def run(file, num=1, output=True, **kwargs):
node_inno = [Counter() for _ in range(num)] if num > 1 else Counter()
con_inno = [Counter() for _ in range(num)] if num > 1 else Counter()
genome = [Genome() for _ in range(num)] if num > 1 else Genome()
setup_func(genome, node_inno, con_inno)
name = 'output/' + file.split('/')[-1].replace('.py', '')
viewer = GenomeViewer(**kwargs)
viewer.orientation = GenomeViewer.RIGHT
if output:
if num > 1:
for i, g in enumerate(genome):
viewer.gen(g).save(f'{name}_{i}_before.png', format='PNG')
else:
viewer.gen(genome).save(f'{name}_before.png', format='PNG')
test_func(genome, node_inno, con_inno)
if output:
if num > 1:
for i, g in enumerate(genome):
viewer.gen(g).save(f'{name}_{i}_after.png', format='PNG')
else:
viewer.gen(genome).save(f'{name}_after.png', format='PNG')
def test_print(self):
g = Genome(3, 1)
g.connect_nodes_by_id(1, 4, 1)
g.connect_nodes_by_id(2, 4, 2)
g.connect_nodes_by_id(3, 4, 3)
g.create_node_between(2, 4, 5, 4)
g.connect_nodes_by_id(1, 5, 6)
printer = Printer(g)
printer.print()
def setup(genome, node_inno, con_inno):
seed(1337)
for _ in range(3):
genome.add_node(Node(node_inno.inc, 0, NodeType.INPUT))
genome.add_node(Node(node_inno.inc, 2, NodeType.OUTPUT))
genome.add_node(Node(node_inno.inc, 1, NodeType.HIDDEN))
genome.add_connection(Connection(con_inno.inc, 0, 3, 1.0, True))
genome.add_connection(Connection(con_inno.inc, 1, 3, 1.0, False))
genome.add_connection(Connection(con_inno.inc, 2, 3, 1.0, True))
genome.add_connection(Connection(con_inno.inc, 1, 4, 1.0, True))
genome.add_connection(Connection(con_inno.inc, 4, 3, 1.0, True))
genome.add_connection(Connection(con_inno.inc, 0, 4, 1.0, True))
# genome.add_connection(Connection(con_inno.inc, 2, 4, 1.0, True))
Genome.save(genome, 'output/save_load')
def test_init(self):
g = Genome(2, 1)
self.assertEqual(1, g.nodes[0].get_innovation())
self.assertEqual(2, g.nodes[1].get_innovation())
self.assertEqual(3, g.nodes[2].get_innovation())
self.assertEqual(Node.TYPE_INPUT, g.nodes[0].get_type())
self.assertEqual(Node.TYPE_INPUT, g.nodes[1].get_type())
self.assertEqual(Node.TYPE_OUTPUT, g.nodes[2].get_type())
def test_another_crossover(self):
g1 = Genome(3, 1)
g2 = Genome(3, 1)
node_i = 4
conn_i = 0
for generation in range(10):
conn_i = g1.mutate_connections(conn_i)
node_i, conn_i = g1.mutate_nodes(node_i, conn_i)
conn_i = g2.mutate_connections(conn_i)
node_i, conn_i = g2.mutate_nodes(node_i, conn_i)
a1, a2 = Population.align_genome(g1, g2)
g1 = Population.crossover(a1, a2, g1.get_input_nodes(), g1.get_output_nodes())
g2 = Population.crossover(a1, a2, g1.get_input_nodes(), g1.get_output_nodes())
Printer(g1).print()
def test_remove_node(self):
g = Genome(1, 1)
g.create_node(Node.TYPE_HIDDEN, 3)
g.nodes[0].connect_to(g.nodes[2], 1)
g.nodes[2].connect_to(g.nodes[1], 2)
self.assertEqual(3, g.nodes[0].get_next_connections()[0].get_next_node().get_innovation())
self.assertEqual(2, g.nodes[0].get_next_connections()[0].get_next_node().get_next_connections()[
0].get_next_node().get_innovation())
g.remove_node(3)
self.assertEqual(0, len(g.connections))
self.assertEqual(0, len(g.nodes[0].get_next_connections()))
self.assertEqual(0, len(g.nodes[1].get_prev_connections()))
def test_create_node_between(self):
g = Genome(1, 1)
g.create_node_between(1, 2, 3, 1)
self.assertEqual(2, len(g.connections))
self.assertEqual(1, g.connections[0].get_innovation())
self.assertEqual(2, g.connections[1].get_innovation())
