Zaktualizuj 'src/dimensions.py'

- END of bugfixing

with Michał Malinowski

AI/GeneticAlgorithm.py

@@ -1,5 +1,3 @@
-import random
-
 import keyboard as keyboard
 
 import field as F
@@ -11,18 +9,20 @@ from src import mapschema as maps
 def genetic_algorithm_setup(field):
     population_units = ["", "w", "p", "s"]
 
-    # new_population to be
+    # TODO REPREZENTACJA OSOBNIKA - MACIERZ ROZKłADU PLONÓW
     population_text = []
+    population_text_single = []
+
+    population_size = 10
 
     # Populate the population_text array
+    for k in range(population_size):
+        population_text_single = []
         for row in range(D.GSIZE):
-        population_text.append([])
+            population_text_single.append([])
             for column in range(D.GSIZE):
-            population_text[row].append(random.choice(population_units))
+                population_text_single[row].append(random.choice(population_units))
-
+        population_text.append(population_text_single)
-    # printer
-    for _ in population_text:
-        print(population_text)
 
     """
     Genetic algorithm parameters:
@@ -31,75 +31,110 @@ def genetic_algorithm_setup(field):
     """
 
     # units per population in generation
-    sol_per_pop = 8
-    num_parents_mating = 4
-
-    population_values = []
-    fitness_row = []
-
-    # population Fitness
-    for i in range(0, D.GSIZE):
-        for j in range(D.GSIZE):
-            fitness_row.append(local_fitness(field, i, j, population_text))
-        population_values.append(fitness_row)
-
     best_outputs = []
-    num_generations = 10
+    num_generations = 100
+    num_parents = 4
 
+    # iterative var
     generation = 0
-
+    stop = 0
-    while generation < num_generations:
+    # TODO WARUNEK STOPU
+    while generation < num_generations and stop < 3:
         if keyboard.is_pressed('space'):
             generation += 1
 
             print("Generation : ", generation)
             # Measuring the fitness of each chromosome in the population.
 
-            fitness = cal_pop_fitness(population_values)
+            # population Fitness
+            fitness = []
+
+            for i in range(0, population_size):
+                fitness.append((i, population_fitness(population_text[i], field, population_size)))
+
             print("Fitness")
             print(fitness)
 
-            # best_outputs.append(best_Output(new_population))
+            best = sorted(fitness, key=lambda tup: tup[1], reverse=True)[0:num_parents]
-            # The best result in the current iteration.
-            # print("Best result : ", best_Output(new_population))
 
+            # Leaderboard only
+            best_outputs.append(best[0][1])
+
+            # The best result in the current iteration.
+            print("Best result : ", best[0])
+
+            # TODO METODA WYBORU OSOBNIKA - RANKING
             # Selecting the best parents in the population for mating.
-            parents = select_mating_pool(new_population, fitness,
+            parents = [population_text[i[0]] for i in best]
-                                         num_parents_mating)
+            parents_copy = copy.deepcopy(parents)
             print("Parents")
-            print(parents)
+            for i in range(0, len(parents)):
+                print('\n'.join([''.join(['{:4}'.format(item) for item in row])
+                                 for row in parents[i]]))
+                print("")
 
             # Generating next generation using crossover.
-            offspring_crossover = crossover(parents, offspring_size=(pop_size[0] - parents.shape[0], num_weights))
+            offspring_x = random.randint(1, D.GSIZE - 2)
+            offspring_y = random.randint(1, D.GSIZE - 2)
+
+            # TODO OPERATOR KRZYŻOWANIA
+            offspring_crossover = crossover(parents)
             print("Crossover")
-            print(offspring_crossover)
+            for i in range(0, len(offspring_crossover)):
+                print('\n'.join([''.join(['{:4}'.format(item) for item in row])
+                                 for row in offspring_crossover[i]]))
+                print("")
 
-            # Adding some variations to the offspring using mutation.
+            # TODO OPERATOR MUTACJI
-            offspring_mutation = mutation(offspring_crossover, num_mutations=2)
+            offspring_mutation = mutation(population_units, offspring_crossover, population_size - num_parents,
+                                          num_mutations=10)
             print("Mutation")
-            print(offspring_mutation)
+            for i in range(0, len(offspring_mutation)):
+                print('\n'.join([''.join(['{:4}'.format(item) for item in row])
+                                 for row in offspring_mutation[i]]))
+                print("")
 
