Merge pull request 'Algorytm_genetyczny' (#3) from Algorytm_genetyczny into master

Reviewed-on: s481865/Male_zoo#3

.idea/misc.xml

@@ -3,5 +3,5 @@
   <component name="Black">
     <option name="sdkName" value="Python 3.9" />
   </component>
-  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10 (pythonProject)" project-jdk-type="Python SDK" />
 </project>

.idea/sztuczna.iml

@@ -1,8 +1,10 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <module type="PYTHON_MODULE" version="4">
   <component name="NewModuleRootManager">
-    <content url="file://$MODULE_DIR$" />
-    <orderEntry type="inheritedJdk" />
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/.venv" />
+    </content>
+    <orderEntry type="jdk" jdkName="Python 3.10 (pythonProject)" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
 </module>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

Animals/animal.py

@@ -1,17 +1,31 @@
+import random
 import pygame
 from abc import abstractmethod
 
 class Animal:
-    def __init__(self, x, y,name, image, food_image, food, environment, adult=False,):
+
+    def choose_picture(self, name):
+        ran = random.randint(0, 1)
+        if ran == 0:
+            path = f'images/{name}.png'
+            return path
+        else:
+            path = f'images/{name}2.png'
+            return path
+
+    def __init__(self, x, y,name, image_path, food_image, food, environment, activity, ill=False, adult=False,):
         self.x = x - 1
         self.y = y - 1
         self.name = name
-        self.image = image
+        self.image_path = image_path
+        self.image = pygame.image.load(image_path)
         self.adult = adult
         self.food = food
         self.food_image = food_image
         self._feed = 0
-        self.environment = environment #hot/cold/medium
+        self.environment = environment  # hot/cold/medium
+        self.activity = activity    # diurnal/nocturnal
+        self.ill = ill
 
     def draw(self, screen, grid_size):
         if self.adult:
@@ -30,9 +44,9 @@ class Animal:
         exclamation_image = pygame.transform.scale(exclamation_image, (int(grid_size * 0.45), int(grid_size * 0.45)))
         screen.blit(exclamation_image, (x * grid_size, y * grid_size))
 
-    def draw_food(self, screen, grid_size, x, y):
+    def draw_food(self, screen, grid_size, x, y,food_image):
         scale = 0.45
-        food_image = pygame.image.load(self.food_image)
+        food_image = pygame.image.load(food_image)
 
         if(self.adult):
             y = y + 1
@@ -40,9 +54,32 @@ class Animal:
         food_image = pygame.transform.scale(food_image, (int(grid_size * scale), int(grid_size * scale)))
         screen.blit(food_image, (x * grid_size, (y + 1) * grid_size - int(grid_size * scale)))
 
-    @abstractmethod
-    def feed(self):
-        pass
+    def is_ill(self):
+        chance = random.randint(1, 100)
+        if chance >= 90:
+            return True
+        else: return False
+
+    def draw_illness(self, screen, grid_size, x, y):
+        scale = 0.45
+        illness_image = pygame.image.load('images/ill.png')
+        y = y
+
+        if self.adult:
+            x = x + 1
+            y = y
+            scale = 0.7
+
+        x_blit = x * grid_size + (grid_size - int(grid_size * scale))
+        illness_image = pygame.transform.scale(illness_image, (int(grid_size * scale), int(grid_size * scale)))
+        screen.blit(illness_image, (x_blit, y * grid_size))
+
+    def draw_snack(self, screen, grid_size, x, y):
+        exclamation_image = pygame.image.load(self.food_image)
+        exclamation_image = pygame.transform.scale(exclamation_image, (int(grid_size * 0.45), int(grid_size * 0.45)))
+        screen.blit(exclamation_image, (x * grid_size, y * grid_size))
+        pygame.display.update()
+        pygame.time.wait(700)
 
     @abstractmethod
     def getting_hungry(self):

Animals/animals.py

@@ -3,6 +3,8 @@ from giraffe import Giraffe
 from penguin import Penguin
 from parrot import Parrot
 from bear import Bear
+from owl import Owl
+from bat import Bat
 
 def create_animals():
     giraffe1 = Giraffe(0, 0, adult=True)
@@ -26,22 +28,35 @@ def create_animals():
     elephant5 = Elephant(0, 0)
     parrot1 = Parrot(0, 0)
     parrot2 = Parrot(0, 0)
-    parrot3 = Parrot(0, 0)
-    parrot4 = Parrot(0, 0)
-    parrot5 = Parrot(0, 0)
+    owl1 = Owl(0, 0)
+    owl2 = Owl(0, 0)
+    bat1 = Bat(0, 0)
+    bat2 = Bat(0, 0)
 
     Animals =  [giraffe1, giraffe2, giraffe3, giraffe4, giraffe5,
                 bear1, bear2, bear3, bear4, bear5,
                 elephant1, elephant2, elephant3, elephant4, elephant5,
                 penguin1, penguin2, penguin3, penguin4,
-                parrot1, parrot2, parrot3, parrot4, parrot5]
+                parrot1, parrot2, owl1, owl2, bat1, bat2]
 
     return Animals
 
 def draw_Animals(Animals, const):
     for Animal in Animals:
         Animal.draw(const.screen, const.GRID_SIZE)
-        if Animal.feed() == 'True':
-           Animal.draw_exclamation(const.screen, const.GRID_SIZE, Animal.x, Animal.y)
-        else: 
-            Animal.draw_food(const.screen,const.GRID_SIZE,Animal.x,Animal.y)
+        
+        hunger_level = Animal.getting_hungry(const)
+
+        if hunger_level >= 9:
+            food_image = 'images/empty_bowl.png'
+        elif hunger_level >= 8:
+            food_image = 'images/almost_empty.png'
+        elif hunger_level >= 5:
+            food_image = 'images/half_bowl.png'
+        else:
+            food_image = 'images/full_bowl.png'
+
+        Animal.draw_food(const.screen, const.GRID_SIZE, Animal.x, Animal.y, food_image)
+
+        if Animal.ill:
+            Animal.draw_illness(const.screen, const.GRID_SIZE, Animal.x, Animal.y)

Animals/bat.py

@@ -0,0 +1,26 @@
+from animal import Animal
+import pygame
+from datetime import datetime
+
+class Bat(Animal):
+    def __init__(self, x, y, adult=False):
+        name = 'bat'
+        image_path = self.choose_picture(name)
+        environment = "medium"
+        food_image = 'images/grains.png'
+        parrot_food = 'grains'
+        activity = 'nocturnal'
+        super().__init__(x, y,name, image_path, food_image,parrot_food, environment, adult)
+        self._starttime = datetime.now()
+
+    def getting_hungry(self, const):
+        checktime = datetime.now()
+        delta = checktime - self._starttime
+        minutes_passed = delta.total_seconds() / (25)
+        self._starttime = checktime
+
+        if const.IS_NIGHT and self._feed < 10:
+            self._feed += minutes_passed
+            self._feed = min(self._feed, 10)
+
+        return self._feed

Animals/bear.py

@@ -4,27 +4,24 @@ from datetime import datetime
 
 class Bear(Animal):
     def __init__(self, x, y, adult=False):
-        Bear_image = pygame.image.load('images/bear.png')
         name = 'bear'
+        image_path = self.choose_picture(name)
         environment = "cold"
+        activity = 'nocturnal'
+        ill = self.is_ill()
         bear_food = 'meat'
         food_image = 'images/meat.png'
-        super().__init__(x, y,name, Bear_image, food_image,bear_food,environment, adult)
+        super().__init__(x, y,name, image_path, food_image,bear_food,environment, activity, ill, adult)
         self._starttime = datetime.now()
 
-         
-
-    def feed(self):
-        self.getting_hungry()
-        if self._feed < 2:
-            return 'False'
-        else:
-            return 'True'
+    def getting_hungry(self, const):
         
-
-    def getting_hungry(self):
         checktime = datetime.now()
         delta = checktime - self._starttime
-        minutes_passed = delta.total_seconds() / 60
-        self._feed += minutes_passed
-        self._starttime = checktime
+        minutes_passed = delta.total_seconds() / (45)
+        self._starttime = checktime
+
+        if const.IS_NIGHT and self._feed < 10 and const.season != "winter":
+            self._feed += minutes_passed
+            self._feed = min(self._feed, 10)
+        return self._feed

Animals/elephant.py

@@ -2,13 +2,13 @@ from animal import Animal
 import pygame
 from datetime import datetime
 
-
-
 class Elephant(Animal):
     def __init__(self, x, y, adult=False):
-        Elephant_image = pygame.image.load('images/elephant.png')
         name = 'elephant'
+        image_path = self.choose_picture(name)
         environment = "hot"
+        activity = 'diurnal'
+        ill = self.is_ill()
         if adult:
             elephant_food = 'leavs'
             food_image = 'images/leaves.png'
@@ -16,22 +16,16 @@ class Elephant(Animal):
             elephant_food = 'milk'
             food_image = 'images/milk.png'
         
