def test_multivariate(self):
dtype = dtypes.float32
num_features = 3
covariance = numpy.eye(num_features)
# A single off-diagonal has a non-zero value in the true transition
# noise covariance.
covariance[-1, 0] = 1.
covariance[0, -1] = 1.
dataset_size = 100
values = numpy.cumsum(numpy.random.multivariate_normal(
mean=numpy.zeros(num_features), cov=covariance, size=dataset_size),
axis=0)
times = numpy.arange(dataset_size)
model = MultivariateLevelModel(
configuration=state_space_model.StateSpaceModelConfiguration(
num_features=num_features,
dtype=dtype,
use_observation_noise=False,
transition_covariance_initial_log_scale_bias=5.))
estimator = estimators.StateSpaceRegressor(
model=model,
optimizer=gradient_descent.GradientDescentOptimizer(0.1))
data = {
feature_keys.TrainEvalFeatures.TIMES: times,
feature_keys.TrainEvalFeatures.VALUES: values
}
train_input_fn = input_pipeline.RandomWindowInputFn(
input_pipeline.NumpyReader(data), batch_size=16, window_size=16)
estimator.train(input_fn=train_input_fn, steps=1)
for component in model._ensemble_members:
# Check that input statistics propagated to component models
self.assertTrue(component._input_statistics)
def dry_run_train_helper(
self, sample_every, period, num_samples, model_type, model_args,
num_features=1):
numpy.random.seed(1)
dtype = dtypes.float32
features = self.simple_data(
sample_every, dtype=dtype, period=period, num_samples=num_samples,
num_features=num_features)
model = model_type(
configuration=(
state_space_model.StateSpaceModelConfiguration(
num_features=num_features,
dtype=dtype,
covariance_prior_fn=lambda _: 0.)),
**model_args)
class _RunConfig(estimator_lib.RunConfig):
@property
def tf_random_seed(self):
return 4
estimator = estimators.StateSpaceRegressor(model, config=_RunConfig())
train_input_fn = input_pipeline.RandomWindowInputFn(
input_pipeline.NumpyReader(features), num_threads=1, shuffle_seed=1,
batch_size=16, window_size=16)
eval_input_fn = input_pipeline.WholeDatasetInputFn(
input_pipeline.NumpyReader(features))
estimator.train(input_fn=train_input_fn, max_steps=1)
first_evaluation = estimator.evaluate(input_fn=eval_input_fn, steps=1)
estimator.train(input_fn=train_input_fn, max_steps=3)
second_evaluation = estimator.evaluate(input_fn=eval_input_fn, steps=1)
self.assertLess(second_evaluation["loss"], first_evaluation["loss"])
def _time_dependency_test_template(self, model_type):
"""Test that a time-dependent observation model influences predictions."""
model = model_type()
estimator = estimators.StateSpaceRegressor(
model=model, optimizer=gradient_descent.GradientDescentOptimizer(0.1))
values = numpy.reshape([1., 2., 3., 4.],
newshape=[1, 4, 1])
input_fn = input_pipeline.WholeDatasetInputFn(
input_pipeline.NumpyReader({
feature_keys.TrainEvalFeatures.TIMES: [[0, 1, 2, 3]],
feature_keys.TrainEvalFeatures.VALUES: values
}))
estimator.train(input_fn=input_fn, max_steps=1)
predicted_values = estimator.evaluate(input_fn=input_fn, steps=1)["mean"]
# Throw out the first value so we don't test the prior
self.assertAllEqual(values[1:], predicted_values[1:])
def test_loop_unrolling(self):
"""Tests running/restoring from a checkpoint with static unrolling."""
