timesead.data.smd_dataset
=========================

.. py:module:: timesead.data.smd_dataset


Attributes
----------

.. autoapisummary::

   timesead.data.smd_dataset.FILENAMES
   timesead.data.smd_dataset.TRAIN_LENS
   timesead.data.smd_dataset.TEST_LENS


Classes
-------

.. autoapisummary::

   timesead.data.smd_dataset.SMDDataset


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

.. py:data:: FILENAMES
   :value: ['machine-1-1.txt', 'machine-1-2.txt', 'machine-1-3.txt', 'machine-1-4.txt', 'machine-1-5.txt',...


.. py:data:: TRAIN_LENS
   :value: [28479, 23694, 23702, 23706, 23705, 23688, 23697, 23698, 23693, 23699, 23688, 23689, 23688,...


.. py:data:: TEST_LENS
   :value: [28479, 23694, 23703, 23707, 23706, 23689, 23697, 23699, 23694, 23700, 23689, 23689, 23689,...


.. py:class:: SMDDataset(server_id: int, path: str = os.path.join(DATA_DIRECTORY, 'smd'), training: bool = True, standardize: Union[bool, Callable] = True, download: bool = True, preprocess: bool = True)

   Bases: :py:obj:`timesead.data.dataset.BaseTSDataset`


   Implementation of the Server Machine Dataset [Su2019]_.
   The data consists of traces from 28 different servers recorded over several weeks. We consider each trace to be a
   separate dataset.

   .. note::
       Automatically downloading the dataset currently requires that you have `git` installed on your system!

   .. [Su2019] Y. Su, Y. Zhao, C. Niu, R. Liu, W. Sun, D. Pei.
       Robust anomaly detection for multivariate time series through stochastic recurrent neural network.
       In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining,
       2019 Jul 25 (pp. 2828-2837).

   :param path: Folder from which to load the dataset.
   :param server_id: Data from which machine to load. Must be in [0, ..., 27].
   :param training: Whether to load the training or the test set.
   :param standardize: Can be either a bool that decides whether to apply the dataset-dependent default
       standardization or a function with signature (dataframe, stats) -> dataframe, where stats is a dictionary of
       common statistics on the training dataset (i.e., mean, std, median, etc. for each feature)
   :param download: Whether to download the dataset if it doesn't exist.
   :param preprocess: Whether to setup the dataset for experiments.


   .. py:attribute:: GITHUB_LINK
      :value: 'https://github.com/NetManAIOps/OmniAnomaly.git'



   .. py:attribute:: server_id


   .. py:attribute:: path


   .. py:attribute:: processed_dir


   .. py:attribute:: training
      :value: True



   .. py:attribute:: standardize
      :value: True



   .. py:attribute:: inputs
      :value: None



   .. py:attribute:: targets
      :value: None



   .. py:method:: load_data() -> Tuple[numpy.ndarray, numpy.ndarray]


   .. py:method:: __getitem__(item: int) -> Tuple[Tuple[torch.Tensor], Tuple[torch.Tensor]]


   .. py:method:: __len__() -> Optional[int]


   .. py:property:: seq_len
      :type: Union[int, List[int]]



   .. py:property:: num_features
      :type: int



   .. py:method:: get_default_pipeline() -> Dict[str, Dict[str, Any]]
      :staticmethod:



   .. py:method:: get_feature_names()
      :staticmethod:



   .. py:method:: download()