-        super().__init__(x, y,name, Elephant_image, food_image,elephant_food, environment, adult)
+        super().__init__(x, y,name, image_path, food_image,elephant_food, environment, activity, ill, adult)
         self._starttime = datetime.now()
-
-         
-
-    def feed(self):
-        self.getting_hungry()
-        if self._feed < 0.3:
-            return 'False'
-        else:
-            return 'True'
-        
-
-    def getting_hungry(self):
+ 
+    def getting_hungry(self, const):
         checktime = datetime.now()
         delta = checktime - self._starttime
-        minutes_passed = delta.total_seconds() / 60
-        self._feed += minutes_passed
-        self._starttime = checktime
+        minutes_passed = delta.total_seconds() / (90)
+        self._starttime = checktime
+
+        if not const.IS_NIGHT and self._feed < 10:
+            self._feed += minutes_passed
+            self._feed = min(self._feed, 10)
+        return self._feed

Animals/giraffe.py

@@ -2,31 +2,25 @@ from animal import Animal
 import pygame
 from datetime import datetime
 
-
-
 class Giraffe(Animal):
     def __init__(self, x, y, adult=False):
-        Giraffe_image = pygame.image.load('images/giraffe.png')
         name = 'giraffe'
+        image_path = self.choose_picture(name)
         environment = "hot"
+        activity = 'diurnal'
+        ill = self.is_ill()
         food_image = 'images/leaves.png'
         giraffe_food = 'leaves'
-        super().__init__(x, y,name, Giraffe_image, food_image,giraffe_food, environment, adult)
+        super().__init__(x, y, name, image_path, food_image,giraffe_food, environment, activity, ill, adult)
         self._starttime = datetime.now()
 
-         
-
-    def feed(self):
-        self.getting_hungry()
-        if self._feed < 0.8:
-            return 'False'
-        else:
-            return 'True'
-        
-
-    def getting_hungry(self):
+    def getting_hungry(self, const):
         checktime = datetime.now()
         delta = checktime - self._starttime
-        minutes_passed = delta.total_seconds() / 60
-        self._feed += minutes_passed
-        self._starttime = checktime
+        minutes_passed = delta.total_seconds() / (60)
+        self._starttime = checktime
+
+        if not const.IS_NIGHT and self._feed < 10:
+            self._feed += minutes_passed
+            self._feed = min(self._feed, 10)
+        return self._feed

Animals/owl.py

@@ -0,0 +1,26 @@
+from animal import Animal
+import pygame
+from datetime import datetime
+
+class Owl(Animal):
+    def __init__(self, x, y, adult=False):
+        name = 'owl'
+        image_path = self.choose_picture(name)
+        environment = "medium"
+        food_image = 'images/grains.png'
+        parrot_food = 'grains'
+        activity = 'nocturnal'
+        super().__init__(x, y,name, image_path, food_image,parrot_food, environment, adult)
+        self._starttime = datetime.now()
+
+    def getting_hungry(self, const):
+        checktime = datetime.now()
+        delta = checktime - self._starttime
+        minutes_passed = delta.total_seconds() / (50)
+        self._starttime = checktime
+
+        if const.IS_NIGHT and self._feed < 10:
+            self._feed += minutes_passed
+            self._feed = min(self._feed, 10)
+
+        return self._feed

Animals/parrot.py

@@ -2,31 +2,25 @@ from animal import Animal
 import pygame
 from datetime import datetime
 
-
-
 class Parrot(Animal):
     def __init__(self, x, y, adult=False):
-        Parrot_image = pygame.image.load('images/parrot.png')
         name = 'parrot'
+        image_path = self.choose_picture(name)
         environment = "medium"
+        activity = 'diurnal'
+        ill = self.is_ill()
         food_image = 'images/grains.png'
         parrot_food = 'grains'
-        super().__init__(x, y,name, Parrot_image, food_image,parrot_food, environment, adult)
+        super().__init__(x, y, name, image_path, food_image, parrot_food, environment, activity, ill, adult)
         self._starttime = datetime.now()
 
-         
-
-    def feed(self):
-        self.getting_hungry()
-        if self._feed < 1.5:
-            return 'False'
-        else:
-            return 'True'
-        
-
-    def getting_hungry(self):
+    def getting_hungry(self, const):
         checktime = datetime.now()
         delta = checktime - self._starttime
-        minutes_passed = delta.total_seconds() / 60
-        self._feed += minutes_passed
-        self._starttime = checktime
+        minutes_passed = delta.total_seconds() / (30)
+        self._starttime = checktime
+
+        if not const.IS_NIGHT and self._feed < 10:
+            self._feed += minutes_passed
+            self._feed = min(self._feed, 10)
+        return self._feed

Animals/penguin.py

@@ -2,31 +2,25 @@ from animal import Animal
 import pygame
 from datetime import datetime
 
-
-
 class Penguin(Animal):
     def __init__(self, x, y, adult=False):
-        Penguin_image = pygame.image.load('images/penguin.png')
         name = 'penguin'
+        image_path = self.choose_picture(name)
         environment = "cold"
+        activity = 'diurnal'
+        ill = self.is_ill()
         food_image = 'images/fish.png'
         penguin_food = 'fish'
-        super().__init__(x, y,name, Penguin_image, food_image,penguin_food,environment, adult)
+        super().__init__(x, y, name, image_path, food_image, penguin_food, environment, activity, ill, adult)
         self._starttime = datetime.now()
 
-         
-
-    def feed(self):
-        self.getting_hungry()
-        if self._feed < 2:
-            return 'False'
-        else:
-            return 'True'
-        
-
-    def getting_hungry(self):
+    def getting_hungry(self, const):
         checktime = datetime.now()
         delta = checktime - self._starttime
-        minutes_passed = delta.total_seconds() / 60
-        self._feed += minutes_passed
-        self._starttime = checktime
+        minutes_passed = delta.total_seconds() / (25)
+        self._starttime = checktime
+
+        if not const.IS_NIGHT and self._feed < 10:
+            self._feed += minutes_passed
+            self._feed = min(self._feed, 10)
+        return self._feed

agent.py

@@ -1,6 +1,23 @@
 import pygame
+import random
+from constants import Constants
 from state_space_search import is_border, is_obstacle
+from night import draw_night
+from decision_tree import feed_decision
+from constants import Constants
+from classification import AnimalClassifier
 
+const = Constants()
+
+classes = [
+    "bat",
+    "bear",
+    "elephant",
+    "giraffe",
+    "owl",
+    "parrot",
+    "penguin"
+]
 class Agent:
     def __init__(self, istate, image_path, grid_size):
         self.istate = istate
@@ -8,8 +25,10 @@ class Agent:
         self.grid_size = grid_size
         self.image= pygame.image.load(image_path)
         self.image = pygame.transform.scale(self.image, (grid_size, grid_size))
+        self._dryfood = 0
+        self._wetfood = 0
         
-    def draw(self, screen, grid_size):
+    def draw(self, const):
         # Obróć obrazek zgodnie z kierunkiem
         if self.direction == 'E':
             self.image= pygame.image.load('images/agent4.png')
@@ -19,19 +38,21 @@ class Agent:
             self.image= pygame.image.load('images/agent3.png')
         else:  # direction == 'N'
             self.image= pygame.image.load('images/agent2.png')
-        self.image = pygame.transform.scale(self.image, (grid_size, grid_size))
-        screen.blit(self.image, (self.x * self.grid_size, self.y * self.grid_size))
+        self.image = pygame.transform.scale(self.image, (const.GRID_SIZE, const.GRID_SIZE))
+        const.screen.blit(self.image, (self.x * self.grid_size, self.y * self.grid_size))
 
-    def handle_event(self, event, max_x, max_y, animals, obstacles):
+        if const.IS_NIGHT: draw_night(const)
+
+    def handle_event(self, event, max_x, max_y, animals, obstacles,const):
         if event.type == pygame.KEYDOWN:
             if event.key == pygame.K_UP:
-                self.move('Go Forward', max_x, max_y, obstacles, animals)
+                self.move('Go Forward', max_x, max_y, obstacles, animals,const)
             elif event.key == pygame.K_LEFT:
-                self.move('Turn Left', max_x, max_y, obstacles, animals)
+                self.move('Turn Left', max_x, max_y, obstacles, animals,const)
             elif event.key == pygame.K_RIGHT:
-                self.move('Turn Right', max_x, max_y, obstacles, animals)
+                self.move('Turn Right', max_x, max_y, obstacles, animals,const)
 
