beautiful code
This commit is contained in:
Tomasz Adamczyk
parent
ef93291011
commit
8f0ebe81fc
@ -3,86 +3,19 @@
|
||||
<component name="ChangeListManager">
|
||||
<list default="true" id="56453584-72bd-49f4-a39c-fccf91ab20c6" name="Default Changelist" comment="">
|
||||
<change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/astar.py" beforeDir="false" afterPath="$PROJECT_DIR$/astar.py" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/cart.py" beforeDir="false" afterPath="$PROJECT_DIR$/cart.py" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/definitions.py" beforeDir="false" afterPath="$PROJECT_DIR$/definitions.py" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/field.py" beforeDir="false" afterPath="$PROJECT_DIR$/field.py" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/geneticalgorithm.py" beforeDir="false" afterPath="$PROJECT_DIR$/geneticalgorithm.py" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/graph.py" beforeDir="false" afterPath="$PROJECT_DIR$/graph.py" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/map.py" beforeDir="false" afterPath="$PROJECT_DIR$/map.py" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/neuralnetwork.py" beforeDir="false" afterPath="$PROJECT_DIR$/neuralnetwork.py" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/plant.py" beforeDir="false" afterPath="$PROJECT_DIR$/plant.py" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/genetic_algorithm/optimal.pkl" beforeDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_01_01.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_01_01.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_01_02.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_01_02.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_01_03.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_01_03.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_01_04.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_01_04.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_01_05.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_01_05.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_01_06.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_01_06.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_01_07.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_01_07.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_02_01.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_02_01.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_02_02.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_02_02.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_02_03.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_02_03.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_02_04.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_02_04.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_02_05.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_02_05.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_02_06.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_02_06.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_02_07.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_02_07.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_03_01.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_03_01.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_03_02.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_03_02.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_03_03.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_03_03.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_03_04.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_03_04.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_03_05.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_03_05.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_03_06.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_03_06.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_03_07.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_03_07.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_04_01.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_04_01.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_04_02.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_04_02.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_04_03.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_04_03.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_04_04.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_04_04.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_04_05.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_04_05.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_04_06.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_04_06.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_04_07.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_04_07.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_05_01.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_05_01.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_05_02.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_05_02.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_05_03.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_05_03.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_05_04.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_05_04.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_05_05.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_05_05.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_05_06.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_05_06.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_05_07.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_05_07.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_06_01.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_06_01.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_06_02.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_06_02.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_06_03.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_06_03.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_06_04.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_06_04.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_06_05.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_06_05.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_06_06.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_06_06.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_06_07.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_06_07.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_06_08.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_06_08.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_06_09.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_06_09.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_06_10.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_06_10.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_07_01.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_07_01.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_07_02.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_07_02.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_07_03.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_07_03.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_07_04.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_07_04.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_07_05.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_07_05.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_07_06.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_07_06.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_07_07.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_07_07.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_07_08.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_07_08.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_07_09.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_07_09.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_07_10.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_07_10.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_08_01.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_08_01.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_08_02.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_08_02.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_08_03.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_08_03.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_08_04.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_08_04.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_08_05.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_08_05.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_08_06.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_08_06.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_08_07.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_08_07.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_08_08.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_08_08.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_08_09.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_08_09.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_08_10.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_08_10.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_09_01.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_09_01.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_09_02.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_09_02.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_09_03.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_09_03.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_09_04.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_09_04.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_09_05.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_09_05.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_09_06.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_09_06.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_09_07.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_09_07.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_09_08.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_09_08.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_09_09.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_09_09.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/resources/neural_network/tiles/tile_09_10.png" beforeDir="false" afterPath="$PROJECT_DIR$/resources/neural_network/tiles/tile_09_10.png" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/py.py" beforeDir="false" afterPath="$PROJECT_DIR$/py.py" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/soil.py" beforeDir="false" afterPath="$PROJECT_DIR$/soil.py" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/station.py" beforeDir="false" afterPath="$PROJECT_DIR$/station.py" afterDir="false" />
|
||||
<change beforePath="$PROJECT_DIR$/treelearn.py" beforeDir="false" afterPath="$PROJECT_DIR$/treelearn.py" afterDir="false" />
|
||||
</list>
|
||||
<option name="SHOW_DIALOG" value="false" />
|
||||
<option name="HIGHLIGHT_CONFLICTS" value="true" />
|
||||
@ -262,6 +195,8 @@
|
||||
<workItem from="1623946067787" duration="1589000" />
|
||||
<workItem from="1624000494335" duration="2720000" />
|
||||
<workItem from="1624004901146" duration="4577000" />
|
||||
<workItem from="1624010934783" duration="16000" />
