def _fit_restore_fit_test_template(self, estimator_fn, dtype):
"""Tests restoring previously fit models."""
model_dir = tempfile.mkdtemp(dir=self.get_temp_dir())
exogenous_feature_columns = (
feature_column.numeric_column("exogenous"),
)
first_estimator = estimator_fn(model_dir, exogenous_feature_columns)
times = numpy.arange(20, dtype=numpy.int64)
values = numpy.arange(20, dtype=dtype.as_numpy_dtype)
exogenous = numpy.arange(20, dtype=dtype.as_numpy_dtype)
features = {
feature_keys.TrainEvalFeatures.TIMES: times,
feature_keys.TrainEvalFeatures.VALUES: values,
"exogenous": exogenous
}
train_input_fn = input_pipeline.RandomWindowInputFn(
input_pipeline.NumpyReader(features), shuffle_seed=2, num_threads=1,
batch_size=16, window_size=16)
eval_input_fn = input_pipeline.RandomWindowInputFn(
input_pipeline.NumpyReader(features), shuffle_seed=3, num_threads=1,
batch_size=16, window_size=16)
first_estimator.train(input_fn=train_input_fn, steps=1)
first_evaluation = first_estimator.evaluate(
input_fn=eval_input_fn, steps=1)
first_loss_before_fit = first_evaluation["loss"]
self.assertAllEqual(first_loss_before_fit, first_evaluation["average_loss"])
self.assertAllEqual([], first_loss_before_fit.shape)
first_estimator.train(input_fn=train_input_fn, steps=1)
first_loss_after_fit = first_estimator.evaluate(
input_fn=eval_input_fn, steps=1)["loss"]
self.assertAllEqual([], first_loss_after_fit.shape)
second_estimator = estimator_fn(model_dir, exogenous_feature_columns)
second_estimator.train(input_fn=train_input_fn, steps=1)
whole_dataset_input_fn = input_pipeline.WholeDatasetInputFn(
input_pipeline.NumpyReader(features))
whole_dataset_evaluation = second_estimator.evaluate(
input_fn=whole_dataset_input_fn, steps=1)
exogenous_values_ten_steps = {
"exogenous": numpy.arange(
10, dtype=dtype.as_numpy_dtype)[None, :, None]
}
predict_input_fn = input_pipeline.predict_continuation_input_fn(
evaluation=whole_dataset_evaluation,
exogenous_features=exogenous_values_ten_steps,
steps=10)
# Also tests that limit_epochs in predict_continuation_input_fn prevents
# infinite iteration
(estimator_predictions,
) = list(second_estimator.predict(input_fn=predict_input_fn))
self.assertAllEqual([10, 1], estimator_predictions["mean"].shape)
input_receiver_fn = first_estimator.build_raw_serving_input_receiver_fn()
export_location = first_estimator.export_savedmodel(self.get_temp_dir(),
input_receiver_fn)
with ops.Graph().as_default():
with session.Session() as sess:
signatures = loader.load(sess, [tag_constants.SERVING], export_location)
# Test that prediction and filtering can continue from evaluation output
saved_prediction = saved_model_utils.predict_continuation(
continue_from=whole_dataset_evaluation,
steps=10,
exogenous_features=exogenous_values_ten_steps,
signatures=signatures,
session=sess)
# Saved model predictions should be the same as Estimator predictions
# starting from the same evaluation.
for prediction_key, prediction_value in estimator_predictions.items():
self.assertAllClose(prediction_value,
numpy.squeeze(
saved_prediction[prediction_key], axis=0))
first_filtering = saved_model_utils.filter_continuation(
continue_from=whole_dataset_evaluation,
features={
feature_keys.FilteringFeatures.TIMES: times[None, -1] + 2,
feature_keys.FilteringFeatures.VALUES: values[None, -1] + 2.,
"exogenous": values[None, -1, None] + 12.
