Ajout demonstration final

demo_boucle.py

@@ -0,0 +1,35 @@
+#! /bin/python3
+
+import socket
+import time
+import numpy as np
+
+from coapthon.client.helperclient import HelperClient
+from coapthon.client.superviseur import (SuperviseurGlobal,
+                                         SuperviseurLocalFiltre)
+from coapthon.utils import parse_uri
+from utils_learning import RequettePeriodique
+
+
+host, port, path = parse_uri("coap://polaris.kokarde.fr/basic")
+try:
+    tmp = socket.gethostbyname(host)
+    host = tmp
+except socket.gaierror:
+    pass
+
+nombreCapteur = 25
+periodeRequette = 1
+periodeControl = 15
+
+clients = [HelperClient(server=(host, port)) for _ in range(nombreCapteur)]
+super_g = SuperviseurGlobal(clients, SuperviseurLocalFiltre)
+
+requests = [RequettePeriodique(client, periodeRequette, path, name="Spamer {}".format(
+            n)) for n, client in enumerate(clients)]
+[request.start() for request in requests]
+
+for _ in range(10):
+    super_g.reset()
+    time.sleep(periodeControl)
+    print(super_g.state)

utils_learning.py

@@ -7,11 +7,7 @@ import time
 from typing import Any, Callable, Iterable, Mapping, Optional
 
 import numpy as np
-import tensorflow as tf
+
-from tf_agents.environments import (py_environment, tf_environment,
-                                    tf_py_environment, utils, wrappers)
-from tf_agents.specs import array_spec
-from tf_agents.trajectories import time_step as ts
 
 from coapthon.client.helperclient import HelperClient
 from coapthon.client.superviseur import (SuperviseurGlobal,
@@ -46,62 +42,70 @@ class RequettePeriodique(threading.Thread):
         else:
             raise ValueError
 
-
+try :
-class MaquetteCoapEnv(py_environment.PyEnvironment):
+    import tensorflow as tf
-    def __init__(self, clients: Iterable[HelperClient], superviseur_local_type: type, superviseur_global_type: type, request_path: str, args_reward: Iterable[Any] = (),
+    from tf_agents.environments import (py_environment, tf_environment,
-                 control_period: float = 30, request_period: Iterable[float] = None) -> None:
+                                        tf_py_environment, utils, wrappers)
-
+    from tf_agents.specs import array_spec
-        self.clients = clients
+    from tf_agents.trajectories import time_step as ts
-        self.super_g = superviseur_global_type(clients, superviseur_local_type)
+    class MaquetteCoapEnv(py_environment.PyEnvironment):
-
+        def __init__(self, clients: Iterable[HelperClient], superviseur_local_type: type, superviseur_global_type: type, request_path: str, args_reward: Iterable[Any] = (),
-        self._action_spec = array_spec.BoundedArraySpec(
+                    control_period: float = 30, request_period: Iterable[float] = None) -> None:
-            shape=(len(clients),), dtype=np.float32, minimum=-10, maximum=10, name='action')
+
-        self._observation_spec = array_spec.BoundedArraySpec(
+            self.clients = clients
-            shape=(superviseur_global_type.nombre_mesure, len(clients)), dtype=np.float32, minimum=0, name='observation')
+            self.super_g = superviseur_global_type(clients, superviseur_local_type)
-        self._episode_ended = False
+
-        self._current_time_step = np.zeros(
+            self._action_spec = array_spec.BoundedArraySpec(
-            (3, len(self.clients)), dtype=np.float32)
+                shape=(len(clients),), dtype=np.float32, minimum=-10, maximum=10, name='action')
-        self.control_period = control_period
+            self._observation_spec = array_spec.BoundedArraySpec(
-
+                shape=(superviseur_global_type.nombre_mesure, len(clients)), dtype=np.float32, minimum=0, name='observation')
-        self._args_reward = args_reward
+            self._episode_ended = False
-
+            self._current_time_step = np.zeros(
-        if request_period is None:
+                (3, len(self.clients)), dtype=np.float32)
-            request_period = [5 for client in clients]
+            self.control_period = control_period
-
+
-        self.requests = [RequettePeriodique(client, request_period[n], request_path, name="Spamer {}".format(
+            self._args_reward = args_reward
-            n)) for n, client in enumerate(clients)]
+
-        [request.start() for request in self.requests]
+            if request_period is None:
-
+                request_period = [5 for client in clients]
-    @property
+
-    def request_period(self):
+            self.requests = [RequettePeriodique(client, request_period[n], request_path, name="Spamer {}".format(
-        return [request.period for request in self.requests]
+                n)) for n, client in enumerate(clients)]
-
+            [request.start() for request in self.requests]
-    def action_spec(self) -> array_spec.BoundedArraySpec:
+
-        return self._action_spec
+        @property
-
+        def request_period(self):
-    def observation_spec(self) -> array_spec.BoundedArraySpec:
+            return [request.period for request in self.requests]
-        return self._observation_spec
+
-
+        def action_spec(self) -> array_spec.BoundedArraySpec:
-    def _reset(self) -> None:
+            return self._action_spec
-        etat = np.zeros(
+
-            (3, len(self.clients)), dtype=np.float32)
+        def observation_spec(self) -> array_spec.BoundedArraySpec:
-        self._current_time_step = etat
+            return self._observation_spec
-        self.super_g.reset_rto()
+
-        return ts.transition(etat, reward=0)
+        def _reset(self) -> None:
-
+            etat = np.zeros(
-    def _step(self, action: Iterable[float]):
+                (3, len(self.clients)), dtype=np.float32)
-        self.super_g.application_action(action)
+            self._current_time_step = etat
-        self.super_g.reset()
+            self.super_g.reset_rto()
-
+            return ts.transition(etat, reward=0)
-        time.sleep(self.control_period)
+
-
+        def _step(self, action: Iterable[float]):
-        etat = self.super_g.state
+            self.super_g.application_action(action)
-        if self._args_reward == ():
+            self.super_g.reset()
-            recompense = self.super_g.qualite(5*[1], 1000, 1, 1)
+
-        else:
+            time.sleep(self.control_period)
-            recompense = self.super_g.qualite(5*[1], *self._args_reward)
+
-        self._current_time_step = etat
+            etat = self.super_g.state
-        if self.super_g.failed:
+            if self._args_reward == ():
-            return ts.termination(etat, -10000)
+                recompense = self.super_g.qualite(5*[1], 1000, 1, 1)
-        else:
+            else:
-            return ts.transition(etat, reward=recompense)
+                recompense = self.super_g.qualite(5*[1], *self._args_reward)
+            self._current_time_step = etat
+            if self.super_g.failed:
+                return ts.termination(etat, -10000)
+            else:
+                return ts.transition(etat, reward=recompense)
+
+except ImportError :
+    print("Pas de fonctionalité d'apprentissage")