def get_net_prediction(train_data,
train_truth,
test_data,
test_truth,
hidden=(5, ),
weight_decay=0.0,
dropout_prob=0.0,
learning_rate=None,
epochs=25,
verbose=False,
iter_id=None):
container = NeuralNetContainer()
container.learning_rate = learning_rate
container.dropout_prob = dropout_prob
container.weight_decay = weight_decay
container.epochs = epochs
container.hidden_layers = hidden
container.verbose = verbose
container.plot = get_should_plot()
mms = MinMaxScaler(feature_range=(-1, 1)) # Scale output from -1 to 1.
train_y = mms.fit_transform(train_truth[:, np.newaxis])
n_features = train_data.shape[1]
collect_time_stats = get_is_time_stats()
if collect_time_stats:
start = time.time()
# Find and return an effectively initialized network to start.
container = _get_initial_net(container, n_features, train_data, train_y)
# Train the network.
if collect_time_stats:
# Train a specific time, never terminating early.
_train_net(container,
train_data,
train_y,
override_epochs=TIMING_EPOCHS,
is_check_train=False)
else:
# Normal training, enable all heuristics.
_train_net(container, train_data, train_y)
if collect_time_stats:
end = time.time()
print('Fitting took {} seconds'.format(end - start))
print(
json.dumps({
'seconds': end - start,
'hidden': container.hidden_layers
}))
# Unsupervised (test) dataset.
predicted = _predict(container, test_data)
predicted = mms.inverse_transform(predicted)
return predicted.ravel()
def main():
params = { 'hidden': HIDDEN
, 'epochs' : (EPOCHS,)
}
backend = PARALLEL_BACKEND
if get_is_on_gpu() or get_is_time_stats() or get_should_plot():
backend = SINGLE_CORE_BACKEND
run_optimization( get_net_prediction, params, 'optimal_nn.shelf', 'N'
, sample_size_multiplier=DOUBLE_MULTIPLIER
, backend=backend, retry_nans=True)
def main():
params = { 'hidden': HIDDEN
, 'dropout_prob': DROPOUT
, 'weight_decay': WEIGHT_DECAY
, 'epochs': (EPOCHS,)
}
backend = PARALLEL_BACKEND
if get_is_on_gpu() or get_is_time_stats() or get_should_plot():
backend = SINGLE_CORE_BACKEND
run_optimization(get_net_prediction, params, 'optimal_wddonn.shelf', 'NWDDO', backend=backend, retry_nans=True)
def get_net_prediction( train_data, train_truth, test_data, test_truth
, hidden=(5,), weight_decay=0.0, dropout_prob=0.0
, learning_rate=None, epochs=25, verbose=False
, iter_id=None
):
container = NeuralNetContainer()
container.learning_rate = learning_rate
container.dropout_prob = dropout_prob
container.weight_decay = weight_decay
container.epochs = epochs
container.hidden_layers = hidden
container.verbose = verbose
container.plot = get_should_plot()
mms = MinMaxScaler(feature_range= (-1, 1)) # Scale output from -1 to 1.
train_y = mms.fit_transform(train_truth[:,np.newaxis])
n_features = train_data.shape[1]
collect_time_stats = get_is_time_stats()
if collect_time_stats:
start = time.time()
# Find and return an effectively initialized network to start.
container = _get_initial_net(container, n_features, train_data, train_y)
# Train the network.
if collect_time_stats:
# Train a specific time, never terminating early.
_train_net(container, train_data, train_y, override_epochs=TIMING_EPOCHS, is_check_train=False)
else:
# Normal training, enable all heuristics.
_train_net(container, train_data, train_y)
if collect_time_stats:
end = time.time()
print('Fitting took {} seconds'.format(end - start))
print(json.dumps({'seconds': end - start, 'hidden': container.hidden_layers}))
# Unsupervised (test) dataset.
predicted = _predict(container, test_data)
predicted = mms.inverse_transform(predicted)
return predicted.ravel()