-            # Creating the new population based on the parents and offspring.
+            population_text_copy = copy.deepcopy(population_text)
-            new_population[0:parents.shape[0], :] = parents
+            unused_indexes = [i for i in range(0, population_size) if i not in [j[0] for j in best]]
-            new_population[parents.shape[0]:, :] = offspring_mutation
+            # Creating next generation
+            population_text = []
+            for k in parents_copy:
+                population_text.append(k)
+            for k in range(0, len(offspring_mutation)):
+                population_text.append(offspring_mutation[k])
+            while len(population_text) < population_size:
+                x = random.choice(unused_indexes)
+                population_text.append(population_text_copy[x])
+                unused_indexes.remove(x)
 
-    # Getting the best solution after iterating finishing all generations.
+            # TODO WARUNEK STOPU
-    # At first, the fitness is calculated for each solution in the final generation.
+            stop = 0
-    fitness = cal_pop_fitness(new_population)
+            if generation > 10:
-    # Then return the index of that solution corresponding to the best fitness.
+                if best_outputs[-1] / best_outputs[-2] < 1.001:
-    best_match_idx = numpy.where(fitness == numpy.max(fitness))
+                    stop += 1
+                if best_outputs[-1] / best_outputs[-3] < 1.001:
+                    stop += 1
+                if best_outputs[-2] / best_outputs[-3] < 1.001:
+                    stop += 1
 
-    print("Best solution : ", new_population[best_match_idx, :])
+    # final Fitness
-    print("Best solution fitness : ", fitness[best_match_idx])
+    fitness = []
+    for i in range(0, population_size):
+        fitness.append((i, population_fitness(population_text[i], field, population_size)))
 
-    import matplotlib.pyplot
+    print("Final Fitness")
+    print(fitness)
 
-    matplotlib.pyplot.plot(best_outputs)
+    best = sorted(fitness, key=lambda tup: tup[1])[0:num_parents]
-    matplotlib.pyplot.xlabel("Iteration")
-    matplotlib.pyplot.ylabel("Fitness")
-    matplotlib.pyplot.show()
 
-    # return best iteration of field
+    print("Best solution : ", )
+    for i in range(0, D.GSIZE):
+        print(population_text[best[0][0]][i])
+    print("Best solution fitness : ", best[0][1])
+
+    pretty_printer(best_outputs)
+
+    # TODO REALLY return best iteration of field
     return 0
 
 

AI/NN_accuracy.py

@@ -1,63 +1,47 @@
-import PIL
+import torch
+import torchvision
 import torchvision.transforms as transforms
-
+import torch.nn as nn
-from AI import neural_network
+import torch.nn.functional as F
+import torch.optim as optim
+import numpy as np
+from matplotlib.pyplot import imshow
+import os
+import PIL
+import numpy as np
+from matplotlib.pyplot import imshow
+import neural_network
+from matplotlib.pyplot import imshow
 
 
-# wcześniej grinder.py
+# wcześniej grader.py
 # Get accuracy for neural_network model 'network_model.pth'
 def NN_accuracy():
     # Create the model
-    model = neural_network.Net()
+    net = neural_network.Net()
 
     # Load state_dict
-    neural_network.load_network_from_structure(model)
+    neural_network.load_network_from_structure(net)
-
-    # Create the preprocessing transformation here
-    transform = transforms.Compose([neural_network.Negative(), transforms.ToTensor()])
-
-    # load your image(s)
-    img = PIL.Image.open('../src/test/0_100.jpg')
-    img2 = PIL.Image.open('../src/test/1_100.jpg')
-    img3 = PIL.Image.open('../src/test/4_100.jpg')
-    img4 = PIL.Image.open('../src/test/5_100.jpg')
-
-    # Transform
-    input = transform(img)
-    input2 = transform(img2)
-    input3 = transform(img3)
-    input4 = transform(img4)
-
-    # unsqueeze batch dimension, in case you are dealing with a single image
-    input = input.unsqueeze(0)
-    input2 = input2.unsqueeze(0)
-    input3 = input3.unsqueeze(0)
-    input4 = input4.unsqueeze(0)
 
     # Set model to eval
-    model.eval()
+    net.eval()
 
-    # Get prediction
+    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
-    output = model(input)
-    output2 = model(input2)
-    output3 = model(input3)
-    output4 = model(input4)
 
-    print(output)
+    folderlist = os.listdir(os.path.dirname(__file__) + "\\test")
-    index = output.cpu().data.numpy().argmax()
-    print(index)
 
-    print(output2)
+    tested = 0
-    index = output2.cpu().data.numpy().argmax()
+    correct = 0
-    print(index)
 