g.create_node_between(3, 2, 4, 3, g.select_connection_by_innovation(2))
self.assertEqual(3, len(g.connections))
current_node = g.nodes[0]
self.assertEqual(1, g.nodes[0].get_innovation())
current_node = current_node.get_next_connections()[0].get_next_node()
self.assertEqual(3, current_node.get_innovation())
current_node = current_node.get_next_connections()[0].get_next_node()
self.assertEqual(4, current_node.get_innovation())
current_node = current_node.get_next_connections()[0].get_next_node()
self.assertEqual(2, current_node.get_innovation())
def ttt_test(config):
gens = config['max_generations']
pop = None
start_genome = None
#//Hold records for each run
evals = [ 0 for i in range(neatconfig.num_runs) ]
genes = [ 0 for i in range(neatconfig.num_runs) ]
nodes = [ 0 for i in range(neatconfig.num_runs) ]
# Made as lists for pass-by-reference
winnernum = [ 0 ]
winnergenes = [ 0 ]
winnernodes = [ 0 ]
#//For averaging
totalevals = 0
totalgenes = 0
totalnodes = 0
dprint(DEBUG_INFO, "START TTT TEST")
if config['seed_with_start_genome']:
gene_filename = neatconfig.genedir + "/" + config['start_genome_file']
iFile = open(gene_filename, "r")
if not iFile:
dprint(DEBUG_ERROR, "Unable to open starting genome file %s." % (gene_filename, ))
return pop
dprint(DEBUG_INFO, "Opened start genome file %s." % (gene_filename, ))
#//Read in the start Genome
dprint(DEBUG_INFO, "Reading in the start genome")
line = iFile.readline()
words = line.strip().split()
curword = words[0]
gid = int(words[1])
if curword != "genomestart":
dprint(DEBUG_ERROR, "Bad starting genome file %s." % (gene_filename, ))
return pop
dprint(DEBUG_INFO, "Reading in Genome id %d." % (gid,))
start_genome = Genome()
start_genome.SetFromFile(gid, iFile)
iFile.close()
dprint(DEBUG_INFO, "Verifying start_genome")
if not start_genome.verify():
dprint(DEBUG_ERROR, "genome.verify() failed:", start_genome.deep_string())
#Complete a number of runs
for expcount in range(neatconfig.num_runs):
if config['seed_with_start_genome']:
#//Spawn the Population
dprint(DEBUG_INFO, "Spawning Population off Genome")
pop = Population()
pop.SetFromGenome(start_genome, neatconfig.pop_size)
dprint(DEBUG_INFO, "Verifying Spawned Population[%d]" % (expcount, ))
if not pop.verify():
dprint(DEBUG_ERROR, "Population[%d] verification failed" % (expcount, ))
elif config['seed_with_previous_population']:
population_filename = neatconfig.genedir + "/" + config['previous_population_file']
dprint(DEBUG_INFO, "Reading Population from %s" % (population_filename, ))
pop = Population()
pop.SetFromFilename(population_filename)
dprint(DEBUG_INFO, "Verifying Start Population[%d]" % (expcount, ))
if not pop.verify():
dprint(DEBUG_ERROR, "Population[%d] verification failed" % (expcount, ))
#// evolve up to gens generations
gen = 1
while gen <= gens:
dprint(DEBUG_INFO, "Evaluating Spawned Population[%d] Epoch[%d]" % (expcount, gen))
# if not pop.verify():
# dprint(DEBUG_ERROR, "Population[%d] Epoch[%d] verification failed" % (expcount, gen))
#print "Epoch", gen
generation_filename = neatconfig.generationdir + "/tttgen_%d" % (gen,)
# Evaluate one generation, checking for a successful end
#//Check for success
if ttt_epoch(pop, gen, generation_filename, winnernum, winnergenes, winnernodes):
evals[expcount] = neatconfig.pop_size * (gen-1) + winnernum[0]
genes[expcount] = winnergenes[0]
nodes[expcount] = winnernodes[0]
break