-    def move(self, action, max_x, max_y, obstacles, animals, goal):
+    def move(self, action, max_x, max_y, obstacles, animals, goal,const):
         if action == 'Go Forward':
             new_x, new_y = self.x, self.y
             if self.direction == 'N':
@@ -54,13 +75,54 @@ class Agent:
             self.direction = {'N': 'E', 'E': 'S', 'S': 'W', 'W': 'N'}[self.direction]
         
         self.istate = (self.x, self.y, self.direction) 
-        feed_animal(self, animals, goal)
+        feed_animal(self, animals, goal,const)
+        take_food(self)
 
-def feed_animal(self, animals, goal): 
+def feed_animal(self, animals, goal,const):
     goal_x, goal_y = goal
+    neuron = AnimalClassifier('./model/best_model.pth', classes)
     if self.x == goal_x and self.y == goal_y:
         for animal in animals:
             if animal.x == goal_x and animal.y == goal_y:
-                if animal.feed() == 'True':
-                    animal._feed = 0
-                    print(animal.name, "fed with", animal.food)
+                if (animal.activity == 'nocturnal' and const.IS_NIGHT) or (animal.activity == 'diurnal' and not(const.IS_NIGHT)):
+                    activity_time = True
+                else:
+                    activity_time = False
+                guests = random.randint(1, 15)
+                guess = neuron.classify(animal.image_path)
+                if guess == animal.name:
+                    print(f"I'm sure this is {guess} and i give it {animal.food} as a snack")
+                    animal.draw_snack(const.screen, const.GRID_SIZE, animal.x, animal.y)
+                else:
+                    print(f"I was wrong, this is not a {guess} but a {animal.name}")
+                decision = feed_decision(animal.adult, activity_time, animal.ill, const.season, guests, animal._feed, self._dryfood, self._wetfood)
+                if decision != [1]:
+                    if decision == [2]:
+                        if animal.getting_hungry(const=Constants()) < self._wetfood :
+                            self._wetfood -= animal._feed
+                            animal._feed = 0
+                        else:
+                            animal._feed -= self._wetfood
+                            self._wetfood = 0
+                        print(animal.name, "fed with wet food")
+                    else:
+                        if animal.getting_hungry(const=Constants()) < self._dryfood :
+                            self._dryfood -= animal._feed
+                            animal._feed = 0
+                        else:
+                            animal._feed -= self._dryfood
+                            self._dryfood = 0
+                        print(animal.name, "fed with dry food")
+                    print("Current wet food level: ", self._wetfood)
+                    print("Current dry food level: ", self._dryfood)
+                else: print(animal.name, " not fed")
+
+
+def take_food(self):
+    house_x = 3
+    house_y = 1
+    if self.x == house_x and self.y == house_y:
+        if self._dryfood < 1 or self._wetfood < 1:
+            self._dryfood = 50
+            self._wetfood = 50
+            print("Agent took food and current food level is", self._dryfood, self._wetfood)

classification.py

@@ -0,0 +1,47 @@
+import torch
+import torchvision.transforms as transforms
+import PIL.Image as Image
+
+class AnimalClassifier:
+    def __init__(self, model_path, classes, image_size=224, mean=None, std=None):
+        self.classes = classes
+        self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+        self.model = torch.load(model_path, map_location=torch.device('cpu'))
+        self.model = self.model.to(self.device)
+        self.model = self.model.eval()
+        self.image_size = image_size
+        self.mean = mean if mean is not None else [0.5164, 0.5147, 0.4746]
+        self.std = std if std is not None else [0.2180, 0.2126, 0.2172]
+        self.image_transforms = transforms.Compose([
+            transforms.Resize((self.image_size, self.image_size)),
+            transforms.ToTensor(),
+            transforms.Normalize(torch.Tensor(self.mean), torch.Tensor(self.std))
+        ])
+
+    def classify(self, image_path):
+        image = Image.open(image_path)
+
+        if image.mode == 'RGBA':
+            image = image.convert('RGB')
+
+        image = self.image_transforms(image).float()
+        image = image.unsqueeze(0).to(self.device)
+
+        with torch.no_grad():
+            output = self.model(image)
+
+        _, predicted = torch.max(output.data, 1)
+
+        return self.classes[predicted.item()]
+
+classes = [
+    "bat",
+    "bear",
+    "elephant",
+    "giraffe",
+    "owl",
+    "parrot",
+    "penguin"
+]
+
+

constants.py

@@ -1,15 +1,26 @@
+import random
 import pygame
+import time
 
 class Constants:
     def __init__(self):
         self.BLACK = (0, 0, 0)
         self.RED = (255, 0, 0)
-        self.GRID_SIZE = 50
+        self.GRID_SIZE = 65
         self.GRID_WIDTH = 30
         self.GRID_HEIGHT = 15
         self.WINDOW_SIZE = (self.GRID_WIDTH * self.GRID_SIZE, self.GRID_HEIGHT * self.GRID_SIZE)
         self.background_image = pygame.transform.scale(pygame.image.load('images/tło.jpg'), self.WINDOW_SIZE)
 
+        self.IS_NIGHT = False
+        self.TIME_CHANGE = time.time() + 60
+
+        self.season = random.choice(["spring", "summer", "autumn", "winter"])
+
+        self.SIZE = 224
+        self.mean = [0.5164, 0.5147, 0.4746]
+        self.std = [0.2180, 0.2126, 0.2172]
+
 def init_pygame(const):
     pygame.init()
     const.screen = pygame.display.set_mode(const.WINDOW_SIZE)