-    print(output3)
+    for folder in folderlist:
-    index = output3.cpu().data.numpy().argmax()
+        for file in os.listdir(os.path.dirname(__file__) + "\\test\\" + folder):
-    print(index)
+            if neural_network.result_from_network(net, os.path.dirname(__file__) + "\\test\\" + folder + "\\" + file) == folder:
+                correct += 1
+                tested += 1
+            else:
+                tested += 1
 
-    print(output4)
+    print(correct/tested)
-    index = output4.cpu().data.numpy().argmax()
-    print(index)
 
 
 if __name__ == "__main__":

AI/ga_methods.py

@@ -1,3 +1,8 @@
+import copy
+import random
+
+import matplotlib
+import matplotlib.pyplot
 import numpy
 
 import src.dimensions as D
@@ -5,88 +10,94 @@ import src.dimensions as D
 
 # Genetic Algorithm methods
 
-def local_fitness(field, x, y, plants):
+def local_fitness(field, x, y, plants_case):
     soil_value = 0
     if field[x][y].field_type == "soil":
         soil_value = 1
     else:
         soil_value = 0.5
 
-    if plants[x][y] == "":
+    if plants_case[x][y] == "":
         plant_value = 0
-    elif plants[x][y] == "w":
+    elif plants_case[x][y] == "w":
         plant_value = 1
-    elif plants[x][y] == "p":
+    elif plants_case[x][y] == "p":
         plant_value = 2
-    elif plants[x][y] == "s":
+    elif plants_case[x][y] == "s":
         plant_value = 3
+    else:
+        plant_value = 1
 
     neighbour_bonus = 1
+
     if x - 1 >= 0:
-        if plants[x][y] == plants[x - 1][y]:
+        if plants_case[x][y] == plants_case[x - 1][y]:
             neighbour_bonus += 1
     if x + 1 < D.GSIZE:
-        if plants[x][y] == plants[x + 1][y]:
+        if plants_case[x][y] == plants_case[x + 1][y]:
             neighbour_bonus += 1
     if y - 1 >= 0:
-        if plants[x][y] == plants[x][y - 1]:
+        if plants_case[x][y] == plants_case[x][y - 1]:
             neighbour_bonus += 1
     if y + 1 < D.GSIZE:
-        if plants[x][y] == plants[x][y + 1]:
+        if plants_case[x][y] == plants_case[x][y + 1]:
             neighbour_bonus += 1
 
-    # TODO * multiculture_bonus
     local_fitness_value = (soil_value + plant_value) * (0.5 * neighbour_bonus + 1)
     return local_fitness_value
 
 
-def cal_pop_fitness(pop):
+def population_fitness(population_text_local, field, population_size):
     # Calculating the fitness value of each solution in the current population.
     # The fitness function calulates the sum of products between each input and its corresponding weight.
-    fitness = sum(map(sum, pop))
+    fitness = []
+
+    for k in range(population_size):
+        population_values_single = []
+        population_values_single_row = []
+        fitness_row = []
+
+        for i in range(0, D.GSIZE):
+            for j in range(0, D.GSIZE):
+                population_values_single_row.append(local_fitness(field, i, j, population_text_local))
+            population_values_single.append(population_values_single_row)
+
+        for i in range(D.GSIZE):
+            fitness_row.append(sum(population_values_single[i]))
+        fitness = sum(fitness_row)
     return fitness
 
 
-def select_mating_pool(pop, fitness, num_parents):
+def crossover(local_parents):
-    # Selecting the best individuals in the current generation as parents for producing the offspring of the next generation.
+    ret = []
-    parents = numpy.empty((num_parents, pop.shape[1]))
+    for i in range(0, len(local_parents)):
-    for parent_num in range(num_parents):
+        child = copy.deepcopy(local_parents[i])
-        max_fitness_idx = numpy.where(fitness == numpy.max(fitness))
+        # Vertical randomization
-        max_fitness_idx = max_fitness_idx[0][0]
+        width = random.randint(1, D.GSIZE // len(local_parents))  # width of stripes
-        parents[parent_num, :] = pop[max_fitness_idx, :]
+        indexes_parents = numpy.random.permutation(range(0, len(local_parents)))  # sorting of stripes
-        fitness[max_fitness_idx] = -99999999999
+        beginning = random.randint(0, len(local_parents[0]) - width * len(
-    return parents
+            local_parents))  # point we start putting the stripes from
+        for x in indexes_parents:
+            child[beginning:beginning + width] = local_parents[x][beginning:beginning + width]
+            beginning += width
+        ret.append(child)
+    return ret
 