|
||||
<workItem from="1624011102769" duration="230000" />
|
||||
</task>
|
||||
<servers />
|
||||
</component>
|
||||
@ -323,10 +258,10 @@
|
||||
</state>
|
||||
<state width="1879" height="364" key="GridCell.Tab.1.right/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622903620068" />
|
||||
<state width="1879" height="364" key="GridCell.Tab.1.right/0.0.1920.1080@0.0.1920.1080" timestamp="1619289752045" />
|
||||
<state x="0" y="0" key="com.intellij.ide.util.TipDialog" timestamp="1624004901010">
|
||||
<state x="0" y="0" key="com.intellij.ide.util.TipDialog" timestamp="1624011102185">
|
||||
<screen x="0" y="0" width="1920" height="1080" />
|
||||
</state>
|
||||
<state x="0" y="0" key="com.intellij.ide.util.TipDialog/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1624004901010" />
|
||||
<state x="0" y="0" key="com.intellij.ide.util.TipDialog/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1624011102185" />
|
||||
<state x="0" y="0" key="com.intellij.ide.util.TipDialog/0.0.1920.1080@0.0.1920.1080" timestamp="1621439087317" />
|
||||
<state x="615" y="209" key="com.intellij.openapi.editor.actions.MultiplePasteAction$ClipboardContentChooser" timestamp="1623589256933">
|
||||
<screen x="0" y="0" width="1920" height="1080" />
|
||||
|
||||
93
astar.py
93
astar.py
@ -1,75 +1,107 @@
|
||||
from operator import itemgetter
|
||||
import cart
|
||||
import copy
|
||||
class Istate: #stan początkowy wózka (strona, w którą patrzy, miejsce, w którym się on znajduje)
|
||||
|
||||
|
||||
class Istate: # stan początkowy wózka (strona, w którą patrzy, miejsce, w którym się on znajduje)
|
||||
def __init__(self, direction, x, y):
|
||||
self.direction = direction
|
||||
self.x = x
|
||||
self.y = y
|
||||
|
||||
def get_direction(self):
|
||||
return self.direction
|
||||
|
||||
def set_direction(self, direction):
|
||||
self.direction = direction
|
||||
|
||||
def get_x(self):
|
||||
return self.x
|
||||
|
||||
def set_x(self, x):
|
||||
self.x = x
|
||||
|
||||
def get_y(self):
|
||||
return self.y
|
||||
|
||||
def set_y(self, y):
|
||||
self.y = y
|
||||
class Node: #wierzchołek grafu
|
||||
|
||||
|
||||
class Node: # wierzchołek grafu
|
||||
def __init__(self, action, direction, parent, x, y):
|
||||
self.action = action #akcja jaką ma wykonać (obróc się w lewo, obróć się w prawo, ruch do przodu)
|
||||
self.action = action # akcja jaką ma wykonać (obróc się w lewo, obróć się w prawo, ruch do przodu)
|
||||
self.direction = direction
|
||||
self.parent = parent #ojciec wierzchołka
|
||||
self.parent = parent # ojciec wierzchołka
|
||||
self.x = x
|
||||
self.y = y
|
||||
|
||||
def get_action(self):
|
||||
return self.action
|
||||
|
||||
def set_action(self, action):
|
||||
self.action = action
|
||||
|
||||
def get_direction(self):
|
||||
return self.direction
|
||||
|
||||
def set_direction(self, direction):
|
||||
self.direction = direction
|
||||
|
||||
def get_parent(self):
|
||||
return self.parent
|
||||
|
||||
def set_parent(self, parent):
|
||||
self.parent = parent
|
||||
|
||||
def get_x(self):
|
||||
return self.x
|
||||
|
||||
def set_x(self, x):
|
||||
self.x = x
|
||||
|
||||
def get_y(self):
|
||||
return self.y
|
||||
|
||||
def set_y(self, y):
|
||||
self.y = y
|
||||
def cost(map, node): #funkcja kosztu : ile kosztuje przejechanie przez dane pole
|
||||
|
||||
|
||||
def cost(map, node): # funkcja kosztu : ile kosztuje przejechanie przez dane pole
|
||||
cost = 0
|
||||
while(node.get_parent() != None):
|
||||
while (node.get_parent() != None):
|
||||
cost = cost + map.get_field_cost(int(node.get_x()), int(node.get_y())) + 1
|
||||
node = node.get_parent()
|
||||
return cost
|
||||
def f(goaltest, map, node): #funkcja zwracająca sumę funkcji kosztu oraz heurestyki
|
||||
|
||||
|
||||
def f(goaltest, map, node): # funkcja zwracająca sumę funkcji kosztu oraz heurestyki
|
||||
return cost(map, node) + heuristic(goaltest, node)
|
||||
def goal_test(elem, goaltest): #funkcja sprawdzająca czy położenie wózka równa się położeniu punktu docelowego, jeśli tak zwraca prawdę, w przeciwnym wypadku fałsz
|
||||
|
||||
|
||||
def goal_test(elem,
|
||||
goaltest): # funkcja sprawdzająca czy położenie wózka równa się położeniu punktu docelowego, jeśli tak zwraca prawdę, w przeciwnym wypadku fałsz
|
||||
if elem.get_x() == goaltest[0] and elem.get_y() == goaltest[1]:
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
def graphsearch(explored, f, fringe, goaltest, istate, map, succ): #przeszukiwanie grafu wszerz
|
||||
node = Node(None, istate.get_direction(), None, istate.get_x(), istate.get_y()) #wierzchołek początkowy, stworzony ze stanu początkowego wózka
|
||||
fringe.append((node, 0)) #wierzchołki do odwiedzenia z priorytetem
|
||||
|
||||
|
||||
def graphsearch(explored, f, fringe, goaltest, istate, map, succ): # przeszukiwanie grafu wszerz
|
||||
node = Node(None, istate.get_direction(), None, istate.get_x(),
|
||||
istate.get_y()) # wierzchołek początkowy, stworzony ze stanu początkowego wózka
|
||||
fringe.append((node, 0)) # wierzchołki do odwiedzenia z priorytetem
|
||||
while True:
|
||||
if not fringe:
|
||||
return False
|
||||
elem = fringe.pop(0) #zdejmujemy wierzchołek z kolejki fringe i rozpatrujemy go
|
||||
elem = fringe.pop(0) # zdejmujemy wierzchołek z kolejki fringe i rozpatrujemy go
|
||||
temp = copy.copy(elem[0])
|
||||
if goal_test(elem[0], goaltest) is True: #jeżeli osiągniemy cel w trakcie przeszukiwania grafu wszerz (wjedziemy na pole docelowe) : zwracamy listę ruchów, po których wykonaniu dotrzemy na miejsce
|
||||
if goal_test(elem[0],
|
||||
goaltest) is True: # jeżeli osiągniemy cel w trakcie przeszukiwania grafu wszerz (wjedziemy na pole docelowe) : zwracamy listę ruchów, po których wykonaniu dotrzemy na miejsce
|
||||
return print_moves(elem[0])
|
||||
explored.append(elem) #dodajemy wierzchołek do listy wierzchołków odwiedzonych
|
||||
for (action, state) in succ(temp): #iterujemy po wszystkich możliwych akcjach i stanach otrzymanych dla danego wierzchołka grafu
|
||||
explored.append(elem) # dodajemy wierzchołek do listy wierzchołków odwiedzonych
|
||||
for (action, state) in succ(
|
||||
temp): # iterujemy po wszystkich możliwych akcjach i stanach otrzymanych dla danego wierzchołka grafu
|
||||
fringe_tuple = []
|
||||
fringe_tuple_prio = []
|
||||
explored_tuple = []
|
||||
@ -78,31 +110,40 @@ def graphsearch(explored, f, fringe, goaltest, istate, map, succ): #przeszukiwan
|
||||
fringe_tuple_prio.append(((x.get_direction(), x.get_x(), x.get_y()), y))
|
||||
for (x, y) in explored:
|
||||
explored_tuple.append((x.get_direction(), x.get_x(), x.get_y()))
|
||||
x = Node(action, state[0], elem[0], state[1], state[2]) #stworzenie nowego wierzchołka, którego rodzicem jest elem
|
||||
p = f(goaltest, map, x) #liczy priorytet
|
||||
if state not in fringe_tuple and state not in explored_tuple: #jeżeli stan nie znajduje się na fringe oraz nie znajduje się w liście wierzchołków odwiedzonych
|
||||
fringe.append((x, p)) #dodanie wierzchołka na fringe
|
||||
fringe = sorted(fringe, key=itemgetter(1)) #sortowanie fringe'a według priorytetu
|
||||
x = Node(action, state[0], elem[0], state[1],
|
||||
state[2]) # stworzenie nowego wierzchołka, którego rodzicem jest elem
|
||||
p = f(goaltest, map, x) # liczy priorytet
|
||||
if state not in fringe_tuple and state not in explored_tuple: # jeżeli stan nie znajduje się na fringe oraz nie znajduje się w liście wierzchołków odwiedzonych
|
||||
fringe.append((x, p)) # dodanie wierzchołka na fringe
|
||||
fringe = sorted(fringe, key=itemgetter(1)) # sortowanie fringe'a według priorytetu
|
||||
elif state in fringe_tuple:
|
||||
i = 0
|
||||
for (state_prio, r) in fringe_tuple_prio:
|
||||
if str(state_prio) == str(state):
|
||||
if r > p:
|
||||
fringe.insert(i, (x, p)) #zamiana state, który należy do fringe z priorytetem r na state z priorytetem p (niższym)
|
||||
fringe.insert(i, (x,
|
||||
p)) # zamiana state, który należy do fringe z priorytetem r na state z priorytetem p (niższym)
|
||||
fringe.pop(i + 1)
|
||||
fringe = sorted(fringe, key=itemgetter(1)) #sortowanie fringe'a według priorytetu
|
||||
fringe = sorted(fringe, key=itemgetter(1)) # sortowanie fringe'a według priorytetu
|
||||
break
|
||||
i = i + 1
|
||||
def heuristic(goaltest, node): #funkcja heurestyki : oszacowuje koszt osiągnięcia stanu końcowego (droga)
|
||||
|
||||
|
||||
def heuristic(goaltest, node): # funkcja heurestyki : oszacowuje koszt osiągnięcia stanu końcowego (droga)
|
||||
return abs(node.get_x() - goaltest[0]) + abs(node.get_y() - goaltest[1])
|
||||
def print_moves(elem): #zwraca listę ruchów jakie należy wykonać by dotrzeć do punktu docelowego
|
||||
|
||||
|
||||
def print_moves(elem): # zwraca listę ruchów jakie należy wykonać by dotrzeć do punktu docelowego
|
||||
moves_list = []
|
||||
while (elem.get_parent() != None):
|
||||
moves_list.append(elem.get_action())
|
||||
elem = elem.get_parent()
|
||||
moves_list.reverse()
|
||||
return moves_list
|
||||
def succ(elem): #funkcja następnika, przypisuje jakie akcje są możliwe do wykonania na danym polu oraz jaki będzie stan (kierunek, położenie) po wykonaniu tej akcji
|
||||
|
||||
|
||||
def succ(
|
||||
elem): # funkcja następnika, przypisuje jakie akcje są możliwe do wykonania na danym polu oraz jaki będzie stan (kierunek, położenie) po wykonaniu tej akcji
|
||||
actions_list = []
|
||||
temp = copy.copy(elem.get_direction())
|
||||
if temp == 1:
|
||||
@ -128,4 +169,4 @@ def succ(elem): #funkcja następnika, przypisuje jakie akcje są możliwe do wyk
|
||||
actions_list.append(("move", (elem.get_direction(), elem.get_x(), temp_move_south)))
|
||||
elif cart.Cart.is_move_allowed_succ(elem) == "x - 1":
|
||||
actions_list.append(("move", (elem.get_direction(), temp_move_west, elem.get_y())))
|
||||
return actions_list
|
||||
return actions_list
|
||||
|
||||
112
cart.py
112
cart.py
@ -1,54 +1,81 @@
|
||||
import definitions
|
||||
import random
|
||||
|
||||
|
||||
class Cart:
|
||||
def __init__(self, amount_of_seeds, collected_plants, direction, fertilizer, fuel, water_level, x, y):
|
||||
self.amount_of_seeds = amount_of_seeds #amount_of_seeds to słownik, przechowuje informacje o posiadanej ilości ziaren dla danej rośliny
|
||||
self.collected_plants = collected_plants #collected_plants to słownik, przechowuje informacje o zebranych plonach
|
||||
self.direction = direction #w którą stronę patrzy, zgodnie ze wskazówkami zegara (1 -: godzina 12, 2 : godzina 3, 3 : godzina 6, 4 : godzina 9)
|
||||
self.fertilizer = fertilizer #fertilizer to słownik, przechowuje informacje o ilości posiadanego nawozu dla konkretnej rośliny
|
||||
self.fuel = fuel #aktualna ilość paliwa
|
||||
self.water_level = water_level #aktualna ilość wody do podlewania
|
||||
self.amount_of_seeds = amount_of_seeds # amount_of_seeds to słownik, przechowuje informacje o posiadanej ilości ziaren dla danej rośliny
|
||||
self.collected_plants = collected_plants # collected_plants to słownik, przechowuje informacje o zebranych plonach
|
||||
self.direction = direction # w którą stronę patrzy, zgodnie ze wskazówkami zegara (1 -: godzina 12, 2 : godzina 3, 3 : godzina 6, 4 : godzina 9)
|
||||
self.fertilizer = fertilizer # fertilizer to słownik, przechowuje informacje o ilości posiadanego nawozu dla konkretnej rośliny
|
||||
self.fuel = fuel # aktualna ilość paliwa
|
||||
