timesead.data.transforms.artificial_anomalies
=============================================

.. py:module:: timesead.data.transforms.artificial_anomalies


Classes
-------

.. autoapisummary::

   timesead.data.transforms.artificial_anomalies.InjectArtificialAnomaliesTransform
   timesead.data.transforms.artificial_anomalies.InjectIndependentArtificialAnomaliesTransform
   timesead.data.transforms.artificial_anomalies.InjectWindowsArtificialAnomaliesTransform


Module Contents
---------------

.. py:class:: InjectArtificialAnomaliesTransform(parent: timesead.data.transforms.transform_base.Transform, n: int, min_length: int = 1, max_length: int = 1)

   Bases: :py:obj:`timesead.data.transforms.transform_base.Transform`


   This Transform injects anomalies into the dataset.

   It expects the get_datapoint method of its parent to return a tuple of tuples of length 1.

   :param parent: Another :class:`~timesead.data.transforms.Transform` which is used as the data source for this
       :class:`~timesead.data.transforms.Transform`.
   :param n: Number of anomalies to insert.
   :param min_length: Minimum length of anomalies.
   :param max_length: Maximum length of anomalies.


.. py:class:: InjectIndependentArtificialAnomaliesTransform(parent: timesead.data.transforms.transform_base.Transform, anomaly_fn: Callable, n: int, min_length: int = 1, max_length: int = 1)

   Bases: :py:obj:`InjectArtificialAnomaliesTransform`


   Transform that injects anomalies, that only depend on the anomaly interval.

   :param parent: Another :class:`~timesead.data.transforms.Transform` which is used as the data source for this
       :class:`~timesead.data.transforms.Transform`.
   :param anomaly_fn: Callable that adds an anomaly to an interval and returns a :class:`torch.Tensor` of the same
       size as its input.
   :param n: Number of anomalies to insert.
   :param min_length: Minimum length of anomalies.
   :param max_length: Maximum length of anomalies.


   .. py:attribute:: anomaly


.. py:class:: InjectWindowsArtificialAnomaliesTransform(parent: timesead.data.transforms.transform_base.Transform, mask_fn: Callable, n: int, min_length: int = 1, max_length: int = 1)

   Bases: :py:obj:`InjectArtificialAnomaliesTransform`


   :class:`~timesead.data.transforms.Transform` that inject windows from somewhere else in the dataset as anomalies.

   :param parent: Another :class:`~timesead.data.transforms.Transform` which is used as the data source for this
       :class:`~timesead.data.transforms.Transform`.
   :param mask_fn: Callable that computes a mask to the features of an interval.
   :param n: Number of anomalies to insert.
   :param min_length: Minimum length of anomalies.
   :param max_length: Maximum length of anomalies.


   .. py:attribute:: mask