# in case we want to change after run has started
config = ttt_read_config(neatconfig.configdir + '/ttt.config')
gens = config['max_generations']
gen += 1
# end of generation loop
if g_found_optimal:
break
# end of num_runs loop
#//Average and print stats
dprint(DEBUG_INFO, "Nodes: ")
for expcount in range(neatconfig.num_runs):
dprint(DEBUG_INFO, nodes[expcount])
totalnodes += nodes[expcount]
dprint(DEBUG_INFO, "Genes: ")
for expcount in range(neatconfig.num_runs):
dprint(DEBUG_INFO, genes[expcount])
totalgenes += genes[expcount]
dprint(DEBUG_INFO, "Evals ")
samples = 0
for expcount in range(neatconfig.num_runs):
dprint(DEBUG_INFO, evals[expcount])
if evals[expcount] > 0:
totalevals += evals[expcount]
samples += 1
if samples > 0:
avgnodes = float(totalnodes)/samples
avggenes = float(totalgenes)/samples
avgevals = float(totalevals)/samples
else:
avgnodes = 0
avggenes = 0
avgevals = 0
dprint(DEBUG_INFO, "Failures:", (neatconfig.num_runs - samples), "out of", neatconfig.num_runs, "runs")
dprint(DEBUG_INFO, "Average Nodes:", avgnodes)
dprint(DEBUG_INFO, "Average Genes:", avggenes)
dprint(DEBUG_INFO, "Average Evals:", avgevals)
return pop
def xor_test(gens):
gene_filename = neatconfig.genedir + "/xorstartgenes"
pop = None
start_genome = None
#//Hold records for each run
evals = [ 0 for i in range(neatconfig.num_runs) ]
genes = [ 0 for i in range(neatconfig.num_runs) ]
nodes = [ 0 for i in range(neatconfig.num_runs) ]
# Made as lists for pass-by-reference
winnernum = [ 0 ]
winnergenes = [ 0 ]
winnernodes = [ 0 ]
#//For averaging
totalevals = 0
totalgenes = 0
totalnodes = 0
iFile = open(gene_filename, "r")
if not iFile:
dprint(DEBUG_ERROR, "Unable to open starting genome file %s." % (gene_filename, ))
return pop
print "START XOR TEST"
#//Read in the start Genome
print "Reading in the start genome"
line = iFile.readline()
words = line.strip().split()
curword = words[0]
gid = int(words[1])
if curword != "genomestart":
print "Bad starting genome file %s." % (gene_filename, )
return pop
print "Reading in Genome id %d." % (gid,)
start_genome = Genome()
start_genome.SetFromFile(gid, iFile)
iFile.close()
print "Verifying start_genome"
if not start_genome.verify():
dprint(DEBUG_ERROR, "genome.verify() failed:", start_genome.deep_string())
#Complete a number of runs
for expcount in range(neatconfig.num_runs):
#//Spawn the Population
print "Spawning Population off Genome2"
pop = Population()
pop.SetFromGenome(start_genome, neatconfig.pop_size)
print "Verifying Spawned Population[%d]" % (expcount, )
if not pop.verify():
dprint(DEBUG_ERROR, "Population[%d] verification failed" % (expcount, ))
#// evolve up to gens generations
for gen in range(1, gens+1):
print "Verifying Spawned Population[%d] Epoch[%d]" % (expcount, gen)
if not pop.verify():
dprint(DEBUG_ERROR, "Population[%d] Epoch[%d] verification failed" % (expcount, gen))
#print "Epoch", gen
generation_filename = neatconfig.generationdir + "/gen_%d" % (gen,)
# Evaluate one generation, checking for a successful end
#//Check for success
if xor_epoch(pop, gen, generation_filename, winnernum, winnergenes, winnernodes):
evals[expcount] = neatconfig.pop_size * (gen-1) + winnernum[0]
genes[expcount] = winnergenes[0]
nodes[expcount] = winnernodes[0]
break
# end of generation loop
if g_found_optimal:
break
# end of num_runs loop
#//Average and print stats
print "Nodes: "
for expcount in range(neatconfig.num_runs):
print nodes[expcount]
totalnodes += nodes[expcount]