 
-def crossover(parents, offspring_size):
+def mutation(population_units, offspring_crossover, num_mutants, num_mutations=10):
-    offspring = numpy.empty(offspring_size)
+    for case in range(0, len(offspring_crossover)):
-    # The point at which crossover takes place between two parents. Usually, it is at the center.
+        for mutation in range(0, num_mutations):
-    crossover_point = numpy.uint8(offspring_size[1] / 2)
+            mutation_x = random.randint(0, D.GSIZE - 1)
+            mutation_y = random.randint(0, D.GSIZE - 1)
+            mutation_value = random.choice(population_units)
+            offspring_crossover[case][mutation_x][mutation_y] = mutation_value
+            num_mutants -= 1
 
-    for k in range(offspring_size[0]):
-        # Index of the first parent to mate.
-        parent1_idx = k % parents.shape[0]
-        # Index of the second parent to mate.
-        parent2_idx = (k + 1) % parents.shape[0]
-        # The new offspring will have its first half of its genes taken from the first parent.
-        offspring[k, 0:crossover_point] = parents[parent1_idx, 0:crossover_point]
-        # The new offspring will have its second half of its genes taken from the second parent.
-        offspring[k, crossover_point:] = parents[parent2_idx, crossover_point:]
-    return offspring
-
-
-def mutation(offspring_crossover, num_mutations=1):
-    mutations_counter = numpy.uint8(offspring_crossover.shape[1] / num_mutations)
-    # Mutation changes a number of genes as defined by the num_mutations argument. The changes are random.
-    for idx in range(offspring_crossover.shape[0]):
-        gene_idx = mutations_counter - 1
-        for mutation_num in range(num_mutations):
-            # The random value to be added to the gene.
-            random_value = numpy.random.uniform(-1.0, 1.0, 1)
-            offspring_crossover[idx, gene_idx] = offspring_crossover[idx, gene_idx] + random_value
-            gene_idx = gene_idx + mutations_counter
     return offspring_crossover
 
 
-def best_Output(new_population):
+def pretty_printer(best_outputs):
-    return numpy.max(numpy.sum(new_population * equation_inputs, axis=1))
+    matplotlib.pyplot.plot(best_outputs)
+    matplotlib.pyplot.xlabel("Iteration")
+    matplotlib.pyplot.ylabel("Fitness")
+    matplotlib.pyplot.show()

AI/neural_network.py

@@ -1,18 +1,20 @@
-import PIL
-import numpy as np
 import torch
-import torch.nn as nn
-import torch.optim as optim
 import torchvision
 import torchvision.transforms as transforms
+import torch.nn as nn
+import torch.nn.functional as F
+import torch.optim as optim
+import numpy as np
+from matplotlib.pyplot import imshow
+import os
+import PIL
+import numpy as np
 from matplotlib.pyplot import imshow
-
 
 def to_negative(img):
     img = PIL.ImageOps.invert(img)
     return img
 
-
 class Negative(object):
     def __init__(self):
         pass
@@ -20,41 +22,46 @@ class Negative(object):
     def __call__(self, img):
         return to_negative(img)
        
-
-def plotdigit(image):
-    img = np.reshape(image, (-1, 100))
-    imshow(img, cmap='Greys')
-
-
 transform = transforms.Compose([Negative(), transforms.ToTensor()])
-train_set = torchvision.datasets.ImageFolder(root='../src/train', transform=transform)
+train_set = torchvision.datasets.ImageFolder(root='train', transform=transform)
-classes = ("apple", "potato")
+classes = ("pepper", "potato", "strawberry", "tomato")
 
-BATCH_SIZE = 2
+BATCH_SIZE = 4
 train_loader = torch.utils.data.DataLoader(train_set, batch_size=BATCH_SIZE, shuffle=True, num_workers=0)
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
-
 class Net(nn.Module):
     def __init__(self):
-        super(Net, self).__init__()
+        super().__init__()
-        self.flatten = nn.Flatten()
+        self.network = nn.Sequential(
-        self.linear_relu_stack = nn.Sequential(
+            nn.Conv2d(3, 32, kernel_size=3, padding=1), #3 channels to 32 channels
-            nn.Linear(3 * 100 * 100, 512),
             nn.ReLU(),
-            nn.Linear(512, 512),
+            nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),
             nn.ReLU(),
-            nn.Linear(512, 2),
+            nn.MaxPool2d(2, 2), # output: 64 channels x 50 x 50 image size - decrease
-            nn.ReLU()
-        )
-        self.linear_relu_stack = self.linear_relu_stack.to(device)
 