},
signatures=signatures,
session=sess)
# Test that prediction and filtering can continue from filtering output
second_saved_prediction = saved_model_utils.predict_continuation(
continue_from=first_filtering,
steps=1,
exogenous_features={
"exogenous": numpy.arange(
1, dtype=dtype.as_numpy_dtype)[None, :, None]
},
signatures=signatures,
session=sess)
self.assertEqual(
times[-1] + 3,
numpy.squeeze(
second_saved_prediction[feature_keys.PredictionResults.TIMES]))
saved_model_utils.filter_continuation(
continue_from=first_filtering,
features={
feature_keys.FilteringFeatures.TIMES: times[-1] + 3,
feature_keys.FilteringFeatures.VALUES: values[-1] + 3.,
"exogenous": values[-1, None] + 13.
},
signatures=signatures,
session=sess)
# Test cold starting
six.assertCountEqual(
self,
[feature_keys.FilteringFeatures.TIMES,
feature_keys.FilteringFeatures.VALUES,
"exogenous"],
signatures.signature_def[
feature_keys.SavedModelLabels.COLD_START_FILTER].inputs.keys())
batch_numpy_times = numpy.tile(
numpy.arange(30, dtype=numpy.int64)[None, :], (10, 1))
batch_numpy_values = numpy.ones([10, 30, 1])
state = saved_model_utils.cold_start_filter(
signatures=signatures,
session=sess,
features={
feature_keys.FilteringFeatures.TIMES: batch_numpy_times,
feature_keys.FilteringFeatures.VALUES: batch_numpy_values,
"exogenous": 10. + batch_numpy_values
}
)
predict_times = numpy.tile(
numpy.arange(30, 45, dtype=numpy.int64)[None, :], (10, 1))
predictions = saved_model_utils.predict_continuation(
continue_from=state,
times=predict_times,
exogenous_features={
"exogenous": numpy.tile(numpy.arange(
15, dtype=dtype.as_numpy_dtype), (10,))[None, :, None]
},
signatures=signatures,
session=sess)
self.assertAllEqual([10, 15, 1], predictions["mean"].shape)
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())
with ops.Graph().as_default() as graph:
random_model.initialize_graph()
with self.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.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])
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])
def _fit_restore_fit_test_template(self, estimator_fn, dtype):
"""Tests restoring previously fit models."""
model_dir = tempfile.mkdtemp(dir=self.get_temp_dir())
exogenous_feature_columns = (
feature_column.numeric_column("exogenous"), )
first_estimator = estimator_fn(model_dir, exogenous_feature_columns)
times = numpy.arange(20, dtype=numpy.int64)
values = numpy.arange(20, dtype=dtype.as_numpy_dtype)
exogenous = numpy.arange(20, dtype=dtype.as_numpy_dtype)
features = {
feature_keys.TrainEvalFeatures.TIMES: times,
feature_keys.TrainEvalFeatures.VALUES: values,
"exogenous": exogenous
}
train_input_fn = input_pipeline.RandomWindowInputFn(
input_pipeline.NumpyReader(features),
shuffle_seed=2,
num_threads=1,
batch_size=16,
window_size=16)
eval_input_fn = input_pipeline.RandomWindowInputFn(
input_pipeline.NumpyReader(features),
shuffle_seed=3,
num_threads=1,
batch_size=16,
window_size=16)
first_estimator.train(input_fn=train_input_fn, steps=5)
first_loss_before_fit = first_estimator.evaluate(
input_fn=eval_input_fn, steps=1)["loss"]
first_estimator.train(input_fn=train_input_fn, steps=50)
first_loss_after_fit = first_estimator.evaluate(input_fn=eval_input_fn,
steps=1)["loss"]
self.assertLess(first_loss_after_fit, first_loss_before_fit)
second_estimator = estimator_fn(model_dir, exogenous_feature_columns)
second_estimator.train(input_fn=train_input_fn, steps=2)
whole_dataset_input_fn = input_pipeline.WholeDatasetInputFn(
input_pipeline.NumpyReader(features))
