def test_exogenous_input(self): """Test that no errors are raised when using exogenous features.""" dtype = dtypes.float64 times = [1, 2, 3, 4, 5, 6] values = [[0.01], [5.10], [5.21], [0.30], [5.41], [0.50]] feature_a = [["off"], ["on"], ["on"], ["off"], ["on"], ["off"]] sparse_column_a = feature_column.sparse_column_with_keys( column_name="feature_a", keys=["on", "off"]) one_hot_a = layers.one_hot_column(sparse_id_column=sparse_column_a) regressor = estimators.StructuralEnsembleRegressor( periodicities=[], num_features=1, moving_average_order=0, exogenous_feature_columns=[one_hot_a], dtype=dtype) features = {TrainEvalFeatures.TIMES: times, TrainEvalFeatures.VALUES: values, "feature_a": feature_a} train_input_fn = input_pipeline.RandomWindowInputFn( input_pipeline.NumpyReader(features), window_size=6, batch_size=1) regressor.train(input_fn=train_input_fn, steps=1) eval_input_fn = input_pipeline.WholeDatasetInputFn( input_pipeline.NumpyReader(features)) evaluation = regressor.evaluate(input_fn=eval_input_fn, steps=1) predict_input_fn = input_pipeline.predict_continuation_input_fn( evaluation, times=[[7, 8, 9]], exogenous_features={"feature_a": [[["on"], ["off"], ["on"]]]}) regressor.predict(input_fn=predict_input_fn)
def test_no_periodicity(self): """Test that no errors are raised when periodicites is None.""" dtype = dtypes.float64 times = [1, 2, 3, 4, 5, 6] values = [[0.01], [5.10], [5.21], [0.30], [5.41], [0.50]] regressor = estimators.StructuralEnsembleRegressor( periodicities=None, num_features=1, moving_average_order=0, dtype=dtype) features = {TrainEvalFeatures.TIMES: times, TrainEvalFeatures.VALUES: values} train_input_fn = input_pipeline.RandomWindowInputFn( input_pipeline.NumpyReader(features), window_size=6, batch_size=1) regressor.train(input_fn=train_input_fn, steps=1) eval_input_fn = input_pipeline.WholeDatasetInputFn( input_pipeline.NumpyReader(features)) evaluation = regressor.evaluate(input_fn=eval_input_fn, steps=1) predict_input_fn = input_pipeline.predict_continuation_input_fn( evaluation, times=[[7, 8, 9]]) regressor.predict(input_fn=predict_input_fn)
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 _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)