-    def forward(self, x):
+            nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1),
-        x = self.flatten(x).to(device)
+            nn.ReLU(),
-        logits = self.linear_relu_stack(x).to(device)
+            nn.Conv2d(128, 128, kernel_size=3, stride=1, padding=1), #increase power of model 
-        return logits
+            nn.ReLU(),
+            nn.MaxPool2d(2, 2), # output: 128 x 25 x 25
 
+            nn.Conv2d(128, 256, kernel_size=3, stride=1, padding=1),
+            nn.ReLU(),
+            nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1),
+            nn.ReLU(),
+            nn.MaxPool2d(5, 5), # output: 256 x 5 x 5
+
+            nn.Flatten(), #a single vector 256*5*5,
+            nn.Linear(256*5*5, 1024),
+            nn.ReLU(),
+            nn.Linear(1024, 512),
+            nn.ReLU(),
+            nn.Linear(512, 4))
+        
+    def forward(self, xb):
+        return self.network(xb)
  
 def training_network():
     net = Net()
@@ -63,7 +70,7 @@ def training_network():
     criterion = nn.CrossEntropyLoss()
     optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
  
-    for epoch in range(4):
+    for epoch in range(10):
         running_loss = 0.0
         for i, data in enumerate(train_loader, 0):
             inputs, labels = data[0].to(device), data[1].to(device)
@@ -74,7 +81,7 @@ def training_network():
             optimizer.step()
  
             running_loss += loss.item()
-            if i % 2000 == 1999:
+            if i % 200 == 199:
                 print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss))
                 running_loss = 0.0
  
@@ -84,8 +91,8 @@ def training_network():
  
 def result_from_network(net, loaded_image):
     image = PIL.Image.open(loaded_image)
-    pil_to_tensor = transforms.ToTensor()(image.convert("RGB")).unsqueeze_(0)
+    pil_to_tensor = transforms.Compose([Negative(), transforms.ToTensor()])(image.convert("RGB")).unsqueeze_(0)
-    outputs = net(pil_to_tensor.to(device))
+    outputs = net(pil_to_tensor)
  
     return classes[torch.max(outputs, 1)[1]]
  
@@ -99,7 +106,6 @@ def load_network_from_structure(network):
     network.load_state_dict(torch.load('network_model.pth'))
  
  
-# Create network_model.pth
 if __name__ == "__main__":
     print(torch.cuda.is_available())
     training_network()

field.py

@@ -1,9 +1,7 @@
 import pygame
-
 from src.colors import *
 from src.dimensions import *
 
-
 class Field(pygame.sprite.Sprite):
     def __init__(self, row, column, field_type):
         super(Field, self).__init__()
@@ -26,22 +24,62 @@ class Field(pygame.sprite.Sprite):
         self.position = [row, column]
         self.hydration = 0
         self.planted = 0
-        self.fertility = 1
+        self.fertility = 0
         self.tractor_there = False
 
     def hydrate(self):
         if self.field_type == "soil" and self.hydration <= 5:
                 self.hydration += 1
-
+                if self.fertility == 1:
-            # color field to it's hydration value
+                    if self.hydration == 0:
-            self.surf.fill(eval('BROWN' + str(self.hydration)))
+                        self.surf.fill(REDDISH0)
+                        self.fertility = 0
+                    if self.hydration == 1:
+                        self.surf.fill(REDDISH1)
+                    if self.hydration == 2:
+                        self.surf.fill(REDDISH2)
+                    if self.hydration == 3:
+                        self.surf.fill(REDDISH3)
+                    if self.hydration == 4 or self.hydration == 5:
+                        self.surf.fill(REDDISH4)
+                else:
+                    if self.hydration == 0:
+                        self.surf.fill(BROWN0)
+                    if self.hydration == 1:
+                        self.surf.fill(BROWN1)
+                    if self.hydration == 2:
+                        self.surf.fill(BROWN2)
+                    if self.hydration == 3:
+                        self.surf.fill(BROWN3)
+                    if self.hydration == 4 or self.hydration == 5:
+                        self.surf.fill(BROWN4)
     
