scalenie modułów

.idea/.gitignore

@@ -1,8 +0,0 @@
-# Default ignored files
-/shelf/
-/workspace.xml
-# Editor-based HTTP Client requests
-/httpRequests/
-# Datasource local storage ignored files
-/dataSources/
-/dataSources.local.xml

.idea/SI-projekt-smieciarka2.iml

@@ -1,8 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<module type="PYTHON_MODULE" version="4">
-  <component name="NewModuleRootManager">
-    <content url="file://$MODULE_DIR$" />
-    <orderEntry type="inheritedJdk" />
-    <orderEntry type="sourceFolder" forTests="false" />
-  </component>
-</module>

.idea/inspectionProfiles/profiles_settings.xml

@@ -1,6 +0,0 @@
-<component name="InspectionProjectProfileManager">
-  <settings>
-    <option name="USE_PROJECT_PROFILE" value="false" />
-    <version value="1.0" />
-  </settings>
-</component>

.idea/misc.xml

@@ -1,4 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9" project-jdk-type="Python SDK" />
-</project>

.idea/modules.xml

@@ -1,8 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="ProjectModuleManager">
-    <modules>
-      <module fileurl="file://$PROJECT_DIR$/.idea/SI-projekt-smieciarka2.iml" filepath="$PROJECT_DIR$/.idea/SI-projekt-smieciarka2.iml" />
-    </modules>
-  </component>
-</project>

.idea/vcs.xml

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

snn/snn.py

@@ -4,10 +4,10 @@ import pathlib
 temp = pathlib.PosixPath
 pathlib.PosixPath = pathlib.WindowsPath
 
-DATASET_PATH = Path('../dataset')
+DATASET_PATH = pathlib.Path('../dataset')
 
 learn = load_learner(DATASET_PATH/'export.pkl')
-path = Path(DATASET_PATH/'glass/glass1.jpg')
+path = pathlib.Path(DATASET_PATH / 'others/trash1.jpg')
 
 def getPredict(learner, path):
     prediction = learner.predict(path)

src/astar.py

@@ -1,51 +1,58 @@
 from queue import PriorityQueue
+import numpy as np
+
 
 def heuristic(xy1, xy2):
     return abs(xy1[0] - xy2[0]) + abs(xy1[1] - xy2[1])
 
-def neighbours(point):
-    x, y = point
-    list=((x+1,y), (x,y+1), (x,y-1), (x-1,y))
-    return list
 
-#determining the cost of a specific field in the grid
+def neighbours(point, collisionsMap):
+    x, y = point
+    list = [(x + 1, y), (x, y + 1), (x, y - 1), (x - 1, y)]
+    return [(x, y) for x, y in list if 0 <= x <= 14 and 0 <= y <= 14 and not collisionsMap[x][y]]
+
+
+# determining the cost of a specific field in the grid
 def checkCost(grid, xy):
     x, y = xy
     cost = grid[x][y]
     return cost
 
-def aStar(grid, start, goal):
+
+def aStar(grid, collisionsMap, start, goal):
     openlist = PriorityQueue()
     openlist.put(start, 0)
 
     fScore = {}
+    gScore = {}
     origin = {start: None}
-    fScore[start] = 0
-    closedlist=[]
+    fScore[start] = heuristic(start, goal)
+    gScore[start] = 0
 
-    while openlist!= {} :
+    while not openlist.empty():
         current = openlist.get()
 
         if current == goal:
             path = []
-            #following from the succesors to the root our starting point
-            while current != start:
+            # following from the succesors to the root our starting point
+            while current is not None:
                 path.append(current)
                 current = origin[current]
             path.reverse()
-            break
+            return path
 
         # successor function
-        for succ in neighbours(current):
-            #checking if didn't go out of the maze
-            if(succ[0] < 0 or succ[1] < 0 or succ[0] > 14 or succ[1] > 14):
+        for succ in neighbours(current, collisionsMap):
+            # checking if didn't go out of the maze
+            if succ[0] < 0 or succ[1] < 0 or succ[0] > 14 or succ[1] > 14:
                 continue
 
