App.py

@@ -10,6 +10,7 @@ import Ui
 import BFS
 import AStar
 import neuralnetwork
+import json
 
 
 bfs1_flag=False
@@ -20,8 +21,9 @@ Astar2 = False
 if bfs3_flag or Astar or Astar2:
    Pole.stoneFlag = True
 TreeFlag=False
-nnFlag=True
+nnFlag=False
 newModel=False
+finalFlag = True
 
 pygame.init()
 show_console=True
@@ -43,7 +45,15 @@ def init_demo(): #Demo purpose
     old_info=""
     traktor.draw_tractor()
     time.sleep(2)
+    if not finalFlag:
         pole.randomize_colors(nnFlag)
+    else:
+        population = 120
+        iterat = 2500
+        roulette = True
+        with open(f'pole_pop{population}_iter{iterat}_{roulette}.json', 'r') as file:
+            garden_data = json.load(file)
+        pole.setPlantsByList(garden_data)
     traktor.draw_tractor()
     start_flag=True
     while True:
@@ -128,11 +138,16 @@ def init_demo(): #Demo purpose
                     print_to_console("sieć nuronowa nauczona")
                     print('model został wygenerowany')
                 else:
-                    model = neuralnetwork.loadModel('model.pth')
+                    model = neuralnetwork.loadModel('model_500_hidden.pth')
                     print_to_console("model został załądowny")
                 testset = neuralnetwork.getDataset(False)
                 print(neuralnetwork.accuracy(model, testset))
-                traktor.snake_move_predict_plant(pole, model)
+                traktor.snake_move_predict_plant(pole, model, headers=['Coords','Real plant','Predicted plant','Result','Fertilizer'], actions=[traktor.fertilize_slot])
+            if(finalFlag):
+                pass
+                model = neuralnetwork.loadModel('model_500_hidden.pth')
+                Tractor.drzewo.treeLearn()
+                traktor.snake_move_predict_plant(pole, model, headers=['Coords','Real plant','Predicted plant','Result','Decision'], actions=[traktor.irigate_slot_NN])
             start_flag=False
         # demo_move()
         old_info=get_info(old_info)

Drzewo.py

@@ -8,7 +8,7 @@ class Drzewo:
         self.tree=self.treeLearn()
 
     def treeLearn(self):
-        csvdata=pandas.read_csv('Data/dataTree.csv')
+        csvdata=pandas.read_csv('Data/dataTree2.csv')
         #csvdata = pandas.read_csv('Data/dataTree2.csv')
         x=csvdata[atributes]
         decision=csvdata['action']

Image.py

@@ -80,3 +80,25 @@ def getRandomImageFromDataBase():
     image = pygame.image.load(imgPath)
     image=pygame.transform.scale(image,(dCon.CUBE_SIZE,dCon.CUBE_SIZE))
     return image, label, imgPath
+
+def getSpedifiedImageFromDatabase(label):
+    folderPath = f"dataset/test/{label}"
+    files = os.listdir(folderPath)
+    random_image = random.choice(files)
+    imgPath = os.path.join(folderPath, random_image)
+
+    while imgPath in imagePathList:
+        for event in pygame.event.get():
+            if event.type == pygame.QUIT:
+                quit()
+        label = random.choice(neuralnetwork.labels)
+        folderPath = f"dataset/test/{label}"
+        files = os.listdir(folderPath)
+        random_image = random.choice(files)
+        imgPath = os.path.join(folderPath, random_image)
+
+    imagePathList.append(imgPath)
+
+    image = pygame.image.load(imgPath)
+    image=pygame.transform.scale(image,(dCon.CUBE_SIZE,dCon.CUBE_SIZE))
+    return image, label, imgPath

Pole.py

@@ -62,6 +62,14 @@ class Pole:
                 continue
             else:
                 self.slot_dict[coordinates].set_random_plant(nn)
+    def setPlantsByList(self, plantList):
+        pygame.display.update()
+        time.sleep(3)
+        for coordinates in self.slot_dict:
+            if(coordinates==(0,0)):
+                continue
+            else:
+                self.slot_dict[coordinates].set_specifided_plant(plantList[coordinates[1]][coordinates[0]])
 
     def change_color_of_slot(self,coordinates,color): #Coordinates must be tuple (x,y) (left top slot has cord (0,0) ), color has to be from defined in Colors.py or custom in RGB value (R,G,B)
         self.get_slot_from_cord(coordinates).color_change(color)

Slot.py

@@ -50,6 +50,11 @@ class Slot:
             self.plant=Roslina.Roslina(self.label)
         self.set_image()
     