self.water_level = water_level # aktualna ilość wody do podlewania
|
||||
self.x = x
|
||||
self.y = y
|
||||
def get_all_amount_of_seeds(self): #zwraca łączną ilość ziaren (suma ziaren dla wszystkich roślin)
|
||||
return self.amount_of_seeds["beetroot"] + self.amount_of_seeds["carrot"] + self.amount_of_seeds["potato"] + self.amount_of_seeds["wheat"]
|
||||
def get_amount_of_seeds(self, name): #zwraca łączną ilość ziaren dla podanej rośliny (name)
|
||||
|
||||
def get_all_amount_of_seeds(self): # zwraca łączną ilość ziaren (suma ziaren dla wszystkich roślin)
|
||||
return self.amount_of_seeds["beetroot"] + self.amount_of_seeds["carrot"] + self.amount_of_seeds["potato"] + \
|
||||
self.amount_of_seeds["wheat"]
|
||||
|
||||
def get_amount_of_seeds(self, name): # zwraca łączną ilość ziaren dla podanej rośliny (name)
|
||||
return self.amount_of_seeds[name]
|
||||
def set_amount_of_seeds(self, name, value): #dla podanej rośliny (name) ustawia łączną ilość ziaren (value)
|
||||
|
||||
def set_amount_of_seeds(self, name, value): # dla podanej rośliny (name) ustawia łączną ilość ziaren (value)
|
||||
self.amount_of_seeds[name] = value
|
||||
def get_all_collected_plants(self): #zwraca łączną ilość zebranych plonów (suma plonów wszystkich roślin)
|
||||
return self.collected_plants["beetroot"] + self.collected_plants["carrot"] + self.collected_plants["potato"] + self.collected_plants["wheat"]
|
||||
def get_collected_plants(self, name): #zwraca łączną ilość zebranych plonów dla podanej rośliny (name)
|
||||
|
||||
def get_all_collected_plants(self): # zwraca łączną ilość zebranych plonów (suma plonów wszystkich roślin)
|
||||
return self.collected_plants["beetroot"] + self.collected_plants["carrot"] + self.collected_plants["potato"] + \
|
||||
self.collected_plants["wheat"]
|
||||
|
||||
def get_collected_plants(self, name): # zwraca łączną ilość zebranych plonów dla podanej rośliny (name)
|
||||
return self.collected_plants[name]
|
||||
def set_collected_plants(self, name, value): #dla podanej rośliny (name) ustawia łączną ilość zebranych plonów (value)
|
||||
|
||||
def set_collected_plants(self, name,
|
||||
value): # dla podanej rośliny (name) ustawia łączną ilość zebranych plonów (value)
|
||||
self.collected_plants[name] = value
|
||||
|
||||
def get_direction(self):
|
||||
return self.direction
|
||||
|
||||
def set_direction(self, direction):
|
||||
self.direction = direction
|
||||
def get_all_fertilizer(self): #zwraca łączną ilość posiadanego nawozu (suma nawozu dla wszystkich roślin)
|
||||
return self.fertilizer["beetroot"] + self.fertilizer["carrot"] + self.fertilizer["potato"] + self.fertilizer["wheat"]
|
||||
def get_fertilizer(self, name): #zwraca łączną ilość posiadanego nawozu dla podanej rośliny (name)
|
||||
|
||||
def get_all_fertilizer(self): # zwraca łączną ilość posiadanego nawozu (suma nawozu dla wszystkich roślin)
|
||||
return self.fertilizer["beetroot"] + self.fertilizer["carrot"] + self.fertilizer["potato"] + self.fertilizer[
|
||||
"wheat"]
|
||||
|
||||
def get_fertilizer(self, name): # zwraca łączną ilość posiadanego nawozu dla podanej rośliny (name)
|
||||
return self.fertilizer[name]
|
||||
def set_fertilizer(self, name, value): #dla podanej rośliny (name) ustawia ilość posiadanego nawozu (value)
|
||||
|
||||
def set_fertilizer(self, name, value): # dla podanej rośliny (name) ustawia ilość posiadanego nawozu (value)
|
||||
self.fertilizer[name] = value
|
||||
|
||||
def get_fuel(self):
|
||||
return self.fuel
|
||||
|
||||
def set_fuel(self, fuel):
|
||||
self.fuel = fuel
|
||||
|
||||
def get_water_level(self):
|
||||
return self.water_level
|
||||
|
||||
def set_water_level(self, water_level):
|
||||
self.water_level = water_level
|
||||
|
||||
def get_x(self):
|
||||
return self.x
|
||||
|
||||
def set_x(self, x):
|
||||
self.x = x
|
||||
|
||||
def get_y(self):
|
||||
return self.y
|
||||
|
||||
def set_y(self, y):
|
||||
self.y = y
|
||||
def do_work(self, cart_rect, map1, station1): #jaką pracę wózek ma wykonać na danym polu, na którym aktualnie przebywa (zmienia stan logiczny danego pola)
|
||||
|
||||
def do_work(self, cart_rect, map1,
|
||||
station1): # jaką pracę wózek ma wykonać na danym polu, na którym aktualnie przebywa (zmienia stan logiczny danego pola)
|
||||
loop = True
|
||||
if self.get_all_amount_of_seeds() == 0:
|
||||
loop = False
|
||||
@ -90,19 +117,23 @@ class Cart:
|
||||
field.get_plant().set_name("wheat")
|
||||
field.get_plant().set_state(1)
|
||||
loop = False
|
||||
elif field.get_plant().get_name() == "beetroot" and field.get_plant().get_state() > 0 and field.get_plant().get_state() < definitions.BEETROOTS_MAXIMUM_STATE - definitions.BEETROOTS_GROW_TIME and self.get_fertilizer("beetroot") > 0 and field.get_soil().get_is_fertilized() is False:
|
||||
elif field.get_plant().get_name() == "beetroot" and field.get_plant().get_state() > 0 and field.get_plant().get_state() < definitions.BEETROOTS_MAXIMUM_STATE - definitions.BEETROOTS_GROW_TIME and self.get_fertilizer(
|
||||
"beetroot") > 0 and field.get_soil().get_is_fertilized() is False:
|
||||
self.set_fertilizer("beetroot", (self.get_fertilizer("beetroot") - 1))
|
||||
field.get_soil().set_is_fertilized(True)
|
||||
field.get_plant().set_state(field.get_plant().get_state() + definitions.BEETROOTS_GROW_TIME)
|
||||
elif field.get_plant().get_name() == "carrot" and field.get_plant().get_state() > 0 and field.get_plant().get_state() < definitions.CARROTS_MAXIMUM_STATE - definitions.CARROTS_GROW_TIME and self.get_fertilizer("carrot") > 0 and field.get_soil().get_is_fertilized() is False:
|
||||
elif field.get_plant().get_name() == "carrot" and field.get_plant().get_state() > 0 and field.get_plant().get_state() < definitions.CARROTS_MAXIMUM_STATE - definitions.CARROTS_GROW_TIME and self.get_fertilizer(
|
||||
"carrot") > 0 and field.get_soil().get_is_fertilized() is False:
|
||||
self.set_fertilizer("carrot", (self.get_fertilizer("carrot") - 1))
|
||||
field.get_soil().set_is_fertilized(True)
|
||||
field.get_plant().set_state(field.get_plant().get_state() + definitions.CARROTS_GROW_TIME)
|
||||
elif field.get_plant().get_name() == "potato" and field.get_plant().get_state() > 0 and field.get_plant().get_state() < definitions.POTATOES_MAXIMUM_STATE - definitions.POTATOES_GROW_TIME and self.get_fertilizer("potato") > 0 and field.get_soil().get_is_fertilized() is False:
|
||||
elif field.get_plant().get_name() == "potato" and field.get_plant().get_state() > 0 and field.get_plant().get_state() < definitions.POTATOES_MAXIMUM_STATE - definitions.POTATOES_GROW_TIME and self.get_fertilizer(
|
||||
"potato") > 0 and field.get_soil().get_is_fertilized() is False:
|
||||
self.set_fertilizer("potato", (self.get_fertilizer("potato") - 1))
|
||||
field.get_soil().set_is_fertilized(True)
|
||||
field.get_plant().set_state(field.get_plant().get_state() + definitions.POTATOES_GROW_TIME)
|
||||
elif field.get_plant().get_name() == "wheat" and field.get_plant().get_state() > 0 and field.get_plant().get_state() < definitions.WHEAT_MAXIMUM_STATE - definitions.WHEAT_GROW_TIME and self.get_fertilizer("wheat") > 0 and field.get_soil().get_is_fertilized() is False:
|
||||
elif field.get_plant().get_name() == "wheat" and field.get_plant().get_state() > 0 and field.get_plant().get_state() < definitions.WHEAT_MAXIMUM_STATE - definitions.WHEAT_GROW_TIME and self.get_fertilizer(
|
||||
"wheat") > 0 and field.get_soil().get_is_fertilized() is False:
|
||||
self.set_fertilizer("wheat", (self.get_fertilizer("wheat") - 1))
|
||||
field.get_soil().set_is_fertilized(True)
|
||||
field.get_plant().set_state(field.get_plant().get_state() + definitions.WHEAT_GROW_TIME)
|
||||
@ -134,7 +165,8 @@ class Cart:
|
||||
field.get_soil().set_water_level(False)
|
||||
field.get_soil().set_state(False)
|
||||
self.set_collected_plants("wheat", self.get_collected_plants("wheat") + 1)
|
||||
def handle_movement(self, cart_rect, move): #odpowiada za poruszanie się wózka po mapie
|
||||
|
||||
def handle_movement(self, cart_rect, move): # odpowiada za poruszanie się wózka po mapie
|
||||
if self.get_fuel() > 0:
|
||||
if move == "move":
|
||||
self.move()
|
||||
@ -145,7 +177,8 @@ class Cart:
|
||||
self.set_fuel(self.get_fuel() - 1)
|
||||
cart_rect.x = self.get_x()
|
||||
cart_rect.y = self.get_y()
|
||||
def handle_movement_random(self, cart_rect): #odpowiada za losowe poruszanie się wózka po mapie
|
||||
|
||||
def handle_movement_random(self, cart_rect): # odpowiada za losowe poruszanie się wózka po mapie
|
||||
loop = True
|
||||
while loop and self.get_fuel() > 0:
|
||||
random1 = random.randint(1, 3)
|
||||
@ -161,7 +194,9 @@ class Cart:
|
||||
self.rotate_right()
|
||||
loop = False
|
||||
self.set_fuel(self.get_fuel() - 1)
|
||||
def is_move_allowed(self, cart_rect): #sprawdza czy dany ruch, który chce wykonać wózek jest możliwy, zwraca prawdę lub fałsz
|
||||
|
||||
def is_move_allowed(self,
|
||||
cart_rect): # sprawdza czy dany ruch, który chce wykonać wózek jest możliwy, zwraca prawdę lub fałsz
|
||||
if self.direction == definitions.CART_DIRECTION_EAST and cart_rect.x + definitions.BLOCK_SIZE < definitions.WIDTH_MAP:
|
||||
return True
|
||||
elif self.direction == definitions.CART_DIRECTION_NORTH and cart_rect.y - definitions.BLOCK_SIZE >= 0:
|
||||
@ -172,8 +207,10 @@ class Cart:
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
|
||||
@staticmethod
|
||||
def is_move_allowed_succ(node): #sprawdza czy dany ruch, który chce wykonać wózek jest możliwy, zwraca pozycje po wykonaniu ruchu, wersja node
|
||||
def is_move_allowed_succ(
|
||||
node): # sprawdza czy dany ruch, który chce wykonać wózek jest możliwy, zwraca pozycje po wykonaniu ruchu, wersja node
|
||||
if node.get_direction() == definitions.CART_DIRECTION_EAST and node.get_x() * definitions.BLOCK_SIZE + definitions.BLOCK_SIZE < definitions.WIDTH_MAP:
|
||||
return "x + 1"
|
||||
elif node.get_direction() == definitions.CART_DIRECTION_NORTH and node.get_y() * definitions.BLOCK_SIZE - definitions.BLOCK_SIZE >= 0:
|
||||
@ -184,6 +221,7 @@ class Cart:
|
||||
return "x - 1"
|
||||
else:
|
||||
return False
|
||||
|
||||
def move(self):
|
||||
if self.direction == definitions.CART_DIRECTION_EAST:
|
||||
self.x = self.x + definitions.BLOCK_SIZE
|
||||
@ -193,24 +231,32 @@ class Cart:
|
||||
self.y = self.y + definitions.BLOCK_SIZE
|
||||
elif self.direction == definitions.CART_DIRECTION_WEST:
|
||||
self.x = self.x - definitions.BLOCK_SIZE
|
||||
|
||||
def rotate_left(self):
|
||||
if self.direction == 1:
|
||||
self.direction = 4
|
||||
else:
|
||||
self.direction = self.direction - 1
|
||||
|
||||
def rotate_right(self):
|
||||
if self.direction == 4:
|
||||
self.direction = 1
|
||||
else:
|
||||
self.direction = self.direction + 1
|
||||
def station_restore(self, station1): #aktualizuje stan stacji pod względem oddanych plonów oraz uzupełnia zapasy wózka
|
||||
station1.set_collected_plants("beetroot", station1.get_collected_plants("beetroot") + self.get_collected_plants("beetroot"))
|
||||
|
||||
def station_restore(self,
|
||||
station1): # aktualizuje stan stacji pod względem oddanych plonów oraz uzupełnia zapasy wózka
|
||||
station1.set_collected_plants("beetroot",
|
||||
station1.get_collected_plants("beetroot") + self.get_collected_plants("beetroot"))
|
||||
self.set_collected_plants("beetroot", 0)
|
||||
station1.set_collected_plants("carrot", station1.get_collected_plants("carrot") + self.get_collected_plants("carrot"))