print "Genes: "
for expcount in range(neatconfig.num_runs):
print genes[expcount]
totalgenes += genes[expcount]
print "Evals "
samples = 0
for expcount in range(neatconfig.num_runs):
print evals[expcount]
if evals[expcount] > 0:
totalevals += evals[expcount]
samples += 1
if samples > 0:
avgnodes = float(totalnodes)/samples
avggenes = float(totalgenes)/samples
avgevals = float(totalevals)/samples
else:
avgnodes = 0
avggenes = 0
avgevals = 0
print "Failures:", (neatconfig.num_runs - samples), "out of", neatconfig.num_runs, "runs"
print "Average Nodes:", avgnodes
print "Average Genes:", avggenes
print "Average Evals:", avgevals
return pop
def make_child(genome1, genome2, number_of_species):
if genome1.fitness > genome2.fitness:
new_genes = select_genes(genome1, genome2)
elif genome1.fitness < genome2.fitness:
new_genes = select_genes(genome2, genome1)
else:
new_genes = select_genes(genome1, genome2)
nodes = [i + 1 for i in range(genome1.input_nodes + genome1.output_nodes)]
hidden_nodes = []
for gene in new_genes:
if gene.type == 0:
if gene.out_node not in hidden_nodes:
hidden_nodes.append(gene.out_node)
elif gene.type == 1:
if gene.in_node not in hidden_nodes:
hidden_nodes.append(gene.in_node)
node_array = np.concatenate((nodes, hidden_nodes), axis=None)
new_genome = Genome.Genome(0, 0, node_array, genome1.input_nodes,
genome1.output_nodes)
new_genome.connection_genes = new_genes
""" Add a new connection between to nodes"""
# if random.uniform(0, 1) <= CREATE_NEW_CONNECTION_PROBABILITY:
# new_genome.add_connection()
if number_of_species > 5:
""" Add a random amount of weights form 1 to N """
for i in range(
random.randint(1, int(CREATE_NEW_CONNECTION_PROBABILITY))):
new_genome.add_connection()
""" Add a new node inside an existing connection between input node and output node """
if random.uniform(0, 1) <= CREATE_NEW_NODE_PROBABILITY:
new_genome.add_node()
""" Randomly mutate som genes """
if random.uniform(0, 1) <= MUTATE_NEW_CHILD_PROBABILITY:
for genome in new_genome.connection_genes:
if random.uniform(0, 1) <= MUTATE_GENE_PROBABILITY:
if random.uniform(0,
1) <= CHANGE_WEIGHT_SLIGHTLY_PROBABILITY:
genome.weight = genome.weight + random.uniform(-1,
1) * 0.1
else:
genome.weight = random.uniform(-1, 1)
else:
""" Add a random amount of weights form 2 to 3 """
for i in range(random.randint(2, 3)):
new_genome.add_connection()
""" Add a new node inside an existing connection between input node and output node """
if random.uniform(0, 1) <= 0.35:
new_genome.add_node()
""" Randomly mutate som genes """
if random.uniform(0, 1) <= 0.8:
for genome in new_genome.connection_genes:
if random.uniform(0, 1) <= 1:
if random.uniform(0, 1) <= 0.8:
genome.weight = genome.weight + random.uniform(-1,
1) * 0.2
else:
genome.weight = random.uniform(-1, 1)
return new_genome
def test_empty_crossover(self):
g1 = Genome(3, 1)
g2 = Genome(3, 1)
a1, a2 = Population.align_genome(g1, g2)
c = Population.crossover(a1, a2, g1.get_input_nodes(), g1.get_output_nodes())
self.assertGreaterEqual(4, len(c.nodes))
def setUpClass(cls):
print("Testing Mutator")
with open(os.path.join(here, "loopback_test_genome.yaml"),
'r') as in_file:
cls.loopback_test_genome = Genome().from_yaml(
yaml.load(in_file.read()))
def test_get_next_nodes(self):
g = Genome(1, 1)
g.create_node_between(1, 2, 3, 1)
self.assertEqual([3], [n.get_innovation() for n in g.select_node_by_id(1).get_next_nodes()])
def test_align_genome(self):
