results.append(epoch_and_MSE[0])
#print "\n\nNet After Training\n", network
# save the network
network.save_to_file( "trained_configuration.pkl" )
# load a stored network
# network = NeuralNet.load_from_file( "trained_configuration.pkl" )
dfs_concatenated = intermediate_post_process_weights(seed_value, data_collector, dfs_concatenated)
# print out the result
for example_number, example in enumerate(training_set):
inputs_for_training_example = example.features
network.inputs_for_training_example = inputs_for_training_example
output_from_network = network.calc_networks_output()
print "\tnetworks input:", example.features, "\tnetworks output:", output_from_network, "\ttarget:", example.targets
print results
print
print np.median(results)
print
print dfs_concatenated
print
end_angle_values = dfs_concatenated["end"]["hyperplane_angle"]
treatment_values = dfs_concatenated["treatment"]["hyperplane_angle"]
list_of_dfs = [treatment_values] + [ (dfs_concatenated[epochs]["hyperplane_angle"]) for epochs in [0] ] + [end_angle_values]
selected_df = pd.concat( list_of_dfs, axis=1 )
print selected_df
experimental_weight_setting_function(network)
data_collection_interval = 1000
data_collector = NetworkDataCollector(network, data_collection_interval)
# start training on test set one
epoch_and_MSE = network.backpropagation(training_set, 0.01, 3000,
data_collector)
results.append(epoch_and_MSE[0])
# save the network
network.save_to_file("trained_configuration.pkl")
# load a stored network
# network = NeuralNet.load_from_file( "trained_configuration.pkl" )
print "\n\nNetwork State after backpropagation\n", network, "\n"
# print out the result
# print out the result
for example_number, example in enumerate(training_set):
inputs_for_training_example = example.features
network.inputs_for_training_example = inputs_for_training_example
output_from_network = network.calc_networks_output()
print "\tnetworks input:", example.features, "\tnetworks output:", output_from_network, "\ttarget:", example.targets
print results
print
print np.median(results)
print
