@ def test_data_analyst_plot_astar_h_goal_count():
     da.plot_astar()
     assert True
 
+def test_data_analyst_plot_dfs_restricted():
+    da = DataAnalyst()
+    da.plot_dfs(max_pddl_instances=2)
+    assert True
+
+
+def test_data_analyst_plot_bfs_restricted():
+    da = DataAnalyst()
+    da.plot_bfs(max_pddl_instances=2)
+    assert True
+
+
+def test_data_analyst_plot_dijkstra_restricted():
+    da = DataAnalyst()
+    da.plot_dijkstra(max_pddl_instances=2)
+    assert True
+
+
+def test_data_analyst_plot_astar_h_goal_count_restricted():
+    da = DataAnalyst()
+    da.plot_astar(max_pddl_instances=2)
+    assert True
+
 
 def test_data_analyst_plot_astar_h_zero():
     da = DataAnalyst()