added initial artifical const dataset

pts/dataset/__init__.py

@@ -11,3 +11,4 @@ from .sampler import (
 from .process import ProcessStartField, ProcessDataEntry
 from .utils import to_pandas
 from .stat import ScaleHistogram, calculate_dataset_statistics
+from .artificial import constant_dataset

pts/dataset/artificial.py

@@ -0,0 +1,70 @@
+from typing import Callable, List, NamedTuple, Optional, Tuple, Union
+
+from .common import MetaData, CategoricalFeatureInfo, BasicFeatureInfo, FieldName, Dataset
+from .list_dataset import ListDataset
+from .stat import DatasetStatistics, calculate_dataset_statistics
+
+class DatasetInfo(NamedTuple):
+    """
+    Information stored on a dataset. When downloading from the repository, the
+    dataset repository checks that the obtained version matches the one
+    declared in dataset_info/dataset_name.json.
+    """
+
+    name: str
+    metadata: MetaData
+    prediction_length: int
+    train_statistics: DatasetStatistics
+    test_statistics: DatasetStatistics
+
+
+def constant_dataset() -> Tuple[DatasetInfo, Dataset, Dataset]:
+    metadata = MetaData(
+        freq="1H",
+        feat_static_cat=[
+            CategoricalFeatureInfo(
+                name="feat_static_cat_000", cardinality="10"
+            )
+        ],
+        feat_static_real=[BasicFeatureInfo(name="feat_static_real_000")],
+    )
+
+    start_date = "2000-01-01 00:00:00"
+
+    train_ds = ListDataset(
+        data_iter=[
+            {
+                FieldName.ITEM_ID: str(i),
+                FieldName.START: start_date,
+                FieldName.TARGET: [float(i)] * 24,
+                FieldName.FEAT_STATIC_CAT: [i],
+                FieldName.FEAT_STATIC_REAL: [float(i)],
+            }
+            for i in range(10)
+        ],
+        freq=metadata.freq,
+    )
+
+    test_ds = ListDataset(
+        data_iter=[
+            {
+                FieldName.ITEM_ID: str(i),
+                FieldName.START: start_date,
+                FieldName.TARGET: [float(i)] * 30,
+                FieldName.FEAT_STATIC_CAT: [i],
+                FieldName.FEAT_STATIC_REAL: [float(i)],
+            }
+            for i in range(10)
+        ],
+        freq=metadata.freq,
+    )
+
+    info = DatasetInfo(
+        name="constant_dataset",
+        metadata=metadata,
+        prediction_length=2,
+        train_statistics=calculate_dataset_statistics(train_ds),
+        test_statistics=calculate_dataset_statistics(test_ds),
+    )
+
+    return info, train_ds, test_ds

pts/dataset/common.py

@@ -1,5 +1,5 @@
 from abc import ABC, abstractmethod
-from typing import Any, Dict, Iterable, NamedTuple, Sized
+from typing import Any, Dict, Iterable, NamedTuple, Sized, List, Optional
 
 DataEntry = Dict[str, Any]
 
@@ -42,3 +42,21 @@ class Dataset(Sized, Iterable[DataEntry], ABC):
     @abstractmethod
     def __len__(self):
         pass
+
+class CategoricalFeatureInfo():
+    name: str
+    cardinality: str
+
+class BasicFeatureInfo():
+    name: str
+
+class MetaData():
+    freq: str = None
+    target: Optional[BasicFeatureInfo] = None
+
+    feat_static_cat: List[CategoricalFeatureInfo] = []
+    feat_static_real: List[BasicFeatureInfo] = []
+    feat_dynamic_real: List[BasicFeatureInfo] = []
+    feat_dynamic_cat: List[CategoricalFeatureInfo] = []
+
+    prediction_length: Optional[int] = None

pts/model/__init__.py

@@ -2,3 +2,4 @@ from .estimator import Estimator, PTSEstimator
 from .forecast import Forecast
 from .predictor import Predictor
 from .quantile import Quantile
+from .utils import get_module_forward_input_names

test/model/deepar/test_auxillary_outputs.py

@@ -0,0 +1,69 @@
+# Copyright 2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License").
+# You may not use this file except in compliance with the License.
+# A copy of the License is located at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# or in the "license" file accompanying this file. This file is distributed
+# on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either
+# express or implied. See the License for the specific language governing
+# permissions and limitations under the License.
+
+from itertools import islice
+
+import torch
+
+from pts.modules import StudentTOutput
+from pts.dataset import constant_dataset, TrainDataLoader
+from pts.model.deepar import DeepAREstimator
+from pts.model import get_module_forward_input_names
+from pts import Trainer
+
+
+ds_info, train_ds, test_ds = constant_dataset()
+freq = ds_info.metadata.freq
+prediction_length = ds_info.prediction_length
+
+
+def test_distribution():
+    """
+    Makes sure additional tensors can be accessed and have expected shapes
+    """
+    prediction_length = ds_info.prediction_length
+    estimator = DeepAREstimator(
+        freq=freq,
+        prediction_length=prediction_length,
+        trainer=Trainer(epochs=1, num_batches_per_epoch=1),
+        distr_output=StudentTOutput(),
+    )
+
+    train_output = estimator.train_model(train_ds)
+
+    # todo adapt loader to anomaly detection use-case
+    batch_size = 2
+    num_samples = 3
+
+    training_data_loader = TrainDataLoader(
+        dataset=train_ds,
+        transform=train_output.transformation,
+        batch_size=batch_size,
+        num_batches_per_epoch=estimator.trainer.num_batches_per_epoch,
+        device=torch.device("cpu")
+    )
+
+    seq_len = 2 * ds_info.prediction_length
+
+    for data_entry in islice(training_data_loader, 1):
+        input_names = get_module_forward_input_names(train_output.trained_net)
+
+        distr = train_output.trained_net.distribution(
+            *[data_entry[k] for k in input_names]
+        )
+
+        assert distr.sample(num_samples).shape == (
+            num_samples,
+            batch_size,
+            seq_len,
+        )