dane.csv

@@ -0,0 +1,313 @@
+adult,active_time,ill,season,guests,hunger,wet_food,dry_food,decision
+True,True,True,spring,12,4.0462,37.63803,5.60819,2
+True,False,False,spring,9,2.89229,34.37597,27.75948,1
+False,True,True,summer,15,2.4002,45.06447,41.50999,3
+True,False,False,summer,5,0.73248,46.1058,33.44281,1
+True,False,False,summer,12,0.62973,49.99647,41.07699,1
+True,False,False,winter,9,7.0889,46.16796,45.904,2
+False,True,False,summer,2,9.07977,22.08011,20.53507,3
+False,False,True,winter,11,3.5635,14.75823,43.46342,2
+False,False,True,winter,9,8.03113,20.6384,30.81177,2
+True,True,True,summer,0,0.01966,28.27203,3.37575,1
+False,False,False,autumn,12,8.27518,5.91931,1.10505,2
+False,False,True,summer,1,5.058,11.01892,48.04589,3
+False,True,False,winter,9,5.64777,17.19678,12.20864,1
+True,True,True,summer,0,6.86046,19.03315,47.13198,3
+True,False,True,winter,13,0.42516,12.62312,19.15853,1
+True,False,True,summer,14,4.46951,33.59537,47.343,1
+True,True,False,autumn,11,6.49386,0.64398,1.0515,1
+False,False,False,winter,10,1.9354,22.80015,26.01165,1
+True,False,False,summer,7,3.55716,1.91094,41.82462,1
+False,True,True,winter,8,9.01072,15.89341,9.10422,2
+False,True,True,spring,4,4.64513,10.39766,7.57955,2
+True,False,False,autumn,2,4.11019,45.85039,30.34183,1
+True,True,True,spring,8,7.09003,6.92577,24.77301,3
+True,True,False,spring,6,4.12955,47.91516,12.84722,1
+True,True,True,spring,10,2.70845,1.0623,42.6941,3
+True,True,True,spring,15,4.34025,6.89381,3.03923,2
+True,False,False,autumn,5,7.24464,31.34759,6.44719,1
+True,True,True,summer,6,3.8924,18.08964,18.77435,1
+False,False,True,spring,13,4.86962,48.62578,6.05301,2
+False,True,False,spring,11,1.60186,31.34926,14.41007,2
+False,True,False,autumn,2,4.19839,19.58116,28.63919,1
+False,True,True,autumn,6,1.50346,25.88282,24.97486,1
+False,True,False,spring,7,2.67431,17.05587,24.7939,1
+True,True,True,spring,7,1.72828,38.17304,24.3685,1
+False,True,True,summer,12,7.55322,26.52797,42.24754,3
+False,True,False,summer,5,8.74993,30.39317,4.5676,2
+False,True,False,summer,5,7.42862,48.73014,5.94891,2
+True,False,False,spring,4,9.3662,12.90556,41.31266,3
+False,True,False,autumn,8,4.72785,0.1623,19.48377,1
+False,False,False,winter,14,6.49349,29.52121,21.87192,1
+True,False,False,summer,14,1.57899,26.90783,33.03528,1
+False,True,False,summer,3,6.21725,3.60564,23.51978,1
+True,True,True,winter,4,4.18565,25.24209,11.02056,1
+False,False,True,autumn,8,6.5479,39.16107,4.75438,2
+False,False,False,summer,13,2.14609,39.97177,13.98651,1
+True,True,False,winter,9,7.43651,10.09353,15.70939,3
+False,False,True,autumn,5,7.85569,40.47073,49.75818,2
+True,False,True,summer,1,9.03492,23.44692,20.0026,3
+False,True,True,autumn,8,2.36724,42.81768,21.34668,2
+False,False,True,summer,15,6.8222,15.2733,15.14799,3
+True,False,True,summer,4,8.63882,41.36166,7.98981,2
+False,True,False,autumn,12,0.48943,8.67832,40.4952,1
+False,False,False,autumn,3,3.0489,14.81219,8.32707,1
+False,True,True,winter,6,0.41014,49.94757,12.61713,1
+True,False,True,winter,12,5.55017,0.98544,10.25287,1
+True,False,False,summer,11,9.92135,6.80759,48.0665,3
+False,True,True,winter,2,7.14394,11.41862,18.29288,2
+False,True,True,winter,10,1.39924,36.41807,42.95548,2
+False,True,False,summer,1,0.95193,46.53851,25.70391,1
+False,True,False,winter,4,1.44658,6.61497,31.58116,1
+False,True,False,autumn,10,7.9404,26.82316,49.5898,2
+True,False,False,spring,5,5.14951,32.36345,11.32114,1
+True,True,False,summer,5,7.55665,49.12578,29.32983,3
+True,False,True,autumn,3,3.80646,11.86722,35.43034,1
+False,False,False,winter,12,3.65822,0.14026,19.18031,1
+True,False,False,spring,8,8.58384,46.33595,11.52974,2
+True,False,False,summer,3,6.34127,22.66891,19.15813,1
+False,True,False,spring,13,7.86448,8.85557,40.03913,3
+True,True,False,spring,13,8.89316,49.89548,21.04525,2
+True,True,False,autumn,9,0.91339,36.35922,16.09576,1
+False,False,False,summer,3,7.36268,28.50462,29.52973,1
+True,True,True,spring,3,6.1319,37.71758,33.50616,1
+False,True,True,spring,0,0.77228,42.89976,19.19004,1
+True,False,True,autumn,3,7.73055,20.87865,37.18248,1
+False,False,False,summer,1,8.30392,34.47046,8.77926,2
+True,True,False,summer,8,2.96562,17.50839,23.22476,1
+True,True,True,winter,4,2.27279,20.58575,32.17293,1
+True,False,True,spring,7,6.14608,34.46015,17.22245,1
+False,False,True,winter,1,8.32044,12.09058,37.28732,3
+False,True,False,spring,14,9.56618,48.49473,46.37651,2
+True,False,True,spring,10,9.33146,47.99213,35.92519,2
+False,True,False,spring,6,0.47396,37.45415,36.87019,1
+True,False,False,summer,12,7.61463,4.36339,36.07375,3
+True,True,True,autumn,3,6.42039,4.90383,43.29857,3
+False,True,False,winter,13,6.89007,43.09184,3.04284,2
+True,False,True,winter,1,6.56604,19.04681,27.58314,2
+True,False,True,spring,3,1.96784,2.18597,34.02966,1
+False,False,False,spring,0,3.76673,1.64674,34.50649,1
+False,False,True,summer,2,0.05382,10.48896,24.03557,1
+True,False,True,spring,14,5.12387,44.44585,8.35502,3
+True,True,False,autumn,10,4.90335,43.27857,27.22901,1
+True,False,False,winter,11,5.89082,28.91495,15.58095,1
+True,False,True,autumn,3,7.39589,21.53402,44.50694,3
+True,False,True,autumn,3,7.39589,21.53402,0.00000,2
+True,False,False,summer,12,5.68671,49.18777,22.53807,3
+False,False,False,winter,0,0.86765,41.28704,33.77284,1
+False,False,True,summer,10,5.97643,36.23669,48.32615,2
+False,True,True,autumn,7,1.76947,38.34692,13.28679,1
+True,True,True,summer,13,8.63622,16.14861,44.91355,3
+True,False,False,winter,11,8.48481,37.52722,47.76888,2
+True,True,True,summer,12,7.65812,4.16785,34.57922,3
+False,False,True,winter,7,8.44897,42.99815,44.66558,2
+False,False,False,winter,7,0.53067,13.47003,18.45329,1
+False,False,False,winter,14,3.24747,9.51144,6.62824,1
+True,True,False,spring,12,5.19071,47.53107,34.68942,2
+True,False,False,summer,9,6.9442,46.79146,13.92798,2
+True,False,False,autumn,1,3.09242,18.02023,11.03004,1
+True,True,True,spring,3,0.19271,1.00203,1.16671,1
+False,True,True,winter,5,9.00758,37.95091,11.54697,2
+True,False,True,spring,9,6.11904,37.42698,4.82627,2
+False,False,True,autumn,9,6.29507,22.99044,15.46992,2
+False,False,False,winter,13,5.4099,11.75134,6.91861,1
+False,False,False,winter,5,9.92035,21.82547,10.2415,2
+False,True,False,winter,10,6.06913,1.46795,12.76663,1
+True,False,True,spring,5,8.1218,37.03643,32.04156,3
+True,False,False,autumn,11,0.48844,39.36689,0.03464,1
+False,True,True,summer,6,1.72816,26.85829,16.53262,1
+False,False,False,spring,5,6.04025,29.55673,18.85232,2
+False,True,True,winter,2,1.75157,0.6601,49.91163,1
+False,True,True,winter,9,6.75125,15.22221,6.72688,2
+False,True,True,autumn,9,6.72535,24.07403,33.94074,2
+False,False,False,winter,14,0.02843,48.49973,15.81701,1
+False,False,True,autumn,15,1.07944,45.94025,4.05257,1
+False,False,True,winter,12,7.26288,15.82501,22.56163,2
+True,True,True,winter,11,8.50892,23.89966,46.14267,3
+True,False,True,autumn,11,8.10923,24.31448,6.70919,2
+True,True,False,summer,11,4.65313,3.44791,3.96313,3
+True,False,True,summer,2,2.56716,10.85536,49.88738,1
+False,False,True,autumn,4,8.19265,5.43942,48.74041,3
+False,True,False,autumn,5,5.6574,9.75738,25.96888,3
+False,True,False,autumn,5,5.6574,9.75738,0.00000,2
+False,True,False,winter,14,4.87066,33.40134,18.98246,2
+True,True,True,winter,6,8.2623,37.47298,33.76759,2
+True,True,True,spring,10,2.20409,13.6178,5.80078,2
+True,False,True,autumn,7,9.06057,37.8724,23.62209,2
+False,False,True,autumn,3,6.69861,37.07336,16.87187,2
+False,False,True,autumn,3,6.69861,0.00000,16.87187,3
+True,False,True,autumn,13,4.96475,46.87852,3.1412,1
+True,False,True,autumn,9,2.65212,19.06994,37.33364,1
+True,True,False,summer,15,3.47148,35.84529,0.00000,1
+False,True,True,summer,8,1.51025,9.44246,19.05913,1
+False,False,True,autumn,6,6.48485,45.61986,15.91179,2
+False,False,False,spring,2,8.98075,39.32941,42.47669,2
+False,True,True,winter,5,8.37177,12.99299,42.31566,3
+True,True,True,autumn,6,3.38746,48.86975,49.62605,1
+False,True,True,summer,7,7.09358,22.83074,38.5172,2
+False,False,True,spring,9,1.00148,11.16064,0.52706,1
+False,False,True,winter,1,6.08476,37.67744,4.49812,2
+False,True,False,spring,5,4.5182,32.48803,33.44274,1
+True,True,True,summer,8,6.11265,30.32015,46.47287,3
+False,True,True,winter,4,8.50937,22.72015,0.00000,2
+True,False,True,summer,4,7.23924,39.09963,42.82872,3
+False,False,True,summer,5,1.28353,7.18667,38.93923,1
+False,True,False,spring,3,4.50329,22.95269,0.41795,1
+True,True,True,summer,1,0.47824,14.79432,24.64273,1