whole_dataset_evaluation = second_estimator.evaluate(
input_fn=whole_dataset_input_fn, steps=1)
exogenous_values_ten_steps = {
"exogenous":
numpy.arange(10, dtype=dtype.as_numpy_dtype)[None, :, None]
}
predict_input_fn = input_pipeline.predict_continuation_input_fn(
evaluation=whole_dataset_evaluation,
exogenous_features=exogenous_values_ten_steps,
steps=10)
# Also tests that limit_epochs in predict_continuation_input_fn prevents
# infinite iteration
(estimator_predictions, ) = list(
second_estimator.predict(input_fn=predict_input_fn))
self.assertAllEqual([10, 1], estimator_predictions["mean"].shape)
input_receiver_fn = first_estimator.build_raw_serving_input_receiver_fn(
)
export_location = first_estimator.export_savedmodel(
self.get_temp_dir(), input_receiver_fn)
with ops.Graph().as_default():
with session.Session() as sess:
signatures = loader.load(sess, [tag_constants.SERVING],
export_location)
# Test that prediction and filtering can continue from evaluation output
saved_prediction = saved_model_utils.predict_continuation(
continue_from=whole_dataset_evaluation,
steps=10,
exogenous_features=exogenous_values_ten_steps,
signatures=signatures,
session=sess)
# Saved model predictions should be the same as Estimator predictions
# starting from the same evaluation.
for prediction_key, prediction_value in estimator_predictions.items(
):
self.assertAllClose(
prediction_value,
numpy.squeeze(saved_prediction[prediction_key],
axis=0))
first_filtering = saved_model_utils.filter_continuation(
continue_from=whole_dataset_evaluation,
features={
feature_keys.FilteringFeatures.TIMES:
times[None, -1] + 2,
feature_keys.FilteringFeatures.VALUES:
values[None, -1] + 2.,
"exogenous": values[None, -1, None] + 12.
},
signatures=signatures,
session=sess)
# Test that prediction and filtering can continue from filtering output
second_saved_prediction = saved_model_utils.predict_continuation(
continue_from=first_filtering,
steps=1,
exogenous_features={
"exogenous":
numpy.arange(1, dtype=dtype.as_numpy_dtype)[None, :,
None]
},
signatures=signatures,
session=sess)
self.assertEqual(
times[-1] + 3,
numpy.squeeze(second_saved_prediction[
feature_keys.PredictionResults.TIMES]))
saved_model_utils.filter_continuation(
continue_from=first_filtering,
features={
feature_keys.FilteringFeatures.TIMES: times[-1] + 3,
feature_keys.FilteringFeatures.VALUES: values[-1] + 3.,
"exogenous": values[-1, None] + 13.
},
signatures=signatures,
session=sess)
# Test cold starting
six.assertCountEqual(
self, [
feature_keys.FilteringFeatures.TIMES,
feature_keys.FilteringFeatures.VALUES, "exogenous"
],
signatures.signature_def[feature_keys.SavedModelLabels.
COLD_START_FILTER].inputs.keys())
batch_numpy_times = numpy.tile(
numpy.arange(30, dtype=numpy.int64)[None, :], (10, 1))
batch_numpy_values = numpy.ones([10, 30, 1])
state = saved_model_utils.cold_start_filter(
signatures=signatures,
session=sess,
features={
feature_keys.FilteringFeatures.TIMES:
batch_numpy_times,
feature_keys.FilteringFeatures.VALUES:
batch_numpy_values,
"exogenous": 10. + batch_numpy_values
})
predict_times = numpy.tile(
numpy.arange(30, 45, dtype=numpy.int64)[None, :], (10, 1))
predictions = saved_model_utils.predict_continuation(
continue_from=state,
times=predict_times,
exogenous_features={
"exogenous":
numpy.tile(
numpy.arange(15, dtype=dtype.as_numpy_dtype),
(10, ))[None, :, None]
},
signatures=signatures,
session=sess)
self.assertAllEqual([10, 15, 1], predictions["mean"].shape)
def _fit_restore_fit_test_template(self, estimator_fn, dtype):
"""Tests restoring previously fit models."""