|
||||
station1.set_collected_plants("carrot",
|
||||
station1.get_collected_plants("carrot") + self.get_collected_plants("carrot"))
|
||||
self.set_collected_plants("carrot", 0)
|
||||
station1.set_collected_plants("potato", station1.get_collected_plants("potato") + self.get_collected_plants("potato"))
|
||||
station1.set_collected_plants("potato",
|
||||
station1.get_collected_plants("potato") + self.get_collected_plants("potato"))
|
||||
self.set_collected_plants("potato", 0)
|
||||
station1.set_collected_plants("wheat", station1.get_collected_plants("wheat") + self.get_collected_plants("wheat"))
|
||||
station1.set_collected_plants("wheat",
|
||||
station1.get_collected_plants("wheat") + self.get_collected_plants("wheat"))
|
||||
self.set_collected_plants("wheat", 0)
|
||||
self.set_amount_of_seeds("beetroot", definitions.CART_AMOUNT_OF_SEEDS_EACH_TYPE)
|
||||
self.set_amount_of_seeds("carrot", definitions.CART_AMOUNT_OF_SEEDS_EACH_TYPE)
|
||||
@ -221,4 +267,4 @@ class Cart:
|
||||
self.set_fertilizer("potato", definitions.CART_FERTILIZER)
|
||||
self.set_fertilizer("wheat", definitions.CART_FERTILIZER)
|
||||
self.set_fuel(definitions.CART_FUEL)
|
||||
self.set_water_level(definitions.CART_WATER_LEVEL)
|
||||
self.set_water_level(definitions.CART_WATER_LEVEL)
|
||||
|
||||
@ -1,6 +1,7 @@
|
||||
#definicje
|
||||
# definicje
|
||||
import os
|
||||
import pygame
|
||||
|
||||
pygame.init()
|
||||
BLOCK_SIZE = 60
|
||||
BEETROOT = pygame.image.load(os.path.join('resources/images', 'beetroot.png'))
|
||||
@ -119,4 +120,4 @@ WHEAT_STAGE_6 = pygame.image.load(os.path.join('resources/images', 'wheat_stage_
|
||||
WHEAT_STAGE_6 = pygame.transform.scale(WHEAT_STAGE_6, (BLOCK_SIZE, BLOCK_SIZE))
|
||||
WHEAT_STAGE_7 = pygame.image.load(os.path.join('resources/images', 'wheat_stage_7.png'))
|
||||
WHEAT_STAGE_7 = pygame.transform.scale(WHEAT_STAGE_7, (BLOCK_SIZE, BLOCK_SIZE))
|
||||
WINDOW = pygame.display.set_mode((WIDTH, HEIGHT))
|
||||
WINDOW = pygame.display.set_mode((WIDTH, HEIGHT))
|
||||
|
||||
10
field.py
10
field.py
@ -1,17 +1,23 @@
|
||||
class Field:
|
||||
def __init__(self, plant, rect, soil): #składa się z rośliny oraz gleby, plus koordynaty danego pola
|
||||
def __init__(self, plant, rect, soil): # składa się z rośliny oraz gleby, plus koordynaty danego pola
|
||||
self.plant = plant
|
||||
self.rect = rect
|
||||
self.soil = soil
|
||||
|
||||
def get_plant(self):
|
||||
return self.plant
|
||||
|
||||
def set_plant(self, plant):
|
||||
self.plant = plant
|
||||
|
||||
def set_rect(self, rect):
|
||||
self.rect = rect
|
||||
|
||||
def get_rect(self):
|
||||
return self.rect
|
||||
|
||||
def get_soil(self):
|
||||
return self.soil
|
||||
|
||||
def set_soil(self, soil):
|
||||
self.soil = soil
|
||||
self.soil = soil
|
||||
|
||||
@ -10,10 +10,13 @@ import pygame
|
||||
import random
|
||||
import station
|
||||
import treelearn
|
||||
|
||||
|
||||
def create_genetic_algorithm():
|
||||
if os.path.exists("resources/genetic_algorithm/optimalastar.pkl"): #jeżeli algorytm genetyczny utworzył plik wcześcniej to odczytaj
|
||||
if os.path.exists(
|
||||
"resources/genetic_algorithm/optimalastar.pkl"): # jeżeli algorytm genetyczny utworzył plik wcześcniej to odczytaj
|
||||
astar_costs = pickle.load(open(os.path.join('resources/genetic_algorithm', "optimalastar.pkl"), "rb"))
|
||||
#kolejność alfabetyczna
|
||||
# kolejność alfabetyczna
|
||||
definitions.BEETROOTS_ADULT_COST = astar_costs[0]
|
||||
definitions.BEETROOTS_GROW_COST = astar_costs[1]
|
||||
definitions.CARROTS_ADULT_COST = astar_costs[2]
|
||||
@ -27,31 +30,39 @@ def create_genetic_algorithm():
|
||||
definitions.STATION_COST = astar_costs[10]
|
||||
definitions.WHEAT_ADULT_COST = astar_costs[11]
|
||||
definitions.WHEAT_GROW_COST = astar_costs[12]
|
||||
else: #w przeciwnym razie ucz algorytmem genetycznym
|
||||
astar_costs = [definitions.BEETROOTS_ADULT_COST, definitions.BEETROOTS_GROW_COST, definitions.CARROTS_ADULT_COST, definitions.CARROTS_GROW_COST, definitions.DIRT_COST, definitions.FARMLAND_DRY_COST, definitions.FARMLAND_WET_COST, definitions.FLOWER_DANDELION_COST, definitions.POTATOES_ADULT_COST, definitions.POTATOES_GROW_COST, definitions.STATION_COST, definitions.WHEAT_ADULT_COST, definitions.WHEAT_GROW_COST] #kolejność alfabetyczna
|
||||
else: # w przeciwnym razie ucz algorytmem genetycznym
|
||||
astar_costs = [definitions.BEETROOTS_ADULT_COST, definitions.BEETROOTS_GROW_COST,
|
||||
definitions.CARROTS_ADULT_COST, definitions.CARROTS_GROW_COST, definitions.DIRT_COST,
|
||||
definitions.FARMLAND_DRY_COST, definitions.FARMLAND_WET_COST, definitions.FLOWER_DANDELION_COST,
|
||||
definitions.POTATOES_ADULT_COST, definitions.POTATOES_GROW_COST, definitions.STATION_COST,
|
||||
definitions.WHEAT_ADULT_COST, definitions.WHEAT_GROW_COST] # kolejność alfabetyczna
|
||||
astar_costs = evolve(astar_costs)
|
||||
pickle.dump(astar_costs, open(os.path.join('resources/genetic_algorithm', "optimalastar.pkl"), "wb"))
|
||||
|
||||
|
||||
def evolve(astar_costs):
|
||||
first_generation = [] #pierwsza generacja
|
||||
overall_solutions = [] #rozwiązania końcowe
|
||||
solutions = [] #rozwiązania danej generacji
|
||||
for individual in range(definitions.GENETIC_ALGORITHM_NUMBER_OF_INDIVIDUALS_ZERO): #liczba osobników pierwszej generacji
|
||||
first_generation = [] # pierwsza generacja
|
||||
overall_solutions = [] # rozwiązania końcowe
|
||||
solutions = [] # rozwiązania danej generacji
|
||||
for individual in range(
|
||||
definitions.GENETIC_ALGORITHM_NUMBER_OF_INDIVIDUALS_ZERO): # liczba osobników pierwszej generacji
|
||||
for _ in range(definitions.GENETIC_ALGORITHM_COSTS_AMOUNT):
|
||||
first_generation.append(random.uniform(0, 10))
|
||||
solutions.append(first_generation) #generowanie losowych kosztów pól dla pierwszej generacji
|
||||
for gen in range(definitions.GENETIC_ALGORITHM_NUMBER_OF_GENERATIONS): #liczba generacji
|
||||
solutions.append(first_generation) # generowanie losowych kosztów pól dla pierwszej generacji
|
||||
for gen in range(definitions.GENETIC_ALGORITHM_NUMBER_OF_GENERATIONS): # liczba generacji
|
||||
print(f"=== Generation {gen + 1} ===")
|
||||
ranked_solutions = [] #rozwiązania z wynikiem
|
||||
ranked_solutions = [] # rozwiązania z wynikiem
|
||||
index = 0
|
||||
for s in solutions: #przypisanie rozwiązaniom wyniku funkcji fitness
|
||||
for s in solutions: # przypisanie rozwiązaniom wyniku funkcji fitness
|
||||
ranked_solutions.append((fitness(s, index), s))
|
||||
index = index + 1
|
||||
ranked_solutions.sort()
|
||||
print(f"=== Gen {gen + 1} best solution ===")
|
||||
print(ranked_solutions[0])
|
||||
overall_solutions.append(ranked_solutions[0])
|
||||
#TODO warunek stopu
|
||||
best_solutions = ranked_solutions[:definitions.GENETIC_ALGORITHM_NUMBER_OF_BEST_INDIVIDUALS] #najlepsze osobniki w danej generacji
|
||||
# TODO warunek stopu
|
||||
best_solutions = ranked_solutions[
|
||||
:definitions.GENETIC_ALGORITHM_NUMBER_OF_BEST_INDIVIDUALS] # najlepsze osobniki w danej generacji
|
||||
elements = []
|
||||
for element in range(definitions.GENETIC_ALGORITHM_COSTS_AMOUNT):
|
||||
elems = []
|
||||
@ -59,26 +70,31 @@ def evolve(astar_costs):
|
||||
for solution in best_solutions:
|
||||
for element in range(definitions.GENETIC_ALGORITHM_COSTS_AMOUNT):
|
||||
elements[element].append(solution[1][element])
|
||||
next_generation = [] #nowa ganeracja
|
||||
next_generation = [] # nowa ganeracja
|
||||
e = []
|
||||
for individual in range(definitions.GENETIC_ALGORITHM_NUMBER_OF_INDIVIDUALS): #liczba osobników w kolejnej generacji
|
||||
for individual in range(
|
||||
definitions.GENETIC_ALGORITHM_NUMBER_OF_INDIVIDUALS): # liczba osobników w kolejnej generacji
|
||||
for el in range(definitions.GENETIC_ALGORITHM_COSTS_AMOUNT):
|
||||
#mutacje
|
||||
# mutacje
|
||||
e.append(random.choice(elements[el]) * random.uniform(0.99, 1.01))
|
||||
next_generation.append(e)
|
||||
solutions = next_generation #zastąpnienie osobników nową generacją
|
||||
solutions = next_generation # zastąpnienie osobników nową generacją
|
||||
overall_solutions.sort()
|
||||
for _ in range(definitions.GENETIC_ALGORITHM_COSTS_AMOUNT): #przyspianie finalnych kosztów astara
|
||||
for _ in range(definitions.GENETIC_ALGORITHM_COSTS_AMOUNT): # przyspianie finalnych kosztów astara
|
||||
astar_costs[_] = overall_solutions[0][1][_]
|
||||
return astar_costs
|
||||
|
||||
|
||||
def fitness(astar_costs, index):
|
||||
ans = harvest(astar_costs, index)
|
||||
if ans == 0: #TODO
|
||||
if ans == 0: # TODO
|
||||
return 0
|
||||
else:
|
||||
return 1 / ans
|
||||
|
||||
|
||||
def harvest(astar_costs, index):
|
||||
#kolejność alfabetyczna
|
||||
# kolejność alfabetyczna
|
||||
definitions.BEETROOTS_ADULT_COST = astar_costs[0]
|
||||
definitions.BEETROOTS_GROW_COST = astar_costs[1]
|
||||
definitions.CARROTS_ADULT_COST = astar_costs[2]
|
||||
@ -92,41 +108,69 @@ def harvest(astar_costs, index):
|
||||
definitions.STATION_COST = astar_costs[10]
|
||||
definitions.WHEAT_ADULT_COST = astar_costs[11]
|
||||
definitions.WHEAT_GROW_COST = astar_costs[12]
|
||||
#tworzenie podstawowych obiektów
|
||||
# tworzenie podstawowych obiektów
|
||||
map1 = map.Map([])
|
||||
map1.create_base_map()
|
||||
move_list = ["rotate_left", "move", "move", "move", "move", "move", "move", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "move", "move", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move"] #początkowe ruchy
|
||||
amount_of_seeds_dict = {"beetroot": definitions.CART_AMOUNT_OF_SEEDS_EACH_TYPE, "carrot": definitions.CART_AMOUNT_OF_SEEDS_EACH_TYPE, "potato": definitions.CART_AMOUNT_OF_SEEDS_EACH_TYPE, "wheat": definitions.CART_AMOUNT_OF_SEEDS_EACH_TYPE}
|
||||
move_list = ["rotate_left", "move", "move", "move", "move", "move", "move", "rotate_left", "rotate_left", "move",
|
||||
"rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left",
|
||||
"rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move",
|
||||
"rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left",
|
||||
"rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move",
|
||||
"rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "move",
|
||||
"rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left",
|
||||
"rotate_left", "rotate_left", "move", "move", "rotate_left", "rotate_left", "rotate_left",
|
||||
"rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move",
|
||||
"rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move",
|
||||
"rotate_left", "rotate_left", "move", "move", "move", "rotate_left", "rotate_left", "rotate_left",
|
||||
"rotate_left", "rotate_left", "move", "move", "rotate_left", "rotate_left", "rotate_left",
|
||||
"rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move",
|
||||
"rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left",
|
||||
"rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left",
|
||||
"move"] # początkowe ruchy
|
||||
amount_of_seeds_dict = {"beetroot": definitions.CART_AMOUNT_OF_SEEDS_EACH_TYPE,
|
||||
"carrot": definitions.CART_AMOUNT_OF_SEEDS_EACH_TYPE,
|
||||
"potato": definitions.CART_AMOUNT_OF_SEEDS_EACH_TYPE,
|
||||
"wheat": definitions.CART_AMOUNT_OF_SEEDS_EACH_TYPE}
|
||||
collected_plants_dict_cart = {"beetroot": 0, "carrot": 0, "potato": 0, "wheat": 0}
|
||||
collected_plants_dict_station = {"beetroot": 0, "carrot": 0, "potato": 0, "wheat": 0}