model = TimeDependentStateSpaceModel(
# Unroll during training, but not evaluation
static_unrolling_window_size_threshold=2)
estimator = estimators.StateSpaceRegressor(model=model)
times = numpy.arange(100)
values = numpy.arange(100)
dataset = {
feature_keys.TrainEvalFeatures.TIMES: times,
feature_keys.TrainEvalFeatures.VALUES: values
}
train_input_fn = input_pipeline.RandomWindowInputFn(
input_pipeline.NumpyReader(dataset), batch_size=16, window_size=2)
eval_input_fn = input_pipeline.WholeDatasetInputFn(
input_pipeline.NumpyReader(dataset))
estimator.train(input_fn=train_input_fn, max_steps=1)
estimator.evaluate(input_fn=eval_input_fn, steps=1)
def test_savedmodel_state_override(self):
random_model = RandomStateSpaceModel(
state_dimension=5,
state_noise_dimension=4,
configuration=state_space_model.StateSpaceModelConfiguration(
exogenous_feature_columns=[
layers.real_valued_column("exogenous")
],
dtype=dtypes.float64,
num_features=1))
estimator = estimators.StateSpaceRegressor(
model=random_model,
optimizer=gradient_descent.GradientDescentOptimizer(0.1))
combined_input_fn = input_pipeline.WholeDatasetInputFn(
input_pipeline.NumpyReader({
feature_keys.FilteringFeatures.TIMES: [1, 2, 3, 4],
feature_keys.FilteringFeatures.VALUES: [1., 2., 3., 4.],
"exogenous": [-1., -2., -3., -4.]
}))
estimator.train(combined_input_fn, steps=1)
export_location = estimator.export_savedmodel(
self.get_temp_dir(),
estimator.build_raw_serving_input_receiver_fn(
exogenous_features={
"exogenous": numpy.zeros((0, 0), dtype=numpy.float32)
}))
with ops.Graph().as_default() as graph:
random_model.initialize_graph()
with self.test_session(graph=graph) as session:
variables.global_variables_initializer().run()
evaled_start_state = session.run(
random_model.get_start_state())
evaled_start_state = [
state_element[None, ...] for state_element in evaled_start_state
]
with ops.Graph().as_default() as graph:
with self.test_session(graph=graph) as session:
signatures = loader.load(session, [tag_constants.SERVING],
export_location)
first_split_filtering = saved_model_utils.filter_continuation(
continue_from={
feature_keys.FilteringResults.STATE_TUPLE:
evaled_start_state
},
signatures=signatures,
session=session,
features={
feature_keys.FilteringFeatures.TIMES: [1, 2],
feature_keys.FilteringFeatures.VALUES: [1., 2.],
"exogenous": [-1., -2.]
})
second_split_filtering = saved_model_utils.filter_continuation(
continue_from=first_split_filtering,
signatures=signatures,
session=session,
features={
feature_keys.FilteringFeatures.TIMES: [3, 4],
feature_keys.FilteringFeatures.VALUES: [3., 4.],
"exogenous": [-3., -4.]
})
combined_filtering = saved_model_utils.filter_continuation(
continue_from={
feature_keys.FilteringResults.STATE_TUPLE:
evaled_start_state
},
signatures=signatures,
session=session,
features={
feature_keys.FilteringFeatures.TIMES: [1, 2, 3, 4],
feature_keys.FilteringFeatures.VALUES:
[1., 2., 3., 4.],
"exogenous": [-1., -2., -3., -4.]
})
split_predict = saved_model_utils.predict_continuation(
continue_from=second_split_filtering,
signatures=signatures,
session=session,
steps=1,
exogenous_features={"exogenous": [[-5.]]})
combined_predict = saved_model_utils.predict_continuation(
continue_from=combined_filtering,
signatures=signatures,
session=session,
steps=1,
exogenous_features={"exogenous": [[-5.]]})
for state_key, combined_state_value in combined_filtering.items():
if state_key == feature_keys.FilteringResults.TIMES:
continue
self.assertAllClose(combined_state_value,
second_split_filtering[state_key])
for prediction_key, combined_value in combined_predict.items():
self.assertAllClose(combined_value, split_predict[prediction_key])