+False,True,False,spring,10,8.43205,19.1333,20.95803,2
+False,True,False,spring,6,9.94659,18.83814,39.26147,2
+False,True,False,spring,3,3.68802,1.58951,26.4255,1
+False,False,True,autumn,8,4.79336,22.56564,4.95207,2
+False,True,True,spring,10,1.63541,0.00000,31.82704,1
+False,True,False,spring,2,1.2274,47.87731,32.98744,1
+True,True,False,winter,11,7.31457,26.08142,16.5835,2
+False,True,True,summer,2,4.90627,19.73976,49.56272,3
+True,True,False,winter,8,3.02707,35.9547,29.52088,1
+True,True,True,summer,7,5.02577,5.37674,16.61368,3
+False,False,True,spring,8,9.58805,8.12549,0.00000,2
+False,True,True,summer,6,2.08786,37.11126,36.15777,3
+True,True,False,spring,7,8.11839,12.2032,8.26737,2
+True,False,True,summer,7,4.08923,20.77025,11.25944,1
+False,False,True,winter,4,4.85557,0.00000,39.4493,2
+False,False,False,summer,14,9.12718,41.84025,49.51895,2
+True,True,True,summer,15,9.4014,34.10345,26.84361,3
+False,True,False,spring,14,8.61728,28.58017,39.3705,2
+False,True,False,winter,8,7.12808,12.04193,43.86622,2
+True,False,True,winter,1,9.50102,43.46168,28.81571,2
+True,True,False,spring,5,1.35366,6.95688,33.37058,1
+False,False,True,autumn,11,7.61014,11.10761,41.58039,2
+False,True,True,summer,2,6.86814,37.72905,14.64706,3
+True,False,False,winter,1,8.12812,22.55081,9.43532,2
+True,True,True,winter,10,4.18282,27.82423,30.42216,1
+False,False,False,summer,7,2.52646,3.74242,10.61286,1
+False,False,True,spring,13,3.15065,19.01632,34.56097,2
+True,True,False,summer,3,0.18108,46.67684,46.76693,1
+True,True,True,spring,0,1.50217,5.27541,16.18378,1
+False,True,True,summer,5,3.71758,11.15496,12.57224,3
+False,True,False,summer,6,9.92613,8.59078,21.32207,3
+True,False,False,winter,11,0.1261,2.42716,17.23296,1
+True,False,True,summer,14,6.90049,10.76539,3.92394,3
+False,True,True,autumn,15,1.76164,35.60051,2.5168,2
+False,False,True,spring,11,2.39225,36.14198,9.13906,3
+True,True,False,summer,2,4.04026,0.00000,12.47216,1
+True,True,False,spring,13,3.32803,7.59913,1.89442,3
+True,False,True,spring,1,5.15927,44.02139,4.03454,1
+True,True,True,autumn,13,5.52565,7.75133,38.62709,3
+True,True,False,spring,3,8.44216,30.01593,12.45777,3
+False,False,True,summer,13,2.88557,5.18905,5.87065,3
+True,True,True,spring,11,2.45261,7.22671,49.68806,3
+True,True,True,winter,4,8.55814,3.29899,32.82852,2
+False,False,True,summer,4,9.85169,47.62867,17.3155,3
+False,False,True,winter,2,5.30151,26.50068,48.79306,2
+False,False,False,autumn,9,7.59806,0.00000,36.92142,2
+False,True,True,autumn,1,9.28424,17.58014,28.42461,2
+True,False,True,summer,14,7.82306,35.29264,46.36975,3
+False,False,True,winter,2,1.10909,46.37088,40.88245,1
+True,True,False,summer,1,7.71442,43.2301,27.42849,3
+False,True,True,summer,6,1.21255,3.7357,4.31858,1
+True,True,True,winter,8,9.53076,12.54774,17.63524,2
+True,True,True,autumn,3,8.47955,19.04656,3.62988,2
+True,False,True,winter,3,2.58264,28.29242,0.00000,1
+True,False,False,autumn,5,6.83145,0.00000,15.88102,1
+True,False,False,summer,10,3.24742,16.50963,26.24036,1
+False,False,False,summer,8,8.66174,49.55046,33.2433,2
+True,False,True,winter,7,1.40722,4.06585,2.57929,1
+False,True,False,winter,12,4.483,2.42211,20.55941,2
+False,False,True,spring,12,2.98512,30.55243,5.53733,3
+False,False,True,autumn,6,0.84086,33.57311,32.42908,1
+False,True,True,winter,12,1.07916,8.27438,7.9284,1
+False,False,True,spring,12,3.17402,46.59657,14.21739,3
+False,True,True,winter,11,7.09559,14.18261,43.41709,2
+False,False,True,autumn,3,0.53006,21.37664,17.14295,1
+False,False,False,autumn,14,4.67143,4.11788,0.04226,1
+True,False,True,winter,12,3.48493,35.24303,0.00000,1
+True,True,True,spring,9,5.1789,0.97673,8.31413,2
+False,False,False,spring,5,1.50319,28.57762,27.80054,1
+True,True,True,autumn,10,9.23444,43.51842,19.90954,2
+False,False,False,autumn,9,3.84582,40.34953,9.01663,1
+True,True,False,winter,5,3.90587,32.97826,0.67046,1
+True,True,True,autumn,2,9.19994,0.00000,34.36662,3
+False,True,True,summer,6,5.614,29.08038,0.00000,2
+True,True,True,autumn,2,2.15339,6.36751,6.45082,1
+True,False,True,spring,1,9.19416,32.05433,8.27667,2
+True,False,True,autumn,0,8.12282,48.68677,8.38304,2
+False,True,True,spring,12,3.26729,29.61584,1.69993,2
+True,False,True,summer,8,1.99886,31.26437,3.51834,1
+False,False,True,summer,7,7.41314,44.88982,34.46453,2
+True,False,True,summer,0,7.24464,8.85289,34.29828,3
+False,True,False,summer,8,2.38628,21.76861,47.20283,3
+True,True,True,autumn,3,7.12112,12.08359,41.06062,3
+True,False,False,winter,5,6.74504,47.09367,1.97357,2
+False,False,False,summer,8,1.23539,35.47945,7.67276,1
+True,False,False,spring,11,7.91742,34.52557,30.96412,3
+False,True,True,winter,14,5.91181,7.53226,16.37669,3
+False,True,True,spring,13,6.07261,47.43572,15.83885,2
+True,True,True,autumn,2,9.22518,31.25996,28.06488,3
+False,True,True,summer,3,8.47609,0.23934,31.25786,3
+False,True,False,autumn,6,0.97126,13.65648,25.59887,1
+True,False,False,spring,14,9.29029,46.83676,12.58912,2
+False,False,False,winter,14,0.14092,4.6673,20.3859,1
+True,False,True,autumn,2,3.52708,37.61372,32.83573,1
+True,True,True,winter,1,4.37134,43.19138,22.04785,1
+True,False,True,summer,9,1.1614,10.9739,42.3009,1
+False,False,False,winter,9,7.27324,29.74731,47.17759,2
+False,True,True,winter,9,3.17153,35.14715,21.37868,2
+False,True,False,autumn,0,2.37863,20.35733,46.96943,1
+False,False,True,autumn,4,0.70656,8.70201,5.26527,1
+True,True,True,winter,1,8.23562,36.01552,25.03969,2
+True,True,False,winter,3,6.65062,6.75622,24.91086,3
+False,False,False,spring,10,2.30179,19.62758,25.57147,1
+True,True,False,autumn,10,6.60812,6.61336,12.39931,3
+False,False,True,summer,3,8.9948,47.39225,18.11157,2
+True,False,True,autumn,5,6.69302,42.62701,13.01677,2
+False,False,False,spring,14,8.53868,33.42545,2.43572,2
+False,True,True,autumn,10,4.46205,10.37542,39.58137,3
+True,True,False,spring,14,5.34262,15.45545,21.48404,3
+True,False,False,winter,9,7.02885,4.88308,27.56619,3
+False,False,False,autumn,13,3.55279,0.17091,5.43831,1
+True,True,True,autumn,1,9.98637,27.57982,15.82173,2
+False,True,True,summer,9,8.25408,13.10493,27.07596,3
+False,False,False,spring,15,1.9089,33.25115,44.57492,1
+True,False,False,autumn,12,6.65534,38.00972,20.31047,2
+False,True,True,autumn,1,0.01592,6.24929,15.51308,1
+False,True,True,winter,13,1.24017,36.88006,16.50894,1
+False,True,True,winter,13,6.1878,15.18876,9.02381,2
+True,True,True,winter,5,5.45157,13.27868,39.39805,2
+True,False,True,spring,5,2.82881,28.62319,24.03077,1
+False,False,True,spring,2,4.8246,41.45269,48.89539,2
+True,False,False,spring,8,9.3343,39.02018,45.01066,3
+True,True,True,autumn,4,1.8456,2.94366,37.44996,1
+False,True,True,summer,14,0.95333,4.57964,26.37633,1
+False,False,True,autumn,13,9.84087,24.03819,41.72097,2
+True,False,False,autumn,9,3.70617,32.70115,1.69105,1
+True,True,True,spring,12,6.77783,6.67976,20.46179,3
+False,False,True,summer,15,7.15829,31.24546,10.37666,3
+False,True,True,summer,1,2.28393,18.13299,34.38756,3
+True,False,True,autumn,7,3.96302,39.84093,47.0172,1
+True,False,False,summer,1,0.65085,20.20581,14.96995,1
+True,False,False,winter,2,9.24331,26.34543,30.5147,2
+True,False,False,summer,3,2.86309,15.56342,1.04324,1
+True,True,True,autumn,8,5.71809,24.41045,48.78273,2
+True,True,True,autumn,8,5.71809,24.41045,48.78273,2
+True,True,True,winter,8,5.71809,0.99999,48.78273,3
+True,True,True,winter,8,5.71809,1.98675,48.79993,3
+True,True,False,winter,8,7.71809,1.02345,38.78273,3
+True,False,False,summer,1,4.03947,33.84073,6.48891,1
+True,False,False,winter,4,2.46471,24.07929,17.77792,1
+False,False,False,winter,9,3.66415,23.68306,24.43865,1
+True,True,True,autumn,8,5.71809,24.41045,48.78273,2
+False,True,True,spring,3,5.3009,34.83862,6.75862,2
+True,False,True,winter,8,6.23275,8.1183,19.6922,3
+False,True,True,autumn,2,4.21016,11.24334,34.98395,3
+True,True,False,autumn,0,2.79424,13.25106,5.69617,1
+True,True,False,winter,15,2.43843,14.61703,49.57393,2
+True,True,True,summer,8,2.28654,20.9895,5.64007,1
+False,False,False,autumn,1,2.5607,26.85209,47.10784,1
+True,True,True,winter,14,1.56638,18.02703,7.05011,1
+False,False,False,winter,13,3.86632,28.9884,20.1928,1
+True,False,False,summer,13,6.37654,34.3833,34.53892,3
+True,False,False,summer,13,6.37654,34.3833,34.53892,3
+True,False,False,spring,11,8.35634,0.00000,34.53892,3
+True,False,True,summer,13,9.37654,34.3833,0.00000,2
+True,False,False,winter,13,7.77754,34.3833,0.00000,2
+True,True,True,summer,5,8.10422,7.6617,23.41017,3