|
||||
fertilizer_dict = {"beetroot": definitions.CART_FERTILIZER, "carrot": definitions.CART_FERTILIZER, "potato": definitions.CART_FERTILIZER, "wheat": definitions.CART_FERTILIZER}
|
||||
fertilizer_dict = {"beetroot": definitions.CART_FERTILIZER, "carrot": definitions.CART_FERTILIZER,
|
||||
"potato": definitions.CART_FERTILIZER, "wheat": definitions.CART_FERTILIZER}
|
||||
station1 = station.Station(collected_plants_dict_station)
|
||||
cart1 = cart.Cart(amount_of_seeds_dict, collected_plants_dict_cart, definitions.CART_DIRECTION_WEST, fertilizer_dict, definitions.CART_FUEL, definitions.CART_WATER_LEVEL, 0 * definitions.BLOCK_SIZE, 0 * definitions.BLOCK_SIZE)
|
||||
cart1 = cart.Cart(amount_of_seeds_dict, collected_plants_dict_cart, definitions.CART_DIRECTION_WEST,
|
||||
fertilizer_dict, definitions.CART_FUEL, definitions.CART_WATER_LEVEL, 0 * definitions.BLOCK_SIZE,
|
||||
0 * definitions.BLOCK_SIZE)
|
||||
cart1_rect = pygame.Rect(cart1.get_x(), cart1.get_y(), definitions.BLOCK_SIZE, definitions.BLOCK_SIZE)
|
||||
tree = treelearn.treelearn() #tworzenie drzewa decyzyjnego
|
||||
decision = [0] #początkowa decyzja o braku powrotu do stacji (0)
|
||||
tree = treelearn.treelearn() # tworzenie drzewa decyzyjnego
|
||||
decision = [0] # początkowa decyzja o braku powrotu do stacji (0)
|
||||
grow_flower_dandelion = False
|
||||
random_movement = False
|
||||
for run in range(definitions.GENETIC_ALGORITHM_NUMBER_OF_CART_MOVES): #liczba ruchów wózka
|
||||
if not move_list: #jeżeli są jakieś ruchy do wykonania w move_list
|
||||
for run in range(definitions.GENETIC_ALGORITHM_NUMBER_OF_CART_MOVES): # liczba ruchów wózka
|
||||
if not move_list: # jeżeli są jakieś ruchy do wykonania w move_list
|
||||
grow_flower_dandelion = True
|
||||
istate = graph.Istate(cart1.get_direction(), cart1.get_x() / definitions.BLOCK_SIZE, cart1.get_y() / definitions.BLOCK_SIZE) #stan początkowy wózka (jego orientacja oraz jego aktualne miejsce)
|
||||
if plant.Plant.if_any_mature_plant(map1) is True: #jeżeli istnieje jakaś dojrzała roślina
|
||||
istate = graph.Istate(cart1.get_direction(), cart1.get_x() / definitions.BLOCK_SIZE,
|
||||
cart1.get_y() / definitions.BLOCK_SIZE) # stan początkowy wózka (jego orientacja oraz jego aktualne miejsce)
|
||||
if plant.Plant.if_any_mature_plant(map1) is True: # jeżeli istnieje jakaś dojrzała roślina
|
||||
random_movement = False
|
||||
if decision == [0]: #jeżeli decyzja jest 0 (brak powrotu do stacji) to uprawiaj pole
|
||||
move_list = (astar.graphsearch([], astar.f, [], plant.Plant.get_closest_mature_plant(istate, map1), istate, map1, graph.succ)) #lista z ruchami, które należy po kolei wykonać, astar
|
||||
else: #jeżeli decyzja jest 1 (powrót do stacji) to wróć do stacji uzupełnić zapasy
|
||||
move_list = (graph.graphsearch([], [], (0, 0), istate, graph.succ)) #lista z ruchami, które należy po kolei wykonać, graphsearch
|
||||
if decision == [0]: # jeżeli decyzja jest 0 (brak powrotu do stacji) to uprawiaj pole
|
||||
move_list = (
|
||||
astar.graphsearch([], astar.f, [], plant.Plant.get_closest_mature_plant(istate, map1), istate,
|
||||
map1, graph.succ)) # lista z ruchami, które należy po kolei wykonać, astar
|
||||
else: # jeżeli decyzja jest 1 (powrót do stacji) to wróć do stacji uzupełnić zapasy
|
||||
move_list = (graph.graphsearch([], [], (0, 0), istate,
|
||||
graph.succ)) # lista z ruchami, które należy po kolei wykonać, graphsearch
|
||||
else:
|
||||
random_movement = True
|
||||
elif move_list: #jeżeli move_list nie jest pusta
|
||||
cart1.handle_movement(cart1_rect, move_list.pop(0)) #wykonaj kolejny ruch oraz zdejmij ten ruch z początku listy
|
||||
elif move_list: # jeżeli move_list nie jest pusta
|
||||
cart1.handle_movement(cart1_rect,
|
||||
move_list.pop(0)) # wykonaj kolejny ruch oraz zdejmij ten ruch z początku listy
|
||||
if random_movement is True:
|
||||
cart1.handle_movement_random(cart1_rect) #wykonuj losowe ruchy
|
||||
cart1.handle_movement_random(cart1_rect) # wykonuj losowe ruchy
|
||||
if grow_flower_dandelion is True:
|
||||
plant.Plant.grow_flower_dandelion(map1) #losuj urośnięcie kwiatka dandeliona
|
||||
cart1.do_work(cart1_rect, map1, station1) #wykonaj pracę na danym polu
|
||||
decision = treelearn.make_decision(cart1.get_all_amount_of_seeds(), cart1.get_all_collected_plants(), cart1.get_all_fertilizer(), cart1.get_fuel(), tree, cart1.get_water_level()) #podejmij decyzję czy wracać do stacji (0 : NIE, 1 : TAK)
|
||||
plant.Plant.grow_plants(map1) #zwiększ poziom dojrzałości roślin
|
||||
plant.Plant.grow_flower_dandelion(map1) # losuj urośnięcie kwiatka dandeliona
|
||||
cart1.do_work(cart1_rect, map1, station1) # wykonaj pracę na danym polu
|
||||
decision = treelearn.make_decision(cart1.get_all_amount_of_seeds(), cart1.get_all_collected_plants(),
|
||||
cart1.get_all_fertilizer(), cart1.get_fuel(), tree,
|
||||
cart1.get_water_level()) # podejmij decyzję czy wracać do stacji (0 : NIE, 1 : TAK)
|
||||
plant.Plant.grow_plants(map1) # zwiększ poziom dojrzałości roślin
|
||||
print("individual no.", index + 1, "score:", station1.get_all_collected_plants())
|
||||
return station1.get_all_collected_plants()
|
||||
return station1.get_all_collected_plants()
|
||||
|
||||
70
graph.py
70
graph.py
@ -1,83 +1,117 @@
|
||||
import cart
|
||||
import copy
|
||||
class Istate: #stan początkowy wózka (strona, w którą patrzy, miejsce, w którym się on znajduje)
|
||||
|
||||
|
||||
class Istate: # stan początkowy wózka (strona, w którą patrzy, miejsce, w którym się on znajduje)
|
||||
def __init__(self, direction, x, y):
|
||||
self.direction = direction
|
||||
self.x = x
|
||||
self.y = y
|
||||
|
||||
def get_direction(self):
|
||||
return self.direction
|
||||
|
||||
def set_direction(self, direction):
|
||||
self.direction = direction
|
||||
|
||||
def get_x(self):
|
||||
return self.x
|
||||
|
||||
def set_x(self, x):
|
||||
self.x = x
|
||||
|
||||
def get_y(self):
|
||||
return self.y
|
||||
|
||||
def set_y(self, y):
|
||||
self.y = y
|
||||
class Node: #wierzchołek grafu
|
||||
|
||||
|
||||
class Node: # wierzchołek grafu
|
||||
def __init__(self, action, direction, parent, x, y):
|
||||
self.action = action #akcja jaką ma wykonać (obróc się w lewo, obróć się w prawo, ruch do przodu)
|
||||
self.action = action # akcja jaką ma wykonać (obróc się w lewo, obróć się w prawo, ruch do przodu)
|
||||
self.direction = direction
|
||||
self.parent = parent #ojciec wierzchołka
|
||||
self.parent = parent # ojciec wierzchołka
|
||||
self.x = x
|
||||
self.y = y
|
||||
|
||||
def get_action(self):
|
||||
return self.action
|
||||
|
||||
def set_action(self, action):
|
||||
self.action = action
|
||||
|
||||
def get_direction(self):
|
||||
return self.direction
|
||||
|
||||
def set_direction(self, direction):
|
||||
self.direction = direction
|
||||
|
||||
def get_parent(self):
|
||||
return self.parent
|
||||
|
||||
def set_parent(self, parent):
|
||||
self.parent = parent
|
||||
|
||||
def get_x(self):
|
||||
return self.x
|
||||
|
||||
def set_x(self, x):
|
||||
self.x = x
|
||||
|
||||
def get_y(self):
|
||||
return self.y
|
||||
|
||||
def set_y(self, y):
|
||||
self.y = y
|
||||
def goal_test(goaltest, elem): #funkcja sprawdzająca czy położenie wózka równa się położeniu punktu docelowego, jeśli tak zwraca prawdę, w przeciwnym wypadku fałsz
|
||||
|
||||
|
||||
def goal_test(goaltest,
|
||||
elem): # funkcja sprawdzająca czy położenie wózka równa się położeniu punktu docelowego, jeśli tak zwraca prawdę, w przeciwnym wypadku fałsz
|
||||
if elem.get_x() == goaltest[0] and elem.get_y() == goaltest[1]:
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
def graphsearch(explored, fringe, goaltest, istate, succ): #przeszukiwanie grafu wszerz
|
||||
node = Node(None, istate.get_direction(), None, istate.get_x(), istate.get_y()) #wierzchołek początkowy, stworzony ze stanu początkowego wózka
|
||||
fringe.append(node) #wierzchołki do odwiedzenia
|
||||
|
||||
|
||||
def graphsearch(explored, fringe, goaltest, istate, succ): # przeszukiwanie grafu wszerz
|
||||
node = Node(None, istate.get_direction(), None, istate.get_x(),
|
||||
istate.get_y()) # wierzchołek początkowy, stworzony ze stanu początkowego wózka
|
||||
fringe.append(node) # wierzchołki do odwiedzenia
|
||||
while True:
|
||||
if not fringe:
|
||||
return False
|
||||
elem = fringe.pop(0) #zdejmujemy wierzchołek z kolejki fringe i rozpatrujemy go
|
||||
elem = fringe.pop(0) # zdejmujemy wierzchołek z kolejki fringe i rozpatrujemy go
|
||||
temp = copy.copy(elem)
|
||||
if goal_test(goaltest, elem) is True: #jeżeli osiągniemy cel w trakcie przeszukiwania grafu wszerz (wjedziemy na pole docelowe) : zwracamy listę ruchów, po których wykonaniu dotrzemy na miejsce
|
||||
if goal_test(goaltest,
|
||||
elem) is True: # jeżeli osiągniemy cel w trakcie przeszukiwania grafu wszerz (wjedziemy na pole docelowe) : zwracamy listę ruchów, po których wykonaniu dotrzemy na miejsce
|
||||
return print_moves(elem)
|
||||
explored.append(elem) #dodajemy wierzchołek do listy wierzchołków odwiedzonych
|
||||
for (action, state) in succ(temp): #iterujemy po wszystkich możliwych akcjach i stanach otrzymanych dla danego wierzchołka grafu
|
||||
explored.append(elem) # dodajemy wierzchołek do listy wierzchołków odwiedzonych
|
||||
for (action, state) in succ(
|
||||
temp): # iterujemy po wszystkich możliwych akcjach i stanach otrzymanych dla danego wierzchołka grafu
|
||||
fringe_tuple = []
|
||||
explored_tuple = []
|
||||
for x in fringe:
|
||||
fringe_tuple.append((x.get_direction(), x.get_x(), x.get_y()))
|
||||
for x in explored:
|
||||
explored_tuple.append((x.get_direction(), x.get_x(), x.get_y()))
|
||||
if state not in fringe_tuple and state not in explored_tuple: #jeżeli stan nie znajduje się na fringe oraz nie znajduje się w liście wierzchołków odwiedzonych
|
||||
x = Node(action, state[0], elem, state[1], state[2]) #stworzenie nowego wierzchołka, którego rodzicem jest elem
|
||||
fringe.append(x) #dodanie wierzchołka na fringe
|
||||
def print_moves(elem): #zwraca listę ruchów jakie należy wykonać by dotrzeć do punktu docelowego
|
||||
if state not in fringe_tuple and state not in explored_tuple: # jeżeli stan nie znajduje się na fringe oraz nie znajduje się w liście wierzchołków odwiedzonych
|
||||
x = Node(action, state[0], elem, state[1],
|
||||
state[2]) # stworzenie nowego wierzchołka, którego rodzicem jest elem
|
||||
fringe.append(x) # dodanie wierzchołka na fringe
|
||||
|
||||
|
||||
def print_moves(elem): # zwraca listę ruchów jakie należy wykonać by dotrzeć do punktu docelowego
|
||||
moves_list = []
|
||||
while (elem.get_parent() != None):
|
||||
moves_list.append(elem.get_action())
|
||||
elem = elem.get_parent()
|
||||
moves_list.reverse()
|
||||
return moves_list
|
||||
def succ(elem): #funkcja następnika, przypisuje jakie akcje są możliwe do wykonania na danym polu oraz jaki będzie stan (kierunek, położenie) po wykonaniu tej akcji
|
||||
|
||||
|
||||
def succ(
|
||||
elem): # funkcja następnika, przypisuje jakie akcje są możliwe do wykonania na danym polu oraz jaki będzie stan (kierunek, położenie) po wykonaniu tej akcji
|
||||
actions_list = []
|
||||
temp = copy.copy(elem.get_direction())
|
||||
if temp == 1:
|
||||
@ -103,4 +137,4 @@ def succ(elem): #funkcja następnika, przypisuje jakie akcje są możliwe do wyk
|
||||