+    def set_specifided_plant(self, plant):
+        self.plant_image, self.label, self.imagePath = self.specified_plant_dataset(plant)
+        self.plant=Roslina.Roslina(self.label)
+        self.set_image()
+
     def set_image(self):
         if self.plant_image is None:
             self.plant_image = self.image_loader.return_random_plant()
@@ -75,6 +80,8 @@ class Slot:
         return self.image_loader.return_random_plant()
     def random_plant_dataset(self):
         return Image.getRandomImageFromDataBase()
+    def specified_plant_dataset(self, plant):
+        return Image.getSpedifiedImageFromDatabase(plant)
     
     def return_plant(self):
         return self.plant

Tractor.py

@@ -30,6 +30,7 @@ class Tractor:
     DIRECTION_SOUTH = 'S'
     DIRECTION_WEST = 'W'
     DIRECTION_EAST = 'E'
+
     def __init__(self,slot,screen, osprzet,clock,bfs2_flag):
         self.tractor_images = {
             Tractor.DIRECTION_NORTH: pygame.transform.scale(pygame.image.load('images/traktorN.png'),
@@ -193,8 +194,7 @@ class Tractor:
                 self.turn_left()
         print("podlanych slotów: ", str(counter))
 
-    def snake_move_predict_plant(self, pole, model):
+    def snake_move_predict_plant(self, pole, model, headers, actions = None):
-        headers=['Coords','Real plant','Predicted plant','Result','Fertilizer']
         print(format_string_nn.format(*headers))
         initPos = (self.slot.x_axis, self.slot.y_axis)
         count = 0
@@ -207,9 +207,11 @@ class Tractor:
                     predictedLabel = nn.predictLabel(self.slot.imagePath, model)
 
                     #print(str("Coords: ({:02d}, {:02d})").format(self.slot.x_axis, self.slot.y_axis), "real:", self.slot.label, "predicted:", predictedLabel, "correct" if (self.slot.label == predictedLabel) else "incorrect", 'nawożę za pomocą:', nn.fertilizer[predictedLabel])
-                    print(format_string_nn.format(f"{self.slot.x_axis,self.slot.y_axis}",self.slot.label,predictedLabel,"correct" if (self.slot.label == predictedLabel) else "incorrect",nn.fertilizer[predictedLabel]))
+                    # print(format_string_nn.format(f"{self.slot.x_axis,self.slot.y_axis}",self.slot.label,predictedLabel,"correct" if (self.slot.label == predictedLabel) else "incorrect",nn.fertilizer[predictedLabel]))
+                    for a in actions:
+                        a(predictedLabel)
                     if self.slot.label != predictedLabel:
-                        self.slot.mark_visited()
+                        # self.slot.mark_visited()
                         count += 1
                 self.move_forward(pole, False)
             if i % 2 == 0 and i != dCon.NUM_Y - 1:
@@ -220,7 +222,19 @@ class Tractor:
                 self.turn_left()
                 self.move_forward(pole, False)
                 self.turn_left()
-        print(f"Dobrze nawiezionych roślin: {20*12-count}, źle nawiezionych roślin: {count}")
+        print(f"Dobrze rozpoznanych roślin: {20*12-count}, źle rozpoznanych roślin: {count}")
+    
+    def fertilize_slot(self, predictedLabel):
+        print(format_string_nn.format(f"{self.slot.x_axis,self.slot.y_axis}",self.slot.label,predictedLabel,"correct" if (self.slot.label == predictedLabel) else "incorrect",nn.fertilizer[predictedLabel]))
+        if self.slot.label != predictedLabel:
+            self.slot.mark_visited()
+
+    def irigate_slot_NN(self, predictedLabel):
+        attributes=self.get_attributes()
+        decision = drzewo.makeDecision(attributes)
+        print(format_string_nn.format(f"{self.slot.x_axis,self.slot.y_axis}",self.slot.label,predictedLabel,"correct" if (self.slot.label == predictedLabel) else "incorrect",decision))
+        condition.cycle()
+        self.waterLevel = random.randint(0, 100)
 
     def snake_move(self,pole,x,y):
         next_slot_coordinates=(x,y)

neuralnetwork.py

@@ -77,7 +77,7 @@ def saveModel(model, path):
 def loadModel(path):
     print("Loading model")
     model = getModel()
-    model.load_state_dict(torch.load(path))
+    model.load_state_dict(torch.load(path, map_location=torch.device('cpu'))) # musiałem tutaj dodać to ładowanie z mapowaniem na cpu bo u mnie CUDA nie działa wy pewnie możecie to usunąć
     return model
 
 def trainNewModel(n_iter=100, batch_size=256):