decision_tree.py

@@ -0,0 +1,48 @@
+import pandas as pd
+from sklearn.tree import DecisionTreeClassifier, plot_tree
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import accuracy_score
+import matplotlib.pyplot as plt
+headers = ['adult','active_time','ill','season','guests','hunger','wet_food','dry_food']
+# Wczytanie danych
+data = pd.read_csv('dane.csv', header=0) 
+X = data[headers]
+Y = data['decision']
+X = pd.get_dummies(data=X, columns=['season'])
+clf = DecisionTreeClassifier(max_depth=6)
+X1, X2, Y1, Y2 = train_test_split(X, Y, train_size=0.8)
+clf = clf.fit(X1, Y1)
+pred = clf.predict(X2)
+accuracy = accuracy_score(Y2, pred)
+print("Dokładność:", accuracy)
+
+
+
+#zapisanie drzewa do pliku
+plt.figure(figsize=(50,30))  
+plot_tree(clf, filled=True, feature_names=X.columns.tolist(), class_names=['nie karmi', 'karmi mokrą karmą', 'karmi suchą karmą']) 
+plt.savefig('tree.png')
+# dane do decyzji
+def feed_decision(adult,active_time,ill,season,guests,hunger,dry_food,wet_food):
+
+    X_new = pd.DataFrame({
+        'adult': [adult],
+        'active_time': [active_time],
+        'ill': [ill],
+        'season': [season],
+        'guests':[guests],
+        'hunger': [hunger],      
+        'wet_food': [wet_food],    
+        'dry_food': [dry_food]      
+})
+    X_new = pd.get_dummies(X_new)
+    missing_columns = set(X.columns) - set(X_new)
+    for col in missing_columns:
+        X_new[col] = False
+        X_new = X_new.reindex(columns=X.columns, fill_value=0)
+    print("Atrybuty zwierzęcia:", adult,active_time,ill,season,guests,hunger,wet_food,dry_food)
+    return (clf.predict(X_new))
+
+
+
+

draw.py

@@ -11,4 +11,12 @@ def draw_grid(const):
     for y in range(0, const.GRID_HEIGHT * const.GRID_SIZE, const.GRID_SIZE):
         for x in range(0, const.GRID_WIDTH * const.GRID_SIZE, const.GRID_SIZE):
             rect = pygame.Rect(x, y, const.GRID_SIZE, const.GRID_SIZE)
-            pygame.draw.rect(const.screen, const.BLACK, rect, 1)
+            pygame.draw.rect(const.screen, const.BLACK, rect, 1)
+
+def draw_house(const):
+    X = 2
+    Y = 0
+    image_path = 'images/house.png'
+    image_surface = pygame.image.load(image_path)  # Wczytanie obrazka do obiektu Surface
+    scaled_image = pygame.transform.scale(image_surface, (const.GRID_SIZE * 2, const.GRID_SIZE * 2))
+    const.screen.blit(scaled_image, (X * const.GRID_SIZE, Y * const.GRID_SIZE))

enclosure.py

@@ -1,6 +1,5 @@
 import pygame
 
-
 class Enclosure:
     def __init__(self, x1, y1, x2, y2, gate1, gate2, type, imageH, imageV, imageGate):
         self.x1 = x1 - 1
@@ -15,6 +14,7 @@ class Enclosure:
         self.imageH = imageH
         self.imageV = imageV
         self.imageGate = imageGate
+        self.animals = set()
 
     def gatebuild(self, screen, grid_size):
         self.imageGate = pygame.transform.scale(self.imageGate, (grid_size, grid_size))
@@ -56,10 +56,10 @@ def create_enclosures():
     gate = pygame.image.load('images/gate.png')
 
     en1 = Enclosure(0, 5, 9, 11, (9, 6), (4, 11), "hot", fenceH, fenceV, gate)  # Lewa klatka
-    en2 = Enclosure(13, 0, 29, 3, (16, 3), (27, 3), 'medium', fenceH, fenceV, gate)  # Górna klatka
-    en3 = Enclosure(11, 5, 16, 11, (12, 5), (16, 8), 'cold', fenceH, fenceV, gate)  # Środkowa klatka
-    en4 = Enclosure(19, 5, 31, 11, (23, 5), (25, 11), 'hot', fenceH, fenceV, gate)  # Prawa klatka
-    en5 = Enclosure(4, 13, 28, 16, (12, 13), (20, 13), 'cold', fenceH, fenceV, gate)  # Dolna klatka
+    en2 = Enclosure(4, 13, 28, 16, (12, 13), (20, 13), 'cold', fenceH, fenceV, gate)  # Dolna klatka
+    en3 = Enclosure(19, 5, 31, 11, (23, 5), (25, 11), 'hot', fenceH, fenceV, gate)  # Prawa klatka
+    en4 = Enclosure(11, 5, 16, 11, (12, 5), (16, 8), 'cold', fenceH, fenceV, gate)  # Środkowa klatka
+    en5 = Enclosure(13, 0, 29, 3, (16, 3), (27, 3), 'medium', fenceH, fenceV, gate)  # Górna klatka
 
     Enclosures = [en1, en2, en3, en4, en5]
 

