def test_update_gp(seed=42):
rng = np.random.RandomState(seed)
for nb_outputs in [1, 2]:
# Generate dummy data
X_tr = rng.normal(size=(N, input_shape[0], input_shape[1]))
Y_tr = [rng.normal(size=(N, 1)) for _ in xrange(nb_outputs)]
X_val = rng.normal(size=(N, input_shape[0], input_shape[1]))
Y_val = [rng.normal(size=(N, 1)) for _ in xrange(nb_outputs)]
# Build & compile the model
model = build_model(nb_outputs)
loss = [gen_gp_loss(gp) for gp in model.gp_output_layers]
model.compile(optimizer=optimizer, loss=loss)
# Setup the callback
update_gp_callback = UpdateGP((X_tr, Y_tr),
val_ins=(X_val, Y_val),
batch_size=batch_size)
update_gp_callback._set_model(model)
# Test the callback
epoch_logs, batch_logs = {}, {}
batch_logs['size'] = batch_size
batch_logs['ids'] = np.arange(batch_size)
update_gp_callback.on_epoch_begin(1, epoch_logs)
update_gp_callback.on_batch_begin(1, batch_logs)
update_gp_callback.on_epoch_end(1, epoch_logs)
assert 'gp_update_elapsed' in epoch_logs
assert 'val_nlml' in epoch_logs
assert 'val_mse' in epoch_logs
def test_compile():
model = build_model()
# Generate losses for GP outputs
loss = [gen_gp_loss(gp) for gp in model.gp_output_layers]
# Compile the model
model.compile(optimizer=optimizer, loss=loss)
def test_evaluate(seed=42):
rng = np.random.RandomState(seed)
for nb_outputs in [1, 2]:
# Generate dummy data
X_ts = rng.normal(size=(N, input_shape[0], input_shape[1]))
Y_ts = [rng.normal(size=(N, 1)) for _ in xrange(nb_outputs)]
# Build & compile the model
model = build_model(nb_outputs)
loss = [gen_gp_loss(gp) for gp in model.gp_output_layers]
model.compile(optimizer=optimizer, loss=loss)
# Evaluate the model
nlml = model.evaluate(X_ts, Y_ts, batch_size=batch_size, verbose=0)
def test_finetune(gp_n_iter=10, seed=42):
rng = np.random.RandomState(seed)
for nb_outputs in [1, 2]:
# Generate dummy data
X_tr = rng.normal(size=(N, input_shape[0], input_shape[1]))
Y_tr = [rng.normal(size=(N, 1)) for _ in xrange(nb_outputs)]
# Build & compile the model
model = build_model(nb_outputs)
loss = [gen_gp_loss(gp) for gp in model.gp_output_layers]
model.compile(optimizer=optimizer, loss=loss)
# Finetune the model
model.finetune(X_tr, Y_tr,
batch_size=batch_size,
gp_n_iter=gp_n_iter,
verbose=0)
def test_predict(seed=42):
rng = np.random.RandomState(seed)
for nb_outputs in [1, 2]:
# Generate dummy data
X_tr = rng.normal(size=(N, input_shape[0], input_shape[1]))
Y_tr = [rng.normal(size=(N, 1)) for _ in xrange(nb_outputs)]
X_ts = rng.normal(size=(N, input_shape[0], input_shape[1]))
Y_ts = [rng.normal(size=(N, 1)) for _ in xrange(nb_outputs)]
# Build & compile the model
model = build_model(nb_outputs)
loss = [gen_gp_loss(gp) for gp in model.gp_output_layers]
model.compile(optimizer=optimizer, loss=loss)
# Predict
Y_pr = model.predict(X_ts, X_tr, Y_tr,
batch_size=batch_size, verbose=0)
assert type(Y_pr) is list
assert len(Y_pr) == len(Y_ts)
assert np.all([(yp.shape == yt.shape) for yp, yt in zip(Y_pr, Y_ts)])
def test_assemble_gpgru():
for gp_type in ['GP', 'MSGP']:
model = assemble('GP-GRU', [gru_configs['1H'], gp_configs[gp_type]])
loss = [gen_gp_loss(gp) for gp in model.output_layers]
model.compile(optimizer=optimizer, loss=loss)
assert model.built
def main():
# Load data
X_train, y_train = load_data('actuator', stop=45.)
X_valid, y_valid = load_data('actuator', start=45., stop=55.)
X_test, y_test = load_data('actuator', start=55.)
data = {
'train': (X_train, y_train),
'valid': (X_valid, y_valid),
'test': (X_test, y_test),
}
data = preprocess_data(data,
standardize=True,
multiple_outputs=True,
t_lag=10,
t_future_shift=1,
t_future_steps=1,
t_sw_step=1)
# Model & training parameters
nb_train_samples = data['train'][0].shape[0]
input_shape = data['train'][0].shape[1:]
nb_outputs = len(data['train'][1])
gp_input_shape = (1, )
batch_size = 128
nb_epoch = 5
# Retrieve model config
nn_configs = load_NN_configs(filename='lstm.yaml',
input_shape=input_shape,
output_shape=gp_input_shape,
H_dim=16,
H_activation='tanh',
dropout=0.1)
gp_configs = load_GP_configs(filename='gp.yaml',
nb_outputs=nb_outputs,
batch_size=batch_size,
nb_train_samples=nb_train_samples,
cov='SEiso',
hyp_lik=-2.0,
hyp_cov=[[-0.7], [0.0]])
# Construct & compile the model
model = assemble('GP-LSTM', [nn_configs['1H'], gp_configs['GP']])
loss = [gen_gp_loss(gp) for gp in model.output_layers]
model.compile(optimizer=Adam(1e-2), loss=loss)
# Callbacks
callbacks = [EarlyStopping(monitor='val_mse', patience=10)]
# Train the model
history = train(model,
data,
callbacks=callbacks,
gp_n_iter=5,
checkpoint='lstm',
checkpoint_monitor='val_mse',
nb_epoch=nb_epoch,
batch_size=batch_size,
verbose=2)
# Finetune the model
model.finetune(*data['train'],
batch_size=batch_size,
gp_n_iter=100,
verbose=0)
# Test the model
X_test, y_test = data['test']
y_preds = model.predict(X_test)
rmse_predict = RMSE(y_test, y_preds)
print('Test predict RMSE:', rmse_predict)