model_dir = tempfile.mkdtemp(dir=self.get_temp_dir())
first_estimator = estimator_fn(model_dir)
times = numpy.arange(20, dtype=numpy.int64)
values = numpy.arange(20, dtype=dtype.as_numpy_dtype)
features = {
feature_keys.TrainEvalFeatures.TIMES: times,
feature_keys.TrainEvalFeatures.VALUES: values
}
train_input_fn = input_pipeline.RandomWindowInputFn(
input_pipeline.NumpyReader(features), shuffle_seed=2, num_threads=1,
batch_size=16, window_size=16)
eval_input_fn = input_pipeline.RandomWindowInputFn(
input_pipeline.NumpyReader(features), shuffle_seed=3, num_threads=1,
batch_size=16, window_size=16)
first_estimator.train(input_fn=train_input_fn, steps=5)
first_loss_before_fit = first_estimator.evaluate(
input_fn=eval_input_fn, steps=1)["loss"]
first_estimator.train(input_fn=train_input_fn, steps=50)
first_loss_after_fit = first_estimator.evaluate(
input_fn=eval_input_fn, steps=1)["loss"]
self.assertLess(first_loss_after_fit, first_loss_before_fit)
second_estimator = estimator_fn(model_dir)
second_estimator.train(input_fn=train_input_fn, steps=2)
whole_dataset_input_fn = input_pipeline.WholeDatasetInputFn(
input_pipeline.NumpyReader(features))
whole_dataset_evaluation = second_estimator.evaluate(
input_fn=whole_dataset_input_fn, steps=1)
predict_input_fn = input_pipeline.predict_continuation_input_fn(
evaluation=whole_dataset_evaluation,
steps=10)
# Also tests that limit_epochs in predict_continuation_input_fn prevents
# infinite iteration
(estimator_predictions,
) = list(second_estimator.predict(input_fn=predict_input_fn))
self.assertAllEqual([10, 1], estimator_predictions["mean"].shape)
input_receiver_fn = first_estimator.build_raw_serving_input_receiver_fn()
export_location = first_estimator.export_savedmodel(self.get_temp_dir(),
input_receiver_fn)
with ops.Graph().as_default():
with session.Session() as sess:
signatures = loader.load(sess, [tag_constants.SERVING], export_location)
# Test that prediction and filtering can continue from evaluation output
saved_prediction = saved_model_utils.predict_continuation(
continue_from=whole_dataset_evaluation,
steps=10,
signatures=signatures,
session=sess)
# Saved model predictions should be the same as Estimator predictions
# starting from the same evaluation.
for prediction_key, prediction_value in estimator_predictions.items():
self.assertAllClose(prediction_value,
numpy.squeeze(
saved_prediction[prediction_key], axis=0))
first_filtering = saved_model_utils.filter_continuation(
continue_from=whole_dataset_evaluation,
features={
feature_keys.FilteringFeatures.TIMES: times[None, -1] + 2,
feature_keys.FilteringFeatures.VALUES: values[None, -1] + 2.
},
signatures=signatures,
session=sess)
# Test that prediction and filtering can continue from filtering output
second_saved_prediction = saved_model_utils.predict_continuation(
continue_from=first_filtering,
steps=1,
signatures=signatures,
session=sess)
self.assertEqual(
times[-1] + 3,
numpy.squeeze(
second_saved_prediction[feature_keys.PredictionResults.TIMES]))
saved_model_utils.filter_continuation(
continue_from=first_filtering,
features={
feature_keys.FilteringFeatures.TIMES: times[-1] + 3,
feature_keys.FilteringFeatures.VALUES: values[-1] + 3.
},
signatures=signatures,
session=sess)