actions_list.append(("move", (elem.get_direction(), elem.get_x(), temp_move_south)))
|
||||
elif cart.Cart.is_move_allowed_succ(elem) == "x - 1":
|
||||
actions_list.append(("move", (elem.get_direction(), temp_move_west, elem.get_y())))
|
||||
return actions_list
|
||||
return actions_list
|
||||
|
||||
59
map.py
59
map.py
@ -3,18 +3,24 @@ import field
|
||||
import plant
|
||||
import pygame
|
||||
import soil
|
||||
|
||||
|
||||
class Map:
|
||||
def __init__(self, fields):
|
||||
self.fields = fields #przechowuje wszystkie pola (Field)
|
||||
self.fields = fields # przechowuje wszystkie pola (Field)
|
||||
|
||||
def get_fields(self):
|
||||
return self.fields
|
||||
|
||||
def set_fields(self, fields):
|
||||
self.fields = fields
|
||||
def create_base_map(self): #wypełnia mapę polami z bazowymi logicznymi wartościami
|
||||
|
||||
def create_base_map(self): # wypełnia mapę polami z bazowymi logicznymi wartościami
|
||||
for i in range(definitions.WIDTH_AMOUNT):
|
||||
temp_map_field = []
|
||||
for j in range(definitions.HEIGHT_AMOUNT):
|
||||
temp_rect = pygame.Rect(i * definitions.BLOCK_SIZE, j * definitions.BLOCK_SIZE, definitions.BLOCK_SIZE, definitions.BLOCK_SIZE)
|
||||
temp_rect = pygame.Rect(i * definitions.BLOCK_SIZE, j * definitions.BLOCK_SIZE, definitions.BLOCK_SIZE,
|
||||
definitions.BLOCK_SIZE)
|
||||
if i == 0 and j == 0:
|
||||
temp_plant = plant.Plant("station", -1)
|
||||
else:
|
||||
@ -23,7 +29,8 @@ class Map:
|
||||
temp_field = field.Field(temp_plant, temp_rect, temp_soil)
|
||||
temp_map_field.append(temp_field)
|
||||
self.fields.append(temp_map_field)
|
||||
def draw_window(self, cart, cart_rect, station): #rysuje mapę
|
||||
|
||||
def draw_window(self, cart, cart_rect, station): # rysuje mapę
|
||||
self.fill_map(station)
|
||||
if cart.get_direction() == definitions.CART_DIRECTION_EAST:
|
||||
definitions.WINDOW.blit(definitions.CART_DIRECTION_EAST_TEXTURE, (cart_rect.x, cart_rect.y))
|
||||
@ -34,7 +41,8 @@ class Map:
|
||||
elif cart.get_direction() == definitions.CART_DIRECTION_WEST:
|
||||
definitions.WINDOW.blit(definitions.CART_DIRECTION_WEST_TEXTURE, (cart_rect.x, cart_rect.y))
|
||||
pygame.display.update()
|
||||
def fill_map(self, station): #wypełnia mapę teksturami na podstawie logicznego stanu pól
|
||||
|
||||
def fill_map(self, station): # wypełnia mapę teksturami na podstawie logicznego stanu pól
|
||||
for i in range(definitions.WIDTH_AMOUNT):
|
||||
for j in range(definitions.HEIGHT_AMOUNT):
|
||||
field = self.fields[i][j]
|
||||
@ -103,40 +111,53 @@ class Map:
|
||||
definitions.WINDOW.blit(block, (rect.x, rect.y))
|
||||
for i in range(definitions.WIDTH_AMOUNT):
|
||||
block = definitions.SPONGE_WET
|
||||
definitions.WINDOW.blit(block, (i * definitions.BLOCK_SIZE, definitions.HEIGHT_AMOUNT * definitions.BLOCK_SIZE))
|
||||
definitions.WINDOW.blit(block,
|
||||
(i * definitions.BLOCK_SIZE, definitions.HEIGHT_AMOUNT * definitions.BLOCK_SIZE))
|
||||
if i == 1:
|
||||
block = definitions.BEETROOT
|
||||
definitions.WINDOW.blit(block, (i * definitions.BLOCK_SIZE, definitions.HEIGHT_AMOUNT * definitions.BLOCK_SIZE))
|
||||
definitions.WINDOW.blit(block, (
|
||||
i * definitions.BLOCK_SIZE, definitions.HEIGHT_AMOUNT * definitions.BLOCK_SIZE))
|
||||
elif i == 2:
|
||||
text = definitions.FONT.render(str(station.get_collected_plants("beetroot")), True, definitions.FONT_COLOR)
|
||||
text = definitions.FONT.render(str(station.get_collected_plants("beetroot")), True,
|
||||
definitions.FONT_COLOR)
|
||||
text_rect = text.get_rect()
|
||||
text_rect.center = (i * definitions.BLOCK_SIZE + definitions.BLOCK_SIZE / 2, definitions.HEIGHT_AMOUNT * definitions.BLOCK_SIZE + definitions.BLOCK_SIZE / 2)
|
||||
text_rect.center = (i * definitions.BLOCK_SIZE + definitions.BLOCK_SIZE / 2,
|
||||
definitions.HEIGHT_AMOUNT * definitions.BLOCK_SIZE + definitions.BLOCK_SIZE / 2)
|
||||
definitions.WINDOW.blit(text, text_rect)
|
||||
elif i == 3:
|
||||
block = definitions.CARROT
|
||||
definitions.WINDOW.blit(block, (i * definitions.BLOCK_SIZE, definitions.HEIGHT_AMOUNT * definitions.BLOCK_SIZE))
|
||||
definitions.WINDOW.blit(block, (
|
||||
i * definitions.BLOCK_SIZE, definitions.HEIGHT_AMOUNT * definitions.BLOCK_SIZE))
|
||||
elif i == 4:
|
||||
text = definitions.FONT.render(str(station.get_collected_plants("carrot")), True, definitions.FONT_COLOR)
|
||||
text = definitions.FONT.render(str(station.get_collected_plants("carrot")), True,
|
||||
definitions.FONT_COLOR)
|
||||
text_rect = text.get_rect()
|
||||
text_rect.center = (i * definitions.BLOCK_SIZE + definitions.BLOCK_SIZE / 2, definitions.HEIGHT_AMOUNT * definitions.BLOCK_SIZE + definitions.BLOCK_SIZE / 2)
|
||||
text_rect.center = (i * definitions.BLOCK_SIZE + definitions.BLOCK_SIZE / 2,
|
||||
definitions.HEIGHT_AMOUNT * definitions.BLOCK_SIZE + definitions.BLOCK_SIZE / 2)
|
||||
definitions.WINDOW.blit(text, text_rect)
|
||||
elif i == 5:
|
||||
block = definitions.POTATO
|
||||
definitions.WINDOW.blit(block, (i * definitions.BLOCK_SIZE, definitions.HEIGHT_AMOUNT * definitions.BLOCK_SIZE))
|
||||
definitions.WINDOW.blit(block, (
|
||||
i * definitions.BLOCK_SIZE, definitions.HEIGHT_AMOUNT * definitions.BLOCK_SIZE))
|
||||
elif i == 6:
|
||||
text = definitions.FONT.render(str(station.get_collected_plants("potato")), True, definitions.FONT_COLOR)
|
||||
text = definitions.FONT.render(str(station.get_collected_plants("potato")), True,
|
||||
definitions.FONT_COLOR)
|
||||
text_rect = text.get_rect()
|
||||
text_rect.center = (i * definitions.BLOCK_SIZE + definitions.BLOCK_SIZE / 2, definitions.HEIGHT_AMOUNT * definitions.BLOCK_SIZE + definitions.BLOCK_SIZE / 2)
|
||||
text_rect.center = (i * definitions.BLOCK_SIZE + definitions.BLOCK_SIZE / 2,
|
||||
definitions.HEIGHT_AMOUNT * definitions.BLOCK_SIZE + definitions.BLOCK_SIZE / 2)
|
||||
definitions.WINDOW.blit(text, text_rect)
|
||||
elif i == 7:
|
||||
block = definitions.WHEAT
|
||||
definitions.WINDOW.blit(block, (i * definitions.BLOCK_SIZE, definitions.HEIGHT_AMOUNT * definitions.BLOCK_SIZE))
|
||||
definitions.WINDOW.blit(block, (
|
||||
i * definitions.BLOCK_SIZE, definitions.HEIGHT_AMOUNT * definitions.BLOCK_SIZE))
|
||||
elif i == 8:
|
||||
text = definitions.FONT.render(str(station.get_collected_plants("wheat")), True, definitions.FONT_COLOR)
|
||||
text_rect = text.get_rect()
|
||||
text_rect.center = (i * definitions.BLOCK_SIZE + definitions.BLOCK_SIZE / 2, definitions.HEIGHT_AMOUNT * definitions.BLOCK_SIZE + definitions.BLOCK_SIZE / 2)
|
||||
text_rect.center = (i * definitions.BLOCK_SIZE + definitions.BLOCK_SIZE / 2,
|
||||
definitions.HEIGHT_AMOUNT * definitions.BLOCK_SIZE + definitions.BLOCK_SIZE / 2)
|
||||
definitions.WINDOW.blit(text, text_rect)
|
||||
def get_field_cost(self, x, y): #zwraca koszt danego pola
|
||||
|
||||
def get_field_cost(self, x, y): # zwraca koszt danego pola
|
||||
field = self.fields[x][y]
|
||||
if field.get_plant().get_name() == "station" and field.get_plant().get_state() == -1:
|
||||
return definitions.STATION_COST
|
||||
@ -163,4 +184,4 @@ class Map:
|
||||
elif field.get_soil().get_state() is True and field.get_soil().get_water_level() is False:
|
||||
return definitions.FARMLAND_DRY_COST
|
||||
elif field.get_soil().get_state() is True and field.get_soil().get_water_level() is True:
|
||||
return definitions.FARMLAND_WET_COST
|
||||
return definitions.FARMLAND_WET_COST
|
||||
|
||||
@ -11,7 +11,12 @@ import pathlib
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torchvision
|
||||
transformer1 = transforms.Compose([transforms.Resize((definitions.IMAGE_SIZE_NEURAL_NETWORK, definitions.IMAGE_SIZE_NEURAL_NETWORK)), transforms.ToTensor(), transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])])
|
||||
|
||||
transformer1 = transforms.Compose(
|
||||
[transforms.Resize((definitions.IMAGE_SIZE_NEURAL_NETWORK, definitions.IMAGE_SIZE_NEURAL_NETWORK)),
|
||||
transforms.ToTensor(), transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])])
|
||||
|
||||
|
||||
class ConvNet(nn.Module):
|
||||
def __init__(self, num_classes=6):
|
||||
super(ConvNet, self).__init__()
|
||||
@ -24,7 +29,9 @@ class ConvNet(nn.Module):
|
||||
self.conv3 = nn.Conv2d(in_channels=20, out_channels=32, kernel_size=3, stride=1, padding=1)
|
||||
self.bn3 = nn.BatchNorm2d(num_features=32)
|
||||
self.relu3 = nn.ReLU()
|
||||
self.fc = nn.Linear(in_features=int(definitions.IMAGE_SIZE_NEURAL_NETWORK / 2) * int(definitions.IMAGE_SIZE_NEURAL_NETWORK / 2) * 32, out_features=num_classes)
|
||||
self.fc = nn.Linear(in_features=int(definitions.IMAGE_SIZE_NEURAL_NETWORK / 2) * int(
|
||||
definitions.IMAGE_SIZE_NEURAL_NETWORK / 2) * 32, out_features=num_classes)
|
||||
|
||||
def forward(self, input):
|
||||
output = self.conv1(input)
|
||||
output = self.bn1(output)
|
||||
@ -35,30 +42,38 @@ class ConvNet(nn.Module):
|
||||
output = self.conv3(output)
|
||||
output = self.bn3(output)
|
||||
output = self.relu3(output)
|
||||
output = output.view(-1, 32 * int(definitions.IMAGE_SIZE_NEURAL_NETWORK / 2) * int(definitions.IMAGE_SIZE_NEURAL_NETWORK / 2))
|
||||
output = output.view(-1, 32 * int(definitions.IMAGE_SIZE_NEURAL_NETWORK / 2) * int(
|
||||
definitions.IMAGE_SIZE_NEURAL_NETWORK / 2))
|
||||
output = self.fc(output)
|
||||
return output
|
||||
def create_neural_network(): #tworzenie sieci neuronowej
|
||||
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') #użyj cuda jeśli możliwe
|
||||
transformer = transforms.Compose([transforms.Resize((definitions.IMAGE_SIZE_NEURAL_NETWORK, definitions.IMAGE_SIZE_NEURAL_NETWORK)), transforms.RandomHorizontalFlip(), transforms.ToTensor(), transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])])
|
||||
train_path = os.path.join('resources/neural_network/train/') #ścieżka do obrazków do treningu
|
||||
test_path = os.path.join('resources/neural_network/test/') #ścieżka do obrazków do testu
|
||||
train_loader = DataLoader(torchvision.datasets.ImageFolder(train_path, transform=transformer), batch_size=64, shuffle=True)
|
||||
test_loader = DataLoader(torchvision.datasets.ImageFolder(test_path, transform=transformer), batch_size=32, shuffle=True)
|
||||
|
||||
|
||||
def create_neural_network(): # tworzenie sieci neuronowej
|
||||
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # użyj cuda jeśli możliwe
|
||||
transformer = transforms.Compose(
|
||||
[transforms.Resize((definitions.IMAGE_SIZE_NEURAL_NETWORK, definitions.IMAGE_SIZE_NEURAL_NETWORK)),
|
||||
transforms.RandomHorizontalFlip(), transforms.ToTensor(),
|
||||
transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])])
|
||||
train_path = os.path.join('resources/neural_network/train/') # ścieżka do obrazków do treningu
|
||||
test_path = os.path.join('resources/neural_network/test/') # ścieżka do obrazków do testu
|
||||
train_loader = DataLoader(torchvision.datasets.ImageFolder(train_path, transform=transformer), batch_size=64,
|
||||
shuffle=True)
|
||||
test_loader = DataLoader(torchvision.datasets.ImageFolder(test_path, transform=transformer), batch_size=32,
|
||||
shuffle=True)
|
||||
root = pathlib.Path(train_path)
|
||||
classes = sorted([j.name.split('/')[-1] for j in root.iterdir()])
|
||||
if os.path.exists("resources/neural_network/checkpoint.model"): #jeżeli istnieje model to wczytaj
|
||||
if os.path.exists("resources/neural_network/checkpoint.model"): # jeżeli istnieje model to wczytaj
|
||||
checkpoint = torch.load(os.path.join('resources/neural_network', 'checkpoint.model'))