-            gScore = fScore[current[0],current[1]] + checkCost(grid, current)
-            if succ not in closedlist or gScore < fScore[succ[0],succ[1]]:
-                closedlist.append(succ)
-                origin[succ[0],succ[1]] = current
-                fScore[succ[0],succ[1]] = gScore
-                priority = gScore + heuristic(goal, succ)
+            tentiative_gScore = gScore.get(current, np.inf) + checkCost(grid, succ)
+            if tentiative_gScore < gScore.get(succ, np.inf):
+                origin[succ] = current
+                priority = tentiative_gScore + heuristic(goal, succ)
+                fScore[succ] = priority
+                gScore[succ] = tentiative_gScore
                 openlist.put(succ, priority)
-    return path
+
+    raise RuntimeError("No path found")

src/board.py

@@ -1,10 +1,32 @@
+from pathlib import Path
+
+import numpy as np
+
 import astar
 import pygame
+import snn
+import joblib
+import os
 
 screen = []
 objectArray = []
 collisionsMap = []
 
+decision_tree = joblib.load(Path('../tree/decisionTreeClassifier'))
+
+type_map = {
+    'glass': 2,
+    'others': 0,
+    'paper': 4,
+    'plastic': 3
+}
+testset_path = Path('../testset')
+testset = [Path(f'{testset_path}/{file}') for file in os.listdir(testset_path)]
+
+season = 2
+truck_full = 0
+truck_working = 0
+
 weightsMap = ([1, 2, 1, 4, 5, 2, 7, 8, 5, 4, 15, 3, 4, 5, 8],
         [1, 2, 1, 4, 5, 2, 7, 8, 1, 4, 1, 3, 4, 5, 1],
         [1, 2, 1, 4, 5, 2, 7, 8, 1, 4, 1, 3, 4, 5, 3],
@@ -65,10 +87,8 @@ class Agent(Object):
         truck = pygame.transform.scale(truck, (square, square))
         screen.blit(truck, (circleX, circleY))
 
-    def move(self, gridLength, path):
-        for (x, y) in path:
-            newPos = self.pos.get_moved(x, y)
-            self.move_if_possible(newPos, gridLength)
+    def move(self, newPos):
+        self.pos = newPos
 
     def move_if_possible(self, newPos, gridLength):
         if movement_allowed(newPos, gridLength):
@@ -76,13 +96,13 @@ class Agent(Object):
 
 
 class House(Object):
-    def __init__(self, name, pos):
+    def __init__(self, name, pos, **kwargs):
         super().__init__(name, pos)
-        self.trash_cans = {
-            "paper": False,
-            "glass": False,
-            "plastic": False,
-            "others": False
+        self.trash_can = {
+            "type": kwargs.get('type', np.random.choice(testset)),
+            'animal': kwargs.get('animal', np.random.randint(0, 2)),
+            'quantity': kwargs.get('quantity', np.random.random() * 0.7 + 0.3),
+            'time': kwargs.get('time', np.random.randint(0, 6))
         }
 
     def draw(self, square):
@@ -167,7 +187,8 @@ if __name__ == '__main__':
         (7, 4), (3, 10), (8, 10), (4, 5), (1, 2), (10, 4), (13, 14), (6, 9)
     ]])]
     holes = [Hole(f'dziura-{i}', pos) for i, pos in enumerate([Position(x, y) for x, y in [
-        (4, 9), (5, 11), (11, 7), (13, 8)
+        (4, 9), (5, 11), (11, 7), (13, 8), (0, 1), (1, 1), (2, 1), (14, 13),
+        (13, 13), (4, 8), (5, 9), (7, 9), (6, 8), (3, 5), (4, 6), (5, 5)
     ]])]
     objectArray.append(agent)
     objectArray.append(junkyard)
@@ -175,7 +196,7 @@ if __name__ == '__main__':
     objectArray += holes
 