genetics.py

@@ -0,0 +1,148 @@
+from state_space_search import graphsearch, generate_cost_map
+import random
+
+# Parametry algorytmu genetycznego
+POPULATION_SIZE = 700
+MUTATION_RATE = 0.01
+NUM_GENERATIONS = 600
+
+# Generowanie początkowej populacji
+def generate_individual(animals):
+    return random.sample(animals, len(animals))
+
+def generate_population(animals, size):
+    return [generate_individual(animals) for _ in range(size)]
+
+# Obliczanie odległości między zwierzetami
+def calculate_distance(animal1, animal2):
+    x1, y1 = animal1
+    x2, y2 = animal2
+    return abs(x1 - x2) + abs(y1 - y2) # Odległość Manhattana
+
+def calculate_total_distance(animals):
+    total_distance = 0
+    for i in range(len(animals) - 1):
+        total_distance += calculate_distance(animals[i], animals[i+1])
+    total_distance += calculate_distance(animals[-1], animals[0])  # Zamknięcie cyklu
+    return total_distance
+
+# Selekcja rodziców za pomocą metody ruletki
+def select_parents(population, num_parents):
+    fitness_scores = [1 / calculate_total_distance(individual) for individual in population]
+    total_fitness = sum(fitness_scores)
+    selection_probs = [fitness / total_fitness for fitness in fitness_scores]
+
+    parents = random.choices(population, weights=selection_probs, k=num_parents)
+    return parents
+
+# Krzyżowanie rodziców (OX,Davis)
+def crossover(parent1, parent2):
+    child1 = [None] * len(parent1)
+    child2 = [None] * len(parent1)
+    start_index = random.randint(0, len(parent1) - 1)
+    end_index = random.randint(start_index, len(parent1) - 1)
+    child1[start_index:end_index+1] = parent1[start_index:end_index+1]
+    child2[start_index:end_index+1] = parent2[start_index:end_index+1]
+
+    # Uzupełnienie brakujących zwierząt z drugiego rodzica
+    for i in range(len(parent1)):
+        if parent2[i] not in child1:
+            for j in range(len(parent2)):
+                if child1[j] is None:
+                    child1[j] = parent2[i]
+                    break
+
+    for i in range(len(parent1)):
+        if parent1[i] not in child2:
+            for j in range(len(parent1)):
+                if child2[j] is None:
+                    child2[j] = parent1[i]
+                    break
+
+    return child1, child2
+
+# Mutacja: zamiana dwóch losowych zwierząt z prawdopodobieństwem MUTATION_RATE
+def mutate(individual):
+    if random.random() < MUTATION_RATE:
+        index1, index2 = random.sample(range(len(individual)), 2)
+        individual[index1], individual[index2] = individual[index2], individual[index1]
+
+# Algorytm genetyczny
+def genetic_algorithm(animals):
+    population = generate_population(animals, POPULATION_SIZE)
+
+    for generation in range(NUM_GENERATIONS):
+        # Selekcja rodziców
+        parents = select_parents(population, POPULATION_SIZE // 2)
+
+        # Krzyżowanie i tworzenie nowej populacji
+        next_generation = []
+        for i in range(0, len(parents), 2):
+            parent1 = parents[i]
+            if i + 1 < len(parents):
+                parent2 = parents[i + 1]
+            else:
+                parent2 = parents[0]
+            child1, child2 = crossover(parent1, parent2)
+            next_generation.extend([child1, child2])
+
+        # Mutacja nowej populacji
+        for individual in next_generation:
+            mutate(individual)
+
+        # Zastąpienie starej populacji nową
+        population = next_generation
+
+    # Znalezienie najlepszego osobnika
+    best_individual = min(population, key=calculate_total_distance)
+
+    return best_individual
+
+# def calculate_distance(start, goal, max_x, max_y, obstacles, cost_map):
+#     istate = (start[0], start[1], 'N')  # Zakładamy, że zaczynamy od kierunku północnego
+#     actions, cost = graphsearch(istate, goal, max_x, max_y, obstacles, cost_map)
+#     return cost
+
+# def calculate_total_distance(animals, max_x, max_y, obstacles, cost_map):
+#     total_distance = 0
+#     for i in range(len(animals) - 1):
+#         total_distance += calculate_distance(animals[i], animals[i+1], max_x, max_y, obstacles, cost_map)
+#     total_distance += calculate_distance(animals[-1], animals[0], max_x, max_y, obstacles, cost_map)  # Zamknięcie cyklu
+#     return total_distance
+
+# # Selekcja rodziców za pomocą metody ruletki
+# def select_parents(population, num_parents, max_x, max_y, obstacles, cost_map):
+#     fitness_scores = [1 / calculate_total_distance(individual, max_x, max_y, obstacles, cost_map) for individual in population]
+#     total_fitness = sum(fitness_scores)
+#     selection_probs = [fitness / total_fitness for fitness in fitness_scores]
+
+#     parents = random.choices(population, weights=selection_probs, k=num_parents)
+#     return parents
+
+
+# def genetic_algorithm(animals, max_x, max_y, obstacles, cost_map):
+#     population = generate_population(animals, POPULATION_SIZE)
+
+#     for generation in range(NUM_GENERATIONS):
+#         # Selekcja rodziców
+#         parents = select_parents(population, POPULATION_SIZE // 2, max_x, max_y, obstacles, cost_map)
+
+#         # Krzyżowanie i tworzenie nowej populacji
+#         next_generation = []
+#         for i in range(0, len(parents), 2):
+#             parent1 = parents[i]
+#             parent2 = parents[i + 1]
+#             child1, child2 = crossover(parent1, parent2)
+#             next_generation.extend([child1, child2])
+
+#         # Mutacja nowej populacji
+#         for individual in next_generation:
+#             mutate(individual)
+
+#         # Zastąpienie starej populacji nową
+#         population = next_generation
+
+#     # Znalezienie najlepszego osobnika
+#     best_individual = min(population, key=lambda individual: calculate_total_distance(individual, max_x, max_y, obstacles, cost_map))
+
+#     return best_individual 

main.py

@@ -1,7 +1,7 @@
 import random
 import pygame
 import sys
-import sys
+
 sys.path.append('./Animals')
 from animals import create_animals, draw_Animals
 from agent import Agent
@@ -10,7 +10,10 @@ from spawner import Spawner
 from state_space_search import graphsearch, generate_cost_map
 from terrain_obstacle import create_obstacles, draw_Terrain_Obstacles
 from constants import Constants, init_pygame
-from draw import draw_goal, draw_grid
+from draw import draw_goal, draw_grid, draw_house
+from season import draw_background
+from night import change_time
+from genetics import genetic_algorithm
 
 const = Constants()
 init_pygame(const)
@@ -75,42 +78,81 @@ def main():
     actions = []
     clock = pygame.time.Clock()
     spawned = False
+    route = False
+
+    # # Lista zawierająca klatki do odwiedzenia
+    # enclosures_to_visit = Enclosures.copy()
+    # current_enclosure_index = -1  # Indeks bieżącej klatki
+    # actions_to_compare_list = []  # Lista zawierająca ścieżki do porównania
+    # goals_to_compare_list = list()  # Lista zawierająca cele do porównania
 
     while True:
         for event in pygame.event.get():
             if event.type == pygame.QUIT:
                 pygame.quit()
                 sys.exit()
-            agent.handle_event(event, const.GRID_WIDTH, const.GRID_HEIGHT, Animals, obstacles)
+            agent.handle_event(event, const.GRID_WIDTH, const.GRID_HEIGHT, Animals, obstacles,const)
 
-        const.screen.blit(const.background_image, (0, 0))
-        draw_grid(const)
+        change_time(const)
+        draw_background(const)
         draw_enclosures(Enclosures, const)
         draw_gates(Enclosures, const)
-
+        draw_house(const)
+  
         if not spawned:
             spawn_all_animals()
             spawn_obstacles()
             cost_map = generate_cost_map(Animals, Terrain_Obstacles)
             for animal in Animals:
-                animal._feed = 2  # Ustawienie, aby zwierzę było głodne
+                # animal._feed = 0
+                animal._feed = random.randint(0, 10)
             spawned = True
+        
+        if not route:
+            animals = [(animal.x, animal.y) for animal in Animals]
+            best_route = genetic_algorithm(animals)
+            route = True
             
         draw_Animals(Animals, const)
         draw_Terrain_Obstacles(Terrain_Obstacles, const)
-        agent.draw(const.screen, const.GRID_SIZE)
+        agent.draw(const)
         pygame.display.flip()
         clock.tick(10)
 
         if actions:
             action = actions.pop(0)
-            agent.move(action, const.GRID_WIDTH, const.GRID_HEIGHT, obstacles, Animals, goal)
+            agent.move(action, const.GRID_WIDTH, const.GRID_HEIGHT, obstacles, Animals, goal,const)
             pygame.time.wait(200)
         else:
-            animal = random.choice(Animals)
-            goal = (animal.x, animal.y)
-            draw_goal(const, goal)
-            actions = graphsearch(agent.istate, goal, const.GRID_WIDTH, const.GRID_HEIGHT, obstacles, cost_map)
+            if agent._dryfood > 1 and agent._wetfood > 1 : 
+                # if not goals_to_compare_list:
+                #     current_enclosure_index = (current_enclosure_index + 1) % len(enclosures_to_visit)
+                #     current_enclosure = enclosures_to_visit[current_enclosure_index] 
+
+                #     for animal in current_enclosure.animals:
+                #         goal = (animal.x, animal.y)
+                #         goals_to_compare_list.append(goal)
+
+                #         actions_to_compare = graphsearch(agent.istate, goal, const.GRID_WIDTH, const.GRID_HEIGHT, obstacles, cost_map)    
+                #         actions_to_compare_list.append((actions_to_compare, goal))
+
+                # chosen_path_and_goal = min(actions_to_compare_list, key=lambda x: len(x[0]))
+                # goal = chosen_path_and_goal[1]  
+                # draw_goal(const, goal)
+
+                # # Usuń wybrany element z listy
+                # actions_to_compare_list.remove(chosen_path_and_goal)
+                # goals_to_compare_list.remove(goal)
+                goal = best_route.pop(0)
+                best_route.append(goal)
+                draw_goal(const, goal)
+
+                actions, cost = graphsearch(agent.istate, goal, const.GRID_WIDTH, const.GRID_HEIGHT, obstacles, cost_map)
+
+            else:
+                goal = (3,1)
+                draw_goal(const, goal)
+                actions, cost = graphsearch(agent.istate, goal, const.GRID_WIDTH, const.GRID_HEIGHT, obstacles, cost_map)
 
 if __name__ == "__main__":
     main()

