network.print_data()
folds = 4
result = [0]
i = 0
start_time = time()
while sum(result) / folds < 90:
results = network.learn_kfolds(folds, times=1)
scores = [(n, [round(x) for x in out] == check) for n, out, check in results]
stuff = Counter(scores)
result = [stuff[(i, True)] / (stuff[(i, False)] + stuff[(i, True)]) * 100 for i in range(folds)]
print("folds results: ", result)
i += 1
if i % 10 == 0:
print("saving dump")
network.dump_network('snek-play-7-new1.yaml')
new_learning_rate = uniform(0.0, 1.0)
for layer in network.layers:
for neuron in layer.neurons:
neuron.learning_factor = new_learning_rate
print("learning for: %s" % (time() - start_time))
end_time = time()
print("learning time: %s" % (end_time - start_time))
try:
network.dump_cypher('snek2.cypher')
except:
pass
network.dump_network('snek-play-awesome.yaml')
{"inputs": [0, 0], "outputs": [0]},
{"inputs": [0, 1], "outputs": [1]},
{"inputs": [1, 1], "outputs": [0]},
{"inputs": [1, 0], "outputs": [1]}
]
network.load_learning_data(learning_data)
network.normalize_learning_data()
print("------- learn -------")
network.print_data()
network.learn(times=10000)
i = [[0, 0], [0, 1], [1, 1], [1, 0]]
o = [network.test(io) for io in i]
print("------- test -------")
network.print_io(i, o)
print("------ weights -----")
network.print_weights()
bias = BiasNeuron(0.1)
bias.set_network_name(net_name)
middle.neurons[0].connect(bias, 'right')
network.dump_network('../data/trained_networks/xor-dump2.yaml', prompt=True)
network.dump_cypher('../data/cypher/xor.cypher', additional_neurons=[bias])
})
inputs = InputLayer([1, 1, 1, 1])
middle = Layer(5)
middle2 = Layer(3)
output = OutputLayer([1, 1, 1])
network = Network([inputs, middle, middle2, output], 'iris')
network.connect()
network.load_learning_data(learning_data)
network.normalize_learning_data()
print("------- learn -------")
network.print_data()
folds = 4
results = network.learn_kfolds(folds, times=1000)
scores = [(n, [round(x) for x in out] == check) for n, out, check in results]
stuff = Counter(scores)
print("folds results: ", [stuff[(i, True)] / (stuff[(i, False)] + stuff[(i, True)]) * 100 for i in range(folds)])
i = [
[6.9, 3.1, 5.1, 2.3], # Iris-virginica
[5.0, 2.0, 3.5, 1.0], # Iris-versicolor
[5.4, 3.7, 1.5, 0.2] # Iris-setosa
]
o = [network.test(io) for io in i]
network.print_io(i, o, output_names=['Iris-virginica', 'Iris-versicolor', 'Iris-setosa'])
network.dump_network('../data/trained_networks/iris.yaml', prompt=True)
network.dump_cypher('../data/cypher/iris.cypher')
network.connect()
network.load_learning_data(learning_data)
#network.normalize_learning_data()
print("------- learn -------")
network.print_data()
#network.learn(times=100)
results = network.learn_kfolds(4, times=100)
scores = [(n, [round(x) for x in out] == check) for n, out, check in results]
stuff = Counter(scores)
print([
stuff[(i, True)] / (stuff[(i, False)] + stuff[(i, True)]) * 100
for i in range(4)
])
i = [
[tic_tac_map[x]
for x in ['x', 'x', 'x', 'o', 'b', 'x', 'b', 'o', 'o']], # positive
[tic_tac_map[x]
for x in ['x', 'o', 'o', 'x', 'x', 'o', 'b', 'x', 'o']] # negative
]
o = [network.test(io) for io in i]
network.print_io(i, o, output_names=['positive/negative'])
print("------ weights -----")
network.print_weights()
network.dump_network('data/trained_networks/tictactoe.yaml', prompt=True)