g1 = Genome(3, 1)
g1.create_node(Node.TYPE_HIDDEN, 5)
g1.connect_nodes_by_id(1, 4, 1)
g1.connect_nodes_by_id(2, 4, 2)
g1.connect_nodes_by_id(3, 4, 3)
g1.connect_nodes_by_id(2, 5, 4)
g1.connect_nodes_by_id(5, 4, 5)
g1.connect_nodes_by_id(1, 5, 8)
g2 = Genome(3, 1)
g2.create_node(Node.TYPE_HIDDEN, 5)
g2.create_node(Node.TYPE_HIDDEN, 6)
g2.connect_nodes_by_id(1, 4, 1)
g2.connect_nodes_by_id(2, 4, 2)
g2.connect_nodes_by_id(3, 4, 3)
g2.connect_nodes_by_id(2, 5, 4)
g2.connect_nodes_by_id(5, 4, 5)
g2.connect_nodes_by_id(5, 6, 6)
g2.connect_nodes_by_id(6, 4, 7)
g2.connect_nodes_by_id(3, 5, 9)
g2.connect_nodes_by_id(1, 6, 10)
# p = Population(2, 3, 1)
# p.population['s0'] = [g1, g2]
a1, a2 = Population.align_genome(g1, g2)
self.assertEqual(1, a1[0].get_innovation())
self.assertEqual(2, a1[1].get_innovation())
self.assertEqual(3, a1[2].get_innovation())
self.assertEqual(4, a1[3].get_innovation())
self.assertEqual(5, a1[4].get_innovation())
self.assertEqual(None, a1[5])
self.assertEqual(None, a1[6])
self.assertEqual(8, a1[7].get_innovation())
self.assertEqual(None, a1[8])
self.assertEqual(None, a1[9])
self.assertEqual(1, a2[0].get_innovation())
self.assertEqual(2, a2[1].get_innovation())
self.assertEqual(3, a2[2].get_innovation())
self.assertEqual(4, a2[3].get_innovation())
self.assertEqual(5, a2[4].get_innovation())
self.assertEqual(6, a2[5].get_innovation())
self.assertEqual(7, a2[6].get_innovation())
self.assertEqual(None, a2[7])
self.assertEqual(9, a2[8].get_innovation())
self.assertEqual(10, a2[9].get_innovation())
def setup(genome, node_inno, con_inno):
seed(1337)
print('========== Test 1 ==========')
genome = Genome()
genome.add_node(Node(0, 0, NodeType.INPUT))
genome.add_node(Node(1, 1, NodeType.OUTPUT))
genome.add_connection(Connection(0, 0, 1, 0.5, True))
net = Network(genome)
input = [1.0]
for _ in range(3):
output = net.calculate(input)
print(f'Output len={len(output)}, output[0]={output[0]}=0.9192')
print()
print('========== Test 2 ==========')
genome = Genome()
genome.add_node(Node(0, 0, NodeType.INPUT))
genome.add_node(Node(1, 1, NodeType.OUTPUT))
genome.add_connection(Connection(0, 0, 1, 0.1, True))
net = Network(genome)
input = [-0.5]
for _ in range(3):
output = net.calculate(input)
print(f'Output len={len(output)}, output[0]={output[0]}=0.50973')
print()
print('========== Test 3 ==========')
genome = Genome()
genome.add_node(Node(0, 0, NodeType.INPUT))
genome.add_node(Node(1, 2, NodeType.OUTPUT))
genome.add_node(Node(2, 1, NodeType.HIDDEN))
genome.add_connection(Connection(0, 0, 2, 0.4, True))
genome.add_connection(Connection(1, 2, 1, 0.7, True))
net = Network(genome)
input = [0.9]
for _ in range(3):
output = net.calculate(input)
print(f'Output len={len(output)}, output[0]={output[0]}=0.9524')
print()
print('========== Test 4 ==========')
genome = Genome()
genome.add_node(Node(0, 0, NodeType.INPUT))
genome.add_node(Node(1, 0, NodeType.INPUT))
genome.add_node(Node(2, 0, NodeType.INPUT))
genome.add_node(Node(3, 2, NodeType.OUTPUT))
genome.add_node(Node(4, 1, NodeType.HIDDEN))
genome.add_connection(Connection(0, 0, 4, 0.4, True))
genome.add_connection(Connection(1, 1, 4, 0.7, True))
genome.add_connection(Connection(2, 2, 4, 0.1, True))
genome.add_connection(Connection(3, 4, 3, 1.0, True))
net = Network(genome)
input = [0.5, 0.75, 0.9]
for _ in range(3):
output = net.calculate(input)
print(f'Output len={len(output)}, output[0]={output[0]}=0.9924')