     collisionsMap = [[False] * gridSize for _ in range(gridSize)]
-    for object in objectArray[1:]:
+    for object in holes:
         collisionsMap[object.pos.x][object.pos.y] = True
 
     width = 610
@@ -184,12 +205,51 @@ if __name__ == '__main__':
 
     startPos = (0, 0)
     finalPos = (14, 14)
-    astarPath = astar.aStar(weightsMap, startPos, finalPos)
+    astarPath = astar.aStar(weightsMap, collisionsMap, startPos, finalPos)
+    checkpoints = [startPos]
+    for house in houses:
+        checkpoints.append((house.pos.x, house.pos.y))
+    checkpoints.append(finalPos)
+    astarPath = []
+    for i in range(len(checkpoints) - 1):
+        path = astar.aStar(weightsMap, collisionsMap, checkpoints[i], checkpoints[i + 1])
+        if i == 0:
+            astarPath += path
+        else:
+            astarPath += path[1:]
+
     print(astarPath)
 
+    pathPos = 0
+    nextCheckpoint = 1
     while True:
+        agent_x, agent_y = astarPath[pathPos]
+        checkpoint_x, checkpoint_y = checkpoints[nextCheckpoint]
+        agent.pos = Position(agent_x, agent_y)
+        for house in houses:
+            if house.pos.x == agent_x and house.pos.y == agent_y \
+                    and agent_x == checkpoint_x and agent_y == checkpoint_y:
+                nextCheckpoint += 1
+                house.trash_can['evaluated_type'] = type_map[snn.getPredict(house.trash_can['type'])[0]]
+                print('House:', house.name, 'pos:', astarPath[pathPos], 'type:', house.trash_can['type'],
+                      'evaluated_type:', house.trash_can['evaluated_type'])
+                tree_input = np.array([
+                    house.trash_can['evaluated_type'],
+                    season,
+                    house.trash_can['animal'],
+                    truck_full,
+                    house.trash_can['quantity'],
+                    house.trash_can['time'],
+                    truck_working
+                ]).reshape(1, -1)
+                should_get = decision_tree.predict(tree_input)
+                print('Desicion tree input:', tree_input, 'result:', should_get)
+        pathPos = pathPos + 1 if pathPos < len(astarPath) - 1 else pathPos
         c = (255, 255, 255)  # tymczasowy kolor tła - do usunięcia, jak już będzie zdjęcie
         screen.fill(c)
         draw(gridSize, objectArray)
         kb_listen(objectArray, gridSize, astarPath)
         pygame.display.update()  # by krata pojawiła się w okienku - update powierzc
+        pygame.time.wait(100)
+
+

src/snn.py

@@ -0,0 +1,16 @@
+from fastai.vision.all import *
+import pathlib
+
+temp = pathlib.PosixPath
+pathlib.PosixPath = pathlib.WindowsPath
+
+DATASET_PATH = pathlib.Path('../dataset')
+
+learn = load_learner(DATASET_PATH/'export.pkl')
+path = pathlib.Path(DATASET_PATH / 'others/trash1.jpg')
+
+def getPredict(path):
+    prediction = learn.predict(path)
+    predictionName = learn.predict(path)[0]
+    # print(prediction, '\n\n','prediction:', predictionName, 'path:', path)
+    return prediction

tree/main.py

@@ -1,5 +1,6 @@
 import pandas as pd
 from sklearn import tree
+import joblib
 
 df = pd.read_csv('data.csv')
 print(df.head())
@@ -19,6 +20,8 @@ print(pred)
 print('Jedynki: ', len(df[df['Y'] == 1]))
 print('Zera: ', len(df[df['Y'] == 0]))
 
+joblib.dump(clf, 'decisionTreeClassifier')
+
 
 #Legenda
 #czy wywiezc zmieci	1 tak 0 nie