model/model.py

@@ -0,0 +1,129 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+import torchvision.datasets
+from torchvision import datasets, transforms, models
+from torch.utils.data import DataLoader
+
+
+def set_device():
+    if torch.cuda.is_available():
+        device = 'cuda'
+    else:
+        device = 'cpu'
+    return torch.device(device)
+
+
+train_dataset_path = './data/train'
+test_dataset_path = './data/val'
+number_of_classes = 7
+
+SIZE = 224
+mean = [0.5164, 0.5147, 0.4746]
+std = [0.2180, 0.2126, 0.2172]
+
+train_transforms = transforms.Compose([
+    transforms.Resize((SIZE, SIZE)),
+    transforms.RandomHorizontalFlip(),
+    transforms.RandomRotation(10),
+    transforms.ToTensor(),
+    transforms.Normalize(torch.Tensor(mean), torch.Tensor(std))
+])
+
+test_transforms = transforms.Compose([
+    transforms.Resize((SIZE, SIZE)),
+    transforms.ToTensor(),
+    transforms.Normalize(torch.Tensor(mean), torch.Tensor(std))
+])
+
+train_dataset = torchvision.datasets.ImageFolder(root=train_dataset_path, transform=train_transforms)
+test_dataset = torchvision.datasets.ImageFolder(root=test_dataset_path, transform=test_transforms)
+
+train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=64, shuffle=True)
+test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=64, shuffle=False)
+
+resnet18_model = models.resnet18(weights=None)
+num_ftrs = resnet18_model.fc.in_features
+resnet18_model.fc = nn.Linear(num_ftrs, number_of_classes)
+device = set_device()
+resnet18_model = resnet18_model.to(device)
+loss_fn = nn.CrossEntropyLoss()
+
+optimizer = optim.SGD(resnet18_model.parameters(), lr=0.001, momentum=0.9, weight_decay=0.003)
+
+
+def save_checkpoint(model, epoch, optimizer, best_acc):
+    state = {
+        'epoch': epoch + 1,
+        'model': model.state_dict(),
+        'best accuracy': best_acc,
+        'optimizer': optimizer.state_dict()
+    }
+    torch.save(state, 'model_best_checkpoint.pth.tar')
+def train_nn(model, train_loader, test_loader, criterion, optimizer, n_epochs):
+    device = set_device()
+    best_acc = 0
+
+    for epoch in range(n_epochs):
+        print("Epoch number %d " % (epoch + 1))
+        model.train()
+        running_loss = 0.0
+        running_correct = 0.0
+        total = 0
+
+        for data in train_loader:
+            images, labels = data
+            images = images.to(device)
+            labels = labels.to(device)
+            total += labels.size(0)
+
+            optimizer.zero_grad()
+            outputs = model(images)
+            _, predicted = torch.max(outputs.data, 1)
+            loss = criterion(outputs, labels)
+            loss.backward()
+            optimizer.step()
+
+            running_loss += loss.item()
+            running_correct += (labels == predicted).sum().item()
+
+        epoch_loss = running_loss/len(train_loader)
+        epoch_acc = 100 * running_correct / total
+        print(f"Training dataset. Got {running_correct} out of {total} images correctly ({epoch_acc}). Epoch loss: {epoch_loss}")
+
+        test_data_acc = evaluate_model_on_test_set(model, test_loader)
+
+        if test_data_acc > best_acc:
+            best_acc = test_data_acc
+            save_checkpoint(model, epoch, optimizer, best_acc)
+
+    print("Finished")
+    return model
+def evaluate_model_on_test_set(model, test_loader):
+    model.eval()
+    predicted_correctly_on_epoch = 0
+    total = 0
+    device = set_device()
+
+    with torch.no_grad():
+        for data in test_loader:
+            images, labels = data
+            images = images.to(device)
+            labels = labels.to(device)
+            total += labels.size(0)
+
+            outputs = model(images)
+            _, predicted = torch.max(outputs.data, 1)
+
+            predicted_correctly_on_epoch += (predicted == labels).sum().item()
+
+    epoch_acc = 100 * predicted_correctly_on_epoch / total
+    print(f"Testing dataset. Got {predicted_correctly_on_epoch} out of {total} images correctly ({epoch_acc})")
+    return epoch_acc
+
+
+train_nn(resnet18_model, train_loader, test_loader, loss_fn, optimizer, n_epochs=30)
+
+checkpoint = torch.load('model_best_checkpoint.pth.tar')
+resnet18_model.load_state_dict(checkpoint['model'])
+torch.save(resnet18_model, 'best_model.pth')

night.py

@@ -0,0 +1,19 @@
+import time
+import pygame
+
+DAY_LENGTH = 90  # Długość dnia w sekundach
+
+def draw_night(const):
+    overlay = pygame.Surface(const.WINDOW_SIZE)
+    overlay.fill((0, 0, 0))
+    overlay.set_alpha(128)  # Ustawienie przezroczystości (0 - całkowicie przeźroczyste, 255 - nieprzeźroczyste)
+    const.screen.blit(overlay, (0, 0))
+
+def change_time(const):
+    current_time = time.time()
+
+    # Sprawdzamy, czy nadszedł czas zmiany pory dnia
+    if current_time >= const.TIME_CHANGE:
+        # Zmieniamy porę dnia
+        const.IS_NIGHT = not const.IS_NIGHT  # Jeśli było dzień, teraz będzie noc, i odwrotnie
+        const.TIME_CHANGE = current_time + DAY_LENGTH

season.py

@@ -0,0 +1,11 @@
+import pygame
+
+def draw_background(const):
+        season_images = {
+        "spring": "images/tłowiosna.jpg",
+        "summer": "images/tło.jpg",
+        "autumn": "images/tłojesień.jpg",
+        "winter": "images/tłozima.jpg"
+    }
+        background_image = pygame.transform.scale(pygame.image.load(season_images[const.season]), const.WINDOW_SIZE)
+        const.screen.blit(background_image, (0, 0))

spawner.py

@@ -9,6 +9,8 @@ class Spawner:
         # Wyrażenie listowe filtrujące tylko te wybiegi, które pasują do środowiska zwierzęcia 
         enclosure = random.choice(self.enclosures)
 
+        enclosure.animals.add(self.entity) # Przydzielenie zwierzęcia do wybiegu
+
         while True:
             if self.entity.adult:
                 self.entity.x = random.randint(enclosure.x1+1, enclosure.x2-2)
@@ -21,7 +23,7 @@ class Spawner:
                 break
 
     def spawn_terrain_obstacles(self, blocked1, blocked2, taken, grid_width, grid_height):
-        blocked1 = blocked1 | {(8,5),(3,10),(15,2),(26,2),(11,4),(15,7),(22,4),(24,10),(11,12),(19,12)}
+        blocked1 = blocked1 | {(2,0),(3,0),(2,1),(3,1),(8,5),(3,10),(15,2),(26,2),(11,4),(15,7),(22,4),(24,10),(11,12),(19,12)}
         while True:
             self.entity.x = random.randint(0, grid_width - 1)
             self.entity.y = random.randint(0, grid_height - 1)

state_space_search.py

@@ -40,7 +40,7 @@ def graphsearch(istate, goal, max_x, max_y, obstacles, cost_map):
         state, _, _ = node
 
         if goaltest(state, goal):
-            return build_action_sequence(node)
+            return build_action_sequence(node), current_cost(node, cost_map)
 
         explored.add(state)
 
@@ -61,7 +61,7 @@ def graphsearch(istate, goal, max_x, max_y, obstacles, cost_map):
                     else:
                         break
 
-    return False
+    return False, float('inf')
 
 def is_state_in_queue(state, queue):
     for _, (s, _, _) in queue.queue:
@@ -111,9 +111,9 @@ def generate_cost_map(Animals, Terrain_Obstacles, cost_map={}):
 
     for animal in Animals:
         if animal.adult:
-            cost_map[(animal.x + 1, animal.y + 1)] = adult_animal_cost
-            cost_map[(animal.x + 1, animal.y)] = adult_animal_cost
-            cost_map[(animal.x, animal.y + 1)] = adult_animal_cost
+            # cost_map[(animal.x + 1, animal.y + 1)] = adult_animal_cost
+            # cost_map[(animal.x + 1, animal.y)] = adult_animal_cost
+            # cost_map[(animal.x, animal.y + 1)] = adult_animal_cost
             cost_map[(animal.x, animal.y)] = adult_animal_cost
         else:
             cost_map[(animal.x, animal.y)] = baby_animal_cost
@@ -124,4 +124,5 @@ def generate_cost_map(Animals, Terrain_Obstacles, cost_map={}):
         else:
             cost_map[(terrain_obstacle.x , terrain_obstacle.y )] = bush_cost
 
-    return cost_map
+    return cost_map
+