print()
print('========== Test 5 ==========')
genome = Genome()
genome.add_node(Node(0, 0, NodeType.INPUT))
genome.add_node(Node(1, 0, NodeType.INPUT))
genome.add_node(Node(2, 0, NodeType.INPUT))
genome.add_node(Node(3, 2, NodeType.OUTPUT))
genome.add_node(Node(4, 1, NodeType.HIDDEN))
genome.add_node(Node(5, 1, NodeType.HIDDEN))
genome.add_connection(Connection(0, 0, 4, 0.4, True))
genome.add_connection(Connection(1, 1, 4, 0.7, True))
genome.add_connection(Connection(2, 2, 4, 0.1, True))
genome.add_connection(Connection(3, 4, 3, 1.0, True))
genome.add_connection(Connection(4, 2, 5, 0.2, True))
genome.add_connection(Connection(5, 5, 4, 0.75, True))
genome.add_connection(Connection(6, 5, 3, 0.55, True))
net = Network(genome)
input = [1., 2., 3.]
for _ in range(3):
output = net.calculate(input)
print(f'Output len={len(output)}, output[0]={output[0]}=0.99895')
print()
def test_run(self):
g = Genome(3, 1, initializer=lambda: random.random())
g.connect_nodes_by_id(1, 4, 1)
g.connect_nodes_by_id(2, 4, 2)
g.connect_nodes_by_id(3, 4, 3)
g.create_node_between(2, 4, 5, 4)
g.connect_nodes_by_id(1, 5, 6)
g.connect_nodes_by_id(5, 5, 7)
output = g.run([1, 1, 1])
self.assertNotEqual(0, output[0])
def test_get_output_nodes(self):
g = Genome(3, 1)
self.assertEqual([4], [g.get_innovation() for g in g.get_output_nodes()])
def test_mutate_add_node(self):
g = Genome(3, 1)
g.connect_nodes_by_id(1, 4, 1)
g.connect_nodes_by_id(2, 4, 2)
g.connect_nodes_by_id(3, 4, 3)
g.create_node_between(2, 4, 5, 4)
g.connect_nodes_by_id(1, 5, 6)
self.assertEqual(True, g.select_node_by_id(1).is_connected_to_next_by_id(4))
self.assertEqual(True, g.select_node_by_id(4).is_connected_to_prev_by_id(1))
self.assertEqual(True, g.select_node_by_id(1).is_connected_to_next_by_id(5))
self.assertEqual(True, g.select_node_by_id(2).is_connected_to_next_by_id(5))
self.assertEqual(True, g.select_node_by_id(5).is_connected_to_next_by_id(4))
self.assertEqual(True, g.select_node_by_id(3).is_connected_to_next_by_id(4))
g.create_node_between(3, 4, 6, 7)
self.assertIsNotNone(g.select_node_by_id(6))
self.assertRaises(Exception, lambda: g.select_node_by_id(7))
def test_mutate_add_connection(self):
g = Genome(3, 1)
g.connect_nodes_by_id(1, 4, 1)
g.connect_nodes_by_id(2, 4, 2)
g.connect_nodes_by_id(3, 4, 3)
g.create_node_between(2, 4, 5, 4)
g.connect_nodes_by_id(1, 5, 6)
self.assertEqual(True, g.select_node_by_id(1).is_connected_to_next_by_id(4))
self.assertEqual(True, g.select_node_by_id(4).is_connected_to_prev_by_id(1))
self.assertEqual(True, g.select_node_by_id(1).is_connected_to_next_by_id(5))
self.assertEqual(True, g.select_node_by_id(2).is_connected_to_next_by_id(5))
self.assertEqual(True, g.select_node_by_id(5).is_connected_to_next_by_id(4))
self.assertEqual(True, g.select_node_by_id(3).is_connected_to_next_by_id(4))
g.connect_nodes_by_id(3, 5, 7)
self.assertEqual(True, g.select_node_by_id(3).is_connected_to_next_by_id(5))
def test(genome, node_inno, con_inno):
genome[2] = Genome.crossover(genome[0], genome[1], 0.10)
print(genome[2])
pass
def run_simulation():
multiprocessing.set_start_method(
'spawn') # Spawn fresh worker processes, don't use fork
config = load_config()
setup_logging(config['log_level'])
Evolution.set_globals_from_config(config)
Speciation._config = config
print('Using these parameters:')
for k, v in config.items():
print('- {}: {}'.format(k, v))
global mutations_in_gen
population_size = config['population_size'] # default 500