     def dehydrate(self):
             if self.field_type == "soil" and self.hydration > 0:
                 self.hydration -= 1
-
+                if self.fertility == 1:
-            # color field to it's hydration value
+                    if self.hydration == 0:
-            self.surf.fill(eval('BROWN' + str(self.hydration)))
+                        self.surf.fill(REDDISH0)
+                        self.fertility = 0
+                    if self.hydration == 1:
+                        self.surf.fill(REDDISH1)
+                    if self.hydration == 2:
+                        self.surf.fill(REDDISH2)
+                    if self.hydration == 3:
+                        self.surf.fill(REDDISH3)
+                    if self.hydration == 4 or self.hydration == 5:
+                        self.surf.fill(REDDISH4)
+                else:
+                    if self.hydration == 0:
+                        self.surf.fill(BROWN0)
+                    if self.hydration == 1:
+                        self.surf.fill(BROWN1)
+                    if self.hydration == 2:
+                        self.surf.fill(BROWN2)
+                    if self.hydration == 3:
+                        self.surf.fill(BROWN3)
+                    if self.hydration == 4 or self.hydration == 5:
+                        self.surf.fill(BROWN4)
     
     def free(self):
         self.planted = 0

main.py

@@ -10,12 +10,15 @@ from pygame.locals import (
     QUIT
 )
 
+
 # Import other files from project
 import field as F
 import node as N
 import plant as P
 import src.colors as C
 import src.dimensions as D
+import AI.GeneticAlgorithm as ga
+import AI.neural_network as nn
 import tractor as T
 from src import mapschema as maps
 
@@ -44,6 +47,16 @@ if __name__ == "__main__":
             field[row].append(fieldbit)
 
     # genetic_algorithm_setup(field)
+    num_of_plants = 0
+    plant_pops = []
+    best_plant_pop = []
+
+    goal_gen = 100
+    best_plant_pop, plant_pops, num_of_plants, fitness = ga.genetic_algorithm_setup(field, plant_pops, goal_gen)
+
+    net = nn.Net()
+    nn.load_network_from_structure(net)
+    net.eval()
 
     # Create Tractor object
     tractor = T.Tractor(field, [0, 0])
@@ -58,9 +71,11 @@ if __name__ == "__main__":
     for row in range(D.GSIZE):
         plants.append([])
         for column in range(D.GSIZE):
-            if mapschema[column][row] != 0:
+            if best_plant_pop[column][row] != "":
-                plantbit = P.Plant(field[row][column], mapschema[column][row])
+                plantbit = P.Plant(field[row][column], best_plant_pop[column][row])
                 plants[row].append(plantbit)
+            else:
+                plants[row].append(0)
 
     # Create list for tractor instructions
     path = []
@@ -77,7 +92,6 @@ if __name__ == "__main__":
     # Main loop
     while RUNNING:
 
-        # Look at every event in the queue
         for event in pygame.event.get():
             # Did the user hit a key?
             if event.type == KEYDOWN:
@@ -105,19 +119,11 @@ if __name__ == "__main__":
                 tractor.rotate_right()
             elif path[0] == "hydrate":
                 tractor.hydrate(field)
-
+            elif path[0] == "fertilize":
+                if plants[tractor.position[1]][tractor.position[0]]:
+                    tractor.fertilize(field, plants, nn.result_from_network(net, plants[tractor.position[0]][tractor.position[1]].testimage))
             path.pop(0)
 
-        # Get all keys pressed at a time CURRENTLY UNUSED
-        pressed_keys = pygame.key.get_pressed()
-
-        # control tractor with pressed keys CURRENTLY UNUSED
-        if pressed_keys[K_UP]:
-            tractor.move()
-        elif pressed_keys[K_LEFT]:
-            tractor.rotate_left()
-        elif pressed_keys[K_RIGHT]:
-            tractor.rotate_right()
 
         # Set the screen background
         screen.fill(C.DBROWN)
@@ -133,6 +139,7 @@ if __name__ == "__main__":
         # Plants grow with every 10th tick, then they are drawn
         for row in plants:
             for plant in row:
+                if plant != 0:
                     plant.tick()
                     plant.grow()
                     screen.blit(plant.surf, plant.rect)
@@ -150,4 +157,4 @@ if __name__ == "__main__":
         pygame.display.flip()
 