|
||||
model = ConvNet(num_classes=6)
|
||||
model.load_state_dict(checkpoint)
|
||||
model.eval()
|
||||
else: #w przeciwnym razie utwórz nowy model
|
||||
else: # w przeciwnym razie utwórz nowy model
|
||||
model = ConvNet(num_classes=6).to(device)
|
||||
optimizer = Adam(model.parameters(), lr=0.001, weight_decay=0.0001)
|
||||
loss_function = nn.CrossEntropyLoss()
|
||||
num_epochs = 10
|
||||
train_count = len(glob.glob(train_path + '/**/*.png')) #liczba obrazków treningowych
|
||||
test_count = len(glob.glob(test_path + '/**/*.png')) #liczba obrazków testowych
|
||||
train_count = len(glob.glob(train_path + '/**/*.png')) # liczba obrazków treningowych
|
||||
test_count = len(glob.glob(test_path + '/**/*.png')) # liczba obrazków testowych
|
||||
best_accuracy = 0.0
|
||||
for epoch in range(num_epochs):
|
||||
model.train()
|
||||
@ -88,7 +103,8 @@ def create_neural_network(): #tworzenie sieci neuronowej
|
||||
_, prediction = torch.max(outputs.data, 1)
|
||||
test_accuracy += int(torch.sum(prediction == labels.data))
|
||||
test_accuracy = test_accuracy / test_count
|
||||
print('Epoch: ' + str(epoch + 1) + ' Train Loss: ' + str(train_loss) + ' Train Accuracy: ' + str(train_accuracy) + ' Test Accuracy: ' + str(test_accuracy))
|
||||
print('Epoch: ' + str(epoch + 1) + ' Train Loss: ' + str(train_loss) + ' Train Accuracy: ' + str(
|
||||
train_accuracy) + ' Test Accuracy: ' + str(test_accuracy))
|
||||
if test_accuracy > best_accuracy:
|
||||
torch.save(model.state_dict(), 'resources/neural_network/checkpoint.model')
|
||||
best_accuracy = test_accuracy
|
||||
@ -97,19 +113,22 @@ def create_neural_network(): #tworzenie sieci neuronowej
|
||||
model.load_state_dict(checkpoint)
|
||||
model.eval()
|
||||
return classes, model
|
||||
def predfield(classes, istate, model): #zwraca najbliższe miejsce pola z wyrośniętą rośliną na podstawie wykrywania obrazu
|
||||
pred_path = os.path.join('resources/neural_network/tiles/') #ścieżka do obrazków do sprawdzenia
|
||||
|
||||
|
||||
def predfield(classes, istate,
|
||||
model): # zwraca najbliższe miejsce pola z wyrośniętą rośliną na podstawie wykrywania obrazu
|
||||
pred_path = os.path.join('resources/neural_network/tiles/') # ścieżka do obrazków do sprawdzenia
|
||||
pred_dict = {}
|
||||
images_path = glob.glob(pred_path + '/*.png')
|
||||
x = None #x'owa pola
|
||||
y = None #y'kowa pola
|
||||
x = None # x'owa pola
|
||||
y = None # y'kowa pola
|
||||
x_position = 15
|
||||
y_position = 12
|
||||
min = None
|
||||
for i in images_path: #dodajemy pocięte obrazki do listy i ustawiamy im przewidywaną metkę
|
||||
for i in images_path: # dodajemy pocięte obrazki do listy i ustawiamy im przewidywaną metkę
|
||||
pred_dict[i[i.rfind('/') + 1:]] = prediction1(classes, i, model, transformer1)
|
||||
for img_name, field in pred_dict.items():
|
||||
if field != "random": #jeżeli metka nie jest 'random' to przypisz do x'a i y'a miejsce wyrośniętej rośliny
|
||||
if field != "random": # jeżeli metka nie jest 'random' to przypisz do x'a i y'a miejsce wyrośniętej rośliny
|
||||
if x is None and y is None:
|
||||
x = img_name[x_position]
|
||||
y = img_name[y_position]
|
||||
@ -141,11 +160,13 @@ def predfield(classes, istate, model): #zwraca najbliższe miejsce pola z wyroś
|
||||
min = len((graph.graphsearch([], [], (temp_x, temp_y), istate, graph.succ)))
|
||||
x = temp_x
|
||||
y = temp_y
|
||||
if x == None and y == None: #jeżeli nie ma wyrośniętej rośliny to zwróć fałsz
|
||||
if x == None and y == None: # jeżeli nie ma wyrośniętej rośliny to zwróć fałsz
|
||||
return False
|
||||
else:
|
||||
return x, y
|
||||
def prediction1(classes, img_path, model, transformer): #zwraca predykcję dla danego obrazka
|
||||
|
||||
|
||||
def prediction1(classes, img_path, model, transformer): # zwraca predykcję dla danego obrazka
|
||||
image = Image.open(img_path).convert('RGB')
|
||||
image_tensor = transformer(image).float()
|
||||
image_tensor = image_tensor.unsqueeze_(0)
|
||||
@ -155,4 +176,4 @@ def prediction1(classes, img_path, model, transformer): #zwraca predykcję dla d
|
||||
output = model(input)
|
||||
index = output.data.numpy().argmax()
|
||||
pred = classes[index]
|
||||
return pred
|
||||
return pred
|
||||
|
||||
31
plant.py
31
plant.py
@ -1,22 +1,30 @@
|
||||
import definitions
|
||||
import graph
|
||||
import random
|
||||
|
||||
|
||||
class Plant:
|
||||
def __init__(self, name, state):
|
||||
self.name = name #nazwa rośliny np. "wheat"
|
||||
self.state = state #etap rozwoju rośliny
|
||||
self.name = name # nazwa rośliny np. "wheat"
|
||||
self.state = state # etap rozwoju rośliny
|
||||
|
||||
def get_name(self):
|
||||
return self.name
|
||||
|
||||
def set_name(self, name):
|
||||
self.name = name
|
||||
|
||||
def get_state(self):
|
||||
return self.state
|
||||
|
||||
def set_state(self, state):
|
||||
self.state = state
|
||||
|
||||
@staticmethod
|
||||
def get_closest_mature_plant(istate, map): #pobiera miejsce najbliższej dojrzałej rośliny od miejsca, w którym znajduje się wózek
|
||||
x = None #x'owa pola
|
||||
y = None #y'kowa pola
|
||||
def get_closest_mature_plant(istate,
|
||||
map): # pobiera miejsce najbliższej dojrzałej rośliny od miejsca, w którym znajduje się wózek
|
||||
x = None # x'owa pola
|
||||
y = None # y'kowa pola
|
||||
min = None
|
||||
for i in range(definitions.WIDTH_AMOUNT):
|
||||
for j in range(definitions.HEIGHT_AMOUNT):
|
||||
@ -62,8 +70,9 @@ class Plant:
|
||||
y = j
|
||||
min = len((graph.graphsearch([], [], (x, y), istate, graph.succ)))
|
||||
return x, y
|
||||
|
||||
@staticmethod
|
||||
def grow_flower_dandelion(map): #metoda statyczna, losująca czy na danym polu ma urosnąć kwiat dandelion
|
||||
def grow_flower_dandelion(map): # metoda statyczna, losująca czy na danym polu ma urosnąć kwiat dandelion
|
||||
for i in range(definitions.WIDTH_AMOUNT):
|
||||
for j in range(definitions.HEIGHT_AMOUNT):
|
||||
field = map.get_fields()[i][j]
|
||||
@ -72,8 +81,10 @@ class Plant:
|
||||
if random1 <= definitions.FLOWER_DANDELION_GROW_PROBABILITY:
|
||||
field.get_plant().set_name("flower_dandelion")
|
||||
field.get_plant().set_state(definitions.FLOWER_DANDELION_MAXIMUM_STATE)
|
||||
|
||||
@staticmethod
|
||||
def grow_plants(map): #metoda statyczna, która zwiększa pole state (etap rozwoju rośliny) dla danej rośliny na danym polu o 1
|
||||
def grow_plants(
|
||||
map): # metoda statyczna, która zwiększa pole state (etap rozwoju rośliny) dla danej rośliny na danym polu o 1
|
||||
for i in range(definitions.WIDTH_AMOUNT):
|
||||
for j in range(definitions.HEIGHT_AMOUNT):
|
||||
field = map.get_fields()[i][j]
|
||||
@ -85,8 +96,10 @@ class Plant:
|
||||
field.get_plant().set_state(field.get_plant().get_state() + 1)
|
||||
elif field.get_plant().get_name() == "wheat" and field.get_plant().get_state() > 0 and field.get_plant().get_state() < definitions.WHEAT_MAXIMUM_STATE:
|
||||
field.get_plant().set_state(field.get_plant().get_state() + 1)
|
||||
|
||||
@staticmethod
|
||||
def if_any_mature_plant(map): #sprawdza czy na polu występuje choć jedna dojrzała roślina, jeśli tak zwraca prawdę, w przeciwnym razie zwraca fałsz
|
||||
def if_any_mature_plant(
|
||||
map): # sprawdza czy na polu występuje choć jedna dojrzała roślina, jeśli tak zwraca prawdę, w przeciwnym razie zwraca fałsz
|
||||
for i in range(definitions.WIDTH_AMOUNT):
|
||||
for j in range(definitions.HEIGHT_AMOUNT):
|
||||
field = map.get_fields()[i][j]
|
||||
@ -98,4 +111,4 @@ class Plant:
|
||||
return True
|
||||
elif field.get_plant().get_name() == "wheat" and field.get_plant().get_state() == definitions.WHEAT_MAXIMUM_STATE:
|
||||
return True
|
||||
return False
|
||||
return False
|
||||
|
||||
94
py.py
94
py.py
@ -11,64 +11,100 @@ import plant
|
||||
import pygame
|
||||
import station
|
||||
import treelearn
|
||||
|
||||
|
||||
def main():
|
||||
#inicjowanie pygame'a
|
||||
# inicjowanie pygame'a
|
||||
pygame.init()
|
||||
pygame.display.set_caption("Smart Cart")
|
||||
#tworzenie podstawowych obiektów
|
||||
# tworzenie podstawowych obiektów
|
||||
map1 = map.Map([])
|
||||
map1.create_base_map()
|
||||
move_list = ["rotate_left", "move", "move", "move", "move", "move", "move", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "move", "move", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move"] #początkowe ruchy
|
||||
amount_of_seeds_dict = {"beetroot": definitions.CART_AMOUNT_OF_SEEDS_EACH_TYPE, "carrot": definitions.CART_AMOUNT_OF_SEEDS_EACH_TYPE, "potato": definitions.CART_AMOUNT_OF_SEEDS_EACH_TYPE, "wheat": definitions.CART_AMOUNT_OF_SEEDS_EACH_TYPE}
|
||||
move_list = ["rotate_left", "move", "move", "move", "move", "move", "move", "rotate_left", "rotate_left", "move",
|
||||
"rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left",
|
||||
"rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move",
|
||||
"rotate_left", "rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left",
|
||||
"rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move",
|
||||
"rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "move",
|
||||
"rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left",
|
||||
"rotate_left", "rotate_left", "move", "move", "rotate_left", "rotate_left", "rotate_left",
|
||||
"rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move",
|
||||
"rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "rotate_left", "move",
|
||||
"rotate_left", "rotate_left", "move", "move", "move", "rotate_left", "rotate_left", "rotate_left",
|
||||
"rotate_left", "rotate_left", "move", "move", "rotate_left", "rotate_left", "rotate_left",
|
||||
"rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left", "move",
|
||||
"rotate_left", "rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left",
|
||||
"rotate_left", "rotate_left", "move", "rotate_left", "rotate_left", "rotate_left",
|
||||
"move"] # początkowe ruchy
|
||||
amount_of_seeds_dict = {"beetroot": definitions.CART_AMOUNT_OF_SEEDS_EACH_TYPE,
|
||||
"carrot": definitions.CART_AMOUNT_OF_SEEDS_EACH_TYPE,
|
||||
"potato": definitions.CART_AMOUNT_OF_SEEDS_EACH_TYPE,
|
||||
"wheat": definitions.CART_AMOUNT_OF_SEEDS_EACH_TYPE}
|
||||
collected_plants_dict_cart = {"beetroot": 0, "carrot": 0, "potato": 0, "wheat": 0}
|
||||
collected_plants_dict_station = {"beetroot": 0, "carrot": 0, "potato": 0, "wheat": 0}
|
||||
fertilizer_dict = {"beetroot": definitions.CART_FERTILIZER, "carrot": definitions.CART_FERTILIZER, "potato": definitions.CART_FERTILIZER, "wheat": definitions.CART_FERTILIZER}
|
||||
fertilizer_dict = {"beetroot": definitions.CART_FERTILIZER, "carrot": definitions.CART_FERTILIZER,
|
||||
"potato": definitions.CART_FERTILIZER, "wheat": definitions.CART_FERTILIZER}
|
||||
station1 = station.Station(collected_plants_dict_station)
|
||||
cart1 = cart.Cart(amount_of_seeds_dict, collected_plants_dict_cart, definitions.CART_DIRECTION_WEST, fertilizer_dict, definitions.CART_FUEL, definitions.CART_WATER_LEVEL, 0 * definitions.BLOCK_SIZE, 0 * definitions.BLOCK_SIZE)
|
||||
cart1 = cart.Cart(amount_of_seeds_dict, collected_plants_dict_cart, definitions.CART_DIRECTION_WEST,
|
||||
fertilizer_dict, definitions.CART_FUEL, definitions.CART_WATER_LEVEL, 0 * definitions.BLOCK_SIZE,
|
||||
0 * definitions.BLOCK_SIZE)
|
||||
cart1_rect = pygame.Rect(cart1.get_x(), cart1.get_y(), definitions.BLOCK_SIZE, definitions.BLOCK_SIZE)
|
||||