generations = config['generations'] # default 100
species_list = []
genomes_list = []
input_nodes = config['input_nodes'] # default 130
output_nodes = config['output_nodes'] # default 7
initial_nodes = [i + 1 for i in range(input_nodes + output_nodes)]
new_genome = Genome.Genome(1, 1, initial_nodes, input_nodes, output_nodes)
number_of_new_connections = random.randint(2, 8)
for i in range(number_of_new_connections):
new_genome.add_connection()
new_species = Species.Species(new_genome)
species_list.append(new_species)
genomes_list.append(new_genome)
data = CollectData.DataCollection(population_size, generations, config)
for i in range(population_size - 1):
new_genome = Genome.Genome(i + 2, 1, initial_nodes, input_nodes,
output_nodes)
number_of_new_connections = random.randint(1, 4)
for _ in range(number_of_new_connections):
new_genome.add_connection()
Speciation.add_to_species(species_list, new_genome)
genomes_list.append(new_genome)
print('New genomes added to species list:', input_nodes + output_nodes)
print('Number of new species:', len(species_list))
simulator = ParallelSimulator(num_workers=config['num_workers'],
max_steps=config['max_simulation_steps'],
render=config['render'])
for gen_num in range(1, generations + 1):
mutations_in_gen = []
"""
counter = 0
for genome in genomes_list:
SimulateMario.simulate_run(genome, 5000, False)
counter += 1
print('Simulating genome:', counter)
"""
simulator.simulate_genomes(genomes_list)
data.collect_data(genomes_list, gen_num, len(species_list))
print('\nFitness:', [genome.fitness for genome in genomes_list])
# for genome in genomes_list:
# print(genome.fitness)
print('\nMaking new children.')
print('\nNumber of species:', len(species_list))
Speciation.calculate_adjusted_fitness(species_list)
genomes_list = Evolution.make_new_generation(population_size,
species_list, gen_num + 1)
""" Empty all genomes from species """
for species in species_list:
# species.update_species_parameters()
species.genomes = []
""" Add new genomes to the existing species, or create new ones """
for i in range(0, len(genomes_list)):
Speciation.add_to_species(species_list, genomes_list[i])
print('Generation', gen_num, 'done.\n')
""" Remove all species without genomes """
species_without_genomes_exist = True
while species_without_genomes_exist:
species_without_genomes_exist = False
for i in range(0, len(species_list)):
if len(species_list[i].genomes) == 0:
del species_list[i]
species_without_genomes_exist = True
break
""" Replace old species representative with new """
for species in species_list:
species.replace_representative()
def test(genome, node_inno, con_inno):
Genome.load('output/save_load.json', genome)
def newGeneration():
global reproduction_count
reproduction_count = 0
global next_generation
# if len(next_generation) > 1:
# if len(next_generation) < 10:
# neat.species_threshold -= 0.3
# elif len(next_generation) >= 10:
# neat.species_threshold +=0.3
children = []
calculateAverageFitness(next_generation)
updateStagnationInformation()
removeStagnantSpecies()
calculateAverageFitness(next_generation)
totalFitness = totalAverageFitness(next_generation)
for x in next_generation:
genelog.info("[Species : " + str(x.number) + " Organisms: " +
str(len(x.organisms)) + " ]")
x.sort()
if (len(x.organisms) > 10):
x.removeUnfit()
genelog.info("[Trim Step- Organisms Survived: " +
str(len(x.organisms)) + " ]")