         # Ensure program maintains a stable framerate
-        clock.tick(8)
+        clock.tick(35)

node.py

@@ -137,10 +137,12 @@ class Node:
             closedList.append(currentNode)
 
             if currentNode.field[currentNode.position[0]][currentNode.position[1]].planted and \
+                currentNode.field[currentNode.position[0]][currentNode.position[1]].field_type == "soil" and \
                     currentNode.field[currentNode.position[0]][currentNode.position[1]].hydration < 2:
                 path = []
                 for _ in range(currentNode.field[currentNode.position[0]][currentNode.position[1]].hydration, 4):
                     path.append("hydrate")
+                path.append("fertilize")
                 current = currentNode
                 while current is not None:
                     path.append(current.action)
@@ -174,3 +176,57 @@ class Node:
                     continue
 
                 heapq.heappush(openList, child)
+
+    def findPathToPlantSpot(self, goals):
+        startNode = Node(self.field, self.position, self.rotation)
+
+        openList = []
+        closedList = []
+
+        startNode.parent = None
+
+        heapq.heappush(openList, startNode)
+
+        while len(openList) > 0:
+            currentNode = heapq.heappop(openList)
+
+            closedList.append(currentNode)
+
+            if not currentNode.field[currentNode.position[0]][currentNode.position[1]].planted and \
+                    goals[currentNode.position[0]][currentNode.position[1]] != "":
+                path = []
+                path.append("plant")
+                current = currentNode
+                while current is not None:
+                    path.append(current.action)
+                    current = current.parent
+                return path[::-1]
+
+            children = succesor(currentNode)
+
+            perm = 0
+            for child in children:
+                for closedChild in closedList:
+                    if child.position == closedChild.position and child.rotation == closedChild.rotation and child.action == closedChild.action:
+                        perm = 1
+                        break
+                if perm == 1:
+                    perm = 0
+                    continue
+                child.parent = currentNode
+                child.startCost = currentNode.startCost + child.field[child.position[0]][child.position[1]].moveCost
+                child.heuristic = abs(startNode.position[0] - child.position[0]) + abs(
+                    startNode.position[1] - child.position[1])
+                child.totalCost = child.startCost + child.heuristic
+
+                for openNode in openList:
+                    if child.position == openNode.position and child.rotation == openNode.rotation and child.action == openNode.action and child.startCost >= openNode.startCost:
+                        perm = 1
+                        break
+
+                if perm == 1:
+                    perm = 0
+                    continue
+
+                heapq.heappush(openList, child)
+        

plant.py

@@ -1,29 +1,32 @@
+import os
+import random
+
 from AI.decision_tree import *
 from src.dimensions import *
 from src.sprites import *
+from src.colors import *
 
+path = os.path.dirname(__file__) + "\\src\\test\\"
 
 class Plant(pygame.sprite.Sprite):
     def __init__(self, field, species):
-        super(Plant, self).__init__()
         self.species = species
-        if self.species == "wheat":
+        if self.species == "tomato":
-            self.growth_speed = 1.5
-            self.humidity_needed = 2
             self.img0 = wheat_img_0
             self.img1 = wheat_img_1
             self.img2 = wheat_img_2
             self.img3 = wheat_img_3
         elif self.species == "potato":
-            self.growth_speed = 1
-            self.humidity_needed = 1
             self.img0 = potato_img_0
             self.img1 = potato_img_1
             self.img2 = potato_img_2
             self.img3 = potato_img_3
         elif self.species == "strawberry":
-            self.growth_speed = 0.8
+            self.img0 = strawberry_img_0
-            self.humidity_needed = 1
+            self.img1 = strawberry_img_1
+            self.img2 = strawberry_img_2
+            self.img3 = strawberry_img_3
+        elif self.species == "pepper":
             self.img0 = strawberry_img_0
             self.img1 = strawberry_img_1
             self.img2 = strawberry_img_2
@@ -38,9 +41,94 @@ class Plant(pygame.sprite.Sprite):
         field.planted = True
         self.tickscount = 0
         self.ticks = 0
+        self.path = path + self.species + "\\"
+        self.testimage = self.path + random.choice(os.listdir(self.path))
 