clock = pygame.time.Clock()
|
||||
tree = treelearn.treelearn() #tworzenie drzewa decyzyjnego
|
||||
decision = [0] #początkowa decyzja o braku powrotu do stacji (0)
|
||||
geneticalgorithm.create_genetic_algorithm() #stworzenie algorytmu genetycznego
|
||||
classes, model = neuralnetwork.create_neural_network() #uczenie sieci neuronowej
|
||||
tree = treelearn.treelearn() # tworzenie drzewa decyzyjnego
|
||||
decision = [0] # początkowa decyzja o braku powrotu do stacji (0)
|
||||
geneticalgorithm.create_genetic_algorithm() # stworzenie algorytmu genetycznego
|
||||
classes, model = neuralnetwork.create_neural_network() # uczenie sieci neuronowej
|
||||
grow_flower_dandelion = False
|
||||
random_movement = False
|
||||
run = True
|
||||
while run: #pętla główna programu
|
||||
while run: # pętla główna programu
|
||||
clock.tick(definitions.FPS)
|
||||
for event in pygame.event.get():
|
||||
if event.type == pygame.QUIT:
|
||||
run = False
|
||||
map1.draw_window(cart1, cart1_rect, station1)
|
||||
if not move_list: #jeżeli są jakieś ruchy do wykonania w move_list
|
||||
if not move_list: # jeżeli są jakieś ruchy do wykonania w move_list
|
||||
grow_flower_dandelion = True
|
||||
pygame.image.save(pygame.display.get_surface(), os.path.join('resources/neural_network/tiles/', 'screen.jpg')) #zrzut obecnego ekranu
|
||||
tiles = image_slicer.slice(os.path.join('resources/neural_network/tiles/', 'screen.jpg'), row=definitions.HEIGHT_AMOUNT + 1, col=definitions.WIDTH_AMOUNT, save=False) #pocięcie ekranu na sto części
|
||||
image_slicer.save_tiles(tiles, directory=os.path.join('resources/neural_network/tiles/'), prefix='tile', format='png') #zapisanie części do folderu tiles
|
||||
pygame.image.save(pygame.display.get_surface(),
|
||||
os.path.join('resources/neural_network/tiles/', 'screen.jpg')) # zrzut obecnego ekranu
|
||||
tiles = image_slicer.slice(os.path.join('resources/neural_network/tiles/', 'screen.jpg'),
|
||||
row=definitions.HEIGHT_AMOUNT + 1, col=definitions.WIDTH_AMOUNT,
|
||||
save=False) # pocięcie ekranu na sto części
|
||||
image_slicer.save_tiles(tiles, directory=os.path.join('resources/neural_network/tiles/'), prefix='tile',
|
||||
format='png') # zapisanie części do folderu tiles
|
||||
os.remove('resources/neural_network/tiles/screen.jpg')
|
||||
for char in range(0, definitions.WIDTH_AMOUNT):
|
||||
if str(char) == "0":
|
||||
os.remove('resources/neural_network/tiles/tile_11_10.png')
|
||||
else:
|
||||
os.remove('resources/neural_network/tiles/tile_11_0' + str(char) + '.png')
|
||||
istate = graph.Istate(cart1.get_direction(), cart1.get_x() / definitions.BLOCK_SIZE, cart1.get_y() / definitions.BLOCK_SIZE) #stan początkowy wózka (jego orientacja oraz jego aktualne miejsce)
|
||||
if neuralnetwork.predfield(classes, istate, model) is not False: #jeżeli istnieje jakaś dojrzała roślina
|
||||
istate = graph.Istate(cart1.get_direction(), cart1.get_x() / definitions.BLOCK_SIZE,
|
||||
cart1.get_y() / definitions.BLOCK_SIZE) # stan początkowy wózka (jego orientacja oraz jego aktualne miejsce)
|
||||
if neuralnetwork.predfield(classes, istate, model) is not False: # jeżeli istnieje jakaś dojrzała roślina
|
||||
random_movement = False
|
||||
if decision == [0]: #jeżeli decyzja jest 0 (brak powrotu do stacji) to uprawiaj pole
|
||||
move_list = (astar.graphsearch([], astar.f, [], neuralnetwork.predfield(classes, istate, model), istate, map1, graph.succ)) #lista z ruchami, które należy po kolei wykonać, astar
|
||||
else: #jeżeli decyzja jest 1 (powrót do stacji) to wróć do stacji uzupełnić zapasy
|
||||
move_list = (graph.graphsearch([], [], (0, 0), istate, graph.succ)) #lista z ruchami, które należy po kolei wykonać, graphsearch
|
||||
if decision == [0]: # jeżeli decyzja jest 0 (brak powrotu do stacji) to uprawiaj pole
|
||||
move_list = (
|
||||
astar.graphsearch([], astar.f, [], neuralnetwork.predfield(classes, istate, model), istate,
|
||||
map1, graph.succ)) # lista z ruchami, które należy po kolei wykonać, astar
|
||||
else: # jeżeli decyzja jest 1 (powrót do stacji) to wróć do stacji uzupełnić zapasy
|
||||
move_list = (graph.graphsearch([], [], (0, 0), istate,
|
||||
graph.succ)) # lista z ruchami, które należy po kolei wykonać, graphsearch
|
||||
else:
|
||||
random_movement = True
|
||||
elif move_list: #jeżeli move_list nie jest pusta
|
||||
cart1.handle_movement(cart1_rect, move_list.pop(0)) #wykonaj kolejny ruch oraz zdejmij ten ruch z początku listy
|
||||
elif move_list: # jeżeli move_list nie jest pusta
|
||||
cart1.handle_movement(cart1_rect,
|
||||
move_list.pop(0)) # wykonaj kolejny ruch oraz zdejmij ten ruch z początku listy
|
||||
if random_movement is True:
|
||||
cart1.handle_movement_random(cart1_rect) #wykonuj losowe ruchy
|
||||
cart1.do_work(cart1_rect, map1, station1) #wykonaj pracę na danym polu
|
||||
decision = treelearn.make_decision(cart1.get_all_amount_of_seeds(), cart1.get_all_collected_plants(), cart1.get_all_fertilizer(), cart1.get_fuel(), tree, cart1.get_water_level()) #podejmij decyzję czy wracać do stacji (0 : NIE, 1 : TAK)
|
||||
cart1.handle_movement_random(cart1_rect) # wykonuj losowe ruchy
|
||||
cart1.do_work(cart1_rect, map1, station1) # wykonaj pracę na danym polu
|
||||
decision = treelearn.make_decision(cart1.get_all_amount_of_seeds(), cart1.get_all_collected_plants(),
|
||||
cart1.get_all_fertilizer(), cart1.get_fuel(), tree,
|
||||
cart1.get_water_level()) # podejmij decyzję czy wracać do stacji (0 : NIE, 1 : TAK)
|
||||
if grow_flower_dandelion is True:
|
||||
plant.Plant.grow_flower_dandelion(map1) #losuj urośnięcie kwiatka dandeliona
|
||||
plant.Plant.grow_plants(map1) #zwiększ poziom dojrzałości roślin
|
||||
plant.Plant.grow_flower_dandelion(map1) # losuj urośnięcie kwiatka dandeliona
|
||||
plant.Plant.grow_plants(map1) # zwiększ poziom dojrzałości roślin
|
||||
pygame.quit()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
main()
|
||||
|
||||
14
soil.py
14
soil.py
@ -1,17 +1,23 @@
|
||||
class Soil:
|
||||
def __init__(self, is_fertilized, state, water_level):
|
||||
self.is_fertilized = is_fertilized #nienawieziona lub nawieziona
|
||||
self.state = state #niezaorana lub zaorana
|
||||
self.water_level = water_level #niepodlana lub podlana
|
||||
self.is_fertilized = is_fertilized # nienawieziona lub nawieziona
|
||||
self.state = state # niezaorana lub zaorana
|
||||
self.water_level = water_level # niepodlana lub podlana
|
||||
|
||||
def get_is_fertilized(self):
|
||||
return self.is_fertilized
|
||||
|
||||
def set_is_fertilized(self, is_fertilized):
|
||||
self.is_fertilized = is_fertilized
|
||||
|
||||
def get_state(self):
|
||||
return self.state
|
||||
|
||||
def set_state(self, state):
|
||||
self.state = state
|
||||
|
||||
def get_water_level(self):
|
||||
return self.water_level
|
||||
|
||||
def set_water_level(self, water_level):
|
||||
self.water_level = water_level
|
||||
self.water_level = water_level
|
||||
|
||||
17
station.py
17
station.py
@ -1,9 +1,14 @@
|
||||
class Station:
|
||||
def __init__(self, collected_plants):
|
||||
self.collected_plants = collected_plants #collected_plants to słownik, przechowuje informacje o oddanych plonach
|
||||
def get_all_collected_plants(self): #zwraca łączną ilość zebranych plonów (suma plonów wszystkich roślin)
|
||||
return self.collected_plants["beetroot"] + self.collected_plants["carrot"] + self.collected_plants["potato"] + self.collected_plants["wheat"]
|
||||
def get_collected_plants(self, name): #zwraca łączną ilość oddanych plonów dla podanej rośliny (name)
|
||||
self.collected_plants = collected_plants # collected_plants to słownik, przechowuje informacje o oddanych plonach
|
||||
|
||||
def get_all_collected_plants(self): # zwraca łączną ilość zebranych plonów (suma plonów wszystkich roślin)
|
||||
return self.collected_plants["beetroot"] + self.collected_plants["carrot"] + self.collected_plants["potato"] + \
|
||||
self.collected_plants["wheat"]
|
||||
|
||||
def get_collected_plants(self, name): # zwraca łączną ilość oddanych plonów dla podanej rośliny (name)
|
||||
return self.collected_plants[name]
|
||||
def set_collected_plants(self, name, value): #dla podanej rośliny (name) ustawia łączną ilość oddanych plonów (value)
|
||||
self.collected_plants[name] = value
|
||||
|
||||
def set_collected_plants(self, name,
|
||||
value): # dla podanej rośliny (name) ustawia łączną ilość oddanych plonów (value)
|
||||
self.collected_plants[name] = value
|
||||
|
||||
31
treelearn.py
31
treelearn.py
@ -6,24 +6,31 @@ import pickle
|
||||
import pydotplus
|
||||
from sklearn import tree
|
||||
from sklearn.tree import DecisionTreeClassifier
|
||||
def make_decision(amount_of_seeds, collected_plants, fertilizer, fuel, tree, water_level): #zwraca decyzję o powrocie do stacji (0 : NIE, 1 : TAK)
|
||||
decision = tree.predict([[amount_of_seeds, collected_plants, fertilizer, fuel, water_level]]) #podejmij decyzję na podstawie aktualnych parametrów wózka o powrocie do stacji lub nie
|
||||
|
||||
|
||||
def make_decision(amount_of_seeds, collected_plants, fertilizer, fuel, tree,
|
||||
water_level): # zwraca decyzję o powrocie do stacji (0 : NIE, 1 : TAK)
|
||||
decision = tree.predict([[amount_of_seeds, collected_plants, fertilizer, fuel,
|
||||
water_level]]) # podejmij decyzję na podstawie aktualnych parametrów wózka o powrocie do stacji lub nie
|
||||
return decision
|
||||
def treelearn(): #zwraca utworzone drzewo decyzyjne
|
||||
if os.path.exists("resources/decision_tree/tree.pkl"): #jeżeli drzewo jest zapisane w pliku to odczytaj
|
||||
|
||||
|
||||
def treelearn(): # zwraca utworzone drzewo decyzyjne
|
||||
if os.path.exists("resources/decision_tree/tree.pkl"): # jeżeli drzewo jest zapisane w pliku to odczytaj
|
||||
dtree = pickle.load(open(os.path.join('resources/decision_tree', "tree.pkl"), "rb"))
|
||||
else: #w przeciwnym razie utwórz drzewo od początku i zapisz do pliku
|
||||
df = pandas.read_csv(os.path.join('resources/decision_tree', 'data.csv')) #czytanie danych do nauki drzewa z pliku .csv
|
||||
else: # w przeciwnym razie utwórz drzewo od początku i zapisz do pliku
|
||||
df = pandas.read_csv(
|
||||
os.path.join('resources/decision_tree', 'data.csv')) # czytanie danych do nauki drzewa z pliku .csv
|
||||
features = ['amount of seeds', 'collected plants', 'fertilizer', 'fuel', 'water level']
|
||||
x = df[features] #wczytanie atrybutów, z których ma się uczyć drzewo
|
||||
y = df['back to station'] #podjęte decyzje
|
||||
dtree = DecisionTreeClassifier() #klasyfikuje drzewo
|
||||
dtree = dtree.fit(x, y) #uczy drzewo
|
||||
x = df[features] # wczytanie atrybutów, z których ma się uczyć drzewo
|
||||
y = df['back to station'] # podjęte decyzje
|
||||
dtree = DecisionTreeClassifier() # klasyfikuje drzewo
|
||||
dtree = dtree.fit(x, y) # uczy drzewo
|
||||
pickle.dump(dtree, open(os.path.join('resources/decision_tree', "tree.pkl"), "wb"))
|
||||
data = tree.export_graphviz(dtree, out_file=None, feature_names=features)
|
||||
graph = pydotplus.graph_from_dot_data(data)
|
||||
graph.write_png(os.path.join('resources/decision_tree', 'mytree.png'))
|
||||
img = pltimg.imread(os.path.join('resources/decision_tree', 'mytree.png'))
|
||||
imgplot = plt.imshow(img)
|
||||
plt.show() #wyświetl drzewo decyzyjne
|
||||
return dtree
|
||||
plt.show() # wyświetl drzewo decyzyjne
|
||||
return dtree
|
||||
|
||||
Loading…
Reference in New Issue
Block a user