breedCount = int((x.repFitness / totalFitness) * gen_iterations) - 1
for i in range(breedCount):
if random.random() < crossover_rate and len(x.organisms) > 1:
genelog.info("[ORGANISM]")
xx = random.randrange(0, len(x.organisms))
xy = random.randrange(0, len(x.organisms))
while xx == xy:
xx = random.randrange(0, len(x.organisms))
xy = random.randrange(0, len(x.organisms))
if x.organisms[xy].global_fitness > x.organisms[
xx].global_fitness:
temp = xx
xx = xy
xy = temp
childGenome = Genome.crossover(x.organisms[xx].genome,
x.organisms[xy].genome)
reproduction_count += 1
# apply random chance of further mutation
childGenome.mutate()
childGenome.mutate_topology()
childOrganism = Agent(i_shape, o_shape, childGenome,
agent_name)
# TODO: random enable disable genes
children.append(childOrganism)
else:
xx = random.randrange(0, len(x.organisms))
childGenome = copy.deepcopy(x.organisms[xx].genome)
childGenome.mutate()
childOrganism = Agent(i_shape, o_shape, childGenome,
agent_name)
children.append(childOrganism)
reproduction_count += 1
if random.random() < mating_rate and len(next_generation) > 1:
print("Interspecies Breeding")
xx = x.organisms[0]
xy = next_generation[random.randrange(
0, len(next_generation))].organisms[0]
while xx == xy:
xy = next_generation[random.randrange(
0, len(next_generation))].organisms[0]
childGenome = Genome.crossover(xx.genome, xy.genome)
reproduction_count += 1
childGenome.mutate()
childGenome.mutate_topology()
childOrganism = Agent(i_shape, o_shape, childGenome, agent_name)
children.append(childOrganism)
for species in next_generation:
species.reduce()
for organism in children:
speciate(organism)
global exceeded
def test_crossover(self):
g1 = Genome(3, 1)
g1.create_node(Node.TYPE_HIDDEN, 5)
g1.connect_nodes_by_id(1, 4, 1)
g1.connect_nodes_by_id(2, 4, 2)
g1.connect_nodes_by_id(3, 4, 3)
g1.connect_nodes_by_id(2, 5, 4)
g1.connect_nodes_by_id(5, 4, 5)
g1.connect_nodes_by_id(1, 5, 8)
g2 = Genome(3, 1)
g2.create_node(Node.TYPE_HIDDEN, 5)
g2.create_node(Node.TYPE_HIDDEN, 6)
g2.connect_nodes_by_id(1, 4, 1)
g2.connect_nodes_by_id(2, 4, 2)
g2.connect_nodes_by_id(3, 4, 3)
g2.connect_nodes_by_id(2, 5, 4)
g2.connect_nodes_by_id(5, 4, 5)
g2.connect_nodes_by_id(5, 6, 6)
g2.connect_nodes_by_id(6, 4, 7)
g2.connect_nodes_by_id(3, 5, 9)
g2.connect_nodes_by_id(1, 6, 10)
p = Population(2, 3, 1)
p.population[0] = g1
p.population[1] = g2
a1, a2 = Population.align_genome(g1, g2)
g3 = Population.crossover(a1, a2, g1.get_input_nodes(), g1.get_output_nodes())
self.assertEqual(10, len(g3.connections))
self.assertEqual(6, len(g3.nodes))
self.assertEqual(1, g3.select_connection_by_innovation(1).get_innovation())
self.assertEqual(2, g3.select_connection_by_innovation(2).get_innovation())
self.assertEqual(3, g3.select_connection_by_innovation(3).get_innovation())
self.assertEqual(4, g3.select_connection_by_innovation(4).get_innovation())
self.assertEqual(5, g3.select_connection_by_innovation(5).get_innovation())
self.assertEqual(6, g3.select_connection_by_innovation(6).get_innovation())
self.assertEqual(7, g3.select_connection_by_innovation(7).get_innovation())
self.assertEqual(8, g3.select_connection_by_innovation(8).get_innovation())
self.assertEqual(9, g3.select_connection_by_innovation(9).get_innovation())
self.assertEqual(10, g3.select_connection_by_innovation(10).get_innovation())
self.assertEqual((2, 3), Population.calculate_excess_disjoint(g1, g2))
self.assertEqual(5, species_distance(g1, g2))