     def dtree(self):
-        decision_tree(self)
+        if self.field.hydration == 4:
+            if self.is_healthy == 1:
+                if self.field.tractor_there == 0:
+                    if self.ticks == 0:
+                        return 0
+                    elif self.ticks == 1:
+                        return 1
+                elif self.field.tractor_there == 1:
+                    return 0
+            elif self.is_healthy == 0:
+                return 0
+        elif self.field.hydration == 2:
+            if self.species == "pepper":
+                if self.ticks == 1:
+                    if self.is_healthy == 1:
+                        return 1
+                    elif self.is_healthy == 0:
+                        return 0
+                elif self.ticks == 0:
+                    return 0
+            elif self.species == "potato":
+                return 0
+            elif self.species == "tomato":
+                return 0
+            elif self.species == "strawberry":
+                return 0
+        elif self.field.hydration == 1:
+            if self.species == "potato":
+                return 0
+            elif self.species == "strawberry":
+                if self.ticks == 1:
+                    return -1
+                elif self.ticks == 0:
+                    return 0
+            elif self.species == "tomato":
+                return 0
+            elif self.species == "pepper":
+                if self.is_healthy == 0:
+                    return 0
+                elif self.is_healthy == 1:
+                    if self.field.tractor_there == 0:
+                        if self.ticks == 0:
+                            return 0
+                        elif self.ticks == 1:
+                            return 1
+                    elif self.field.tractor_there == 1:
+                        return 0
+        elif self.field.hydration == 3:
+            if self.ticks == 1:
+                if self.field.tractor_there == 0:
+                    if self.is_healthy == 1:
+                        if self.species == "potato":
+                            if self.field.fertility == 1:
+                                return 1
+                            elif self.field.fertility == 0:
+                                return 0
+                        elif self.species == "strawberry":
+                            return 1
+                        elif self.species == "pepper":
+                            return 1
+                        elif self.species == "tomato":
+                            return 1
+                    elif self.is_healthy == 0:
+                        return 0
+                elif self.field.tractor_there == 1:
+                    return 0
+            elif self.ticks == 0:
+                return 0
+        elif self.field.hydration == 5:
+            if self.field.tractor_there == 1:
+                return 0
+            elif self.field.tractor_there == 0:
+                if self.is_healthy == 0:
+                    return 0
+                elif self.is_healthy == 1:
+                    if self.ticks == 1:
+                        return 1
+                    elif self.ticks == 0:
+                        return 0
+        elif self.field.hydration == 0:
+            if self.ticks == 0:
+                return 0
+            elif self.ticks == 1:
+                return -1
 
     def update(self):
         if self.growth == 0:
@@ -63,6 +151,7 @@ class Plant(pygame.sprite.Sprite):
             self.growth = 4
         if self.growth < 0:
             self.growth = 0
+
         self.update()
 
     def tick(self):
@@ -70,3 +159,6 @@ class Plant(pygame.sprite.Sprite):
         if self.tickscount >= 25:
             self.tickscount = 0
             self.ticks = 1
+
+    def remove(self):
+        self.field.planted = False

src/colors.py

@@ -7,6 +7,14 @@ BROWN2 = (140, 110, 55)
 BROWN3 = (110, 85, 40)
 BROWN4 = (80, 60, 20)
 BROWN5 = (80, 60, 20)
+
+REDDISH0 = (230, 150, 90)
+REDDISH1 = (210, 130, 70)
+REDDISH2 = (190, 110, 55)
+REDDISH3 = (160, 85, 40)
+REDDISH4 = (130, 60, 20)
+REDDISH5 = (130, 60, 20)
+
 DBROWN = (65, 50, 20)
 LBROWN = (108, 97, 62)
 BLUE = (18, 93, 156)

src/dimensions.py

@@ -2,12 +2,12 @@
 GSIZE = 10
 
 # This sets the WIDTH and HEIGHT of each grid location
-WIDTH = 35
+WIDTH = 80
-HEIGHT = 35
+HEIGHT = 80
 
 # This sets the margin between each cell
 MARGIN = 5
 
 # Window size
 SCREEN_WIDTH = GSIZE * (WIDTH + MARGIN) + MARGIN
-SCREEN_HEIGHT = GSIZE * (HEIGHT + MARGIN) + MARGIN
+SCREEN_HEIGHT = GSIZE * (HEIGHT + MARGIN) + MARGIN + 100

tractor.py

@@ -1,7 +1,6 @@
-from pygame.locals import (K_c)
-
 from src.dimensions import *
 from src.sprites import *
+from plant import *
 
 
 class Tractor(pygame.sprite.Sprite):
@@ -73,10 +72,13 @@ class Tractor(pygame.sprite.Sprite):
         field[self.position[0]][self.position[1]].hydrate()
 
     def cut(self, field, pressed_keys):
-        if pressed_keys[K_c]:
         field[self.position[0]][self.position[1]].free()
 
-    def plant(self, field, plant, pressed_keys):
+    def plant(self, plant_map, plants):
-        if field.planted == 0:
+        print(plant_map[self.position[0]][self.position[1]])
-            field.planted = plant
+        plant = Plant(self.field[self.position[0]][self.position[1]], plant_map[self.position[0]][self.position[1]])
-            plant.field = field
+        plants.append(plant)
+
+    def fertilize(self, field, plants, type):
+        if plants[self.position[0]][self.position[1]].species == type:
+            field[self.position[0]][self.position[1]].fertility = 1