.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/gait_sequences/_05_tvs_evaluation_no_exc.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        :ref:`Go to the end <sphx_glr_download_auto_examples_gait_sequences__05_tvs_evaluation_no_exc.py>`
        to download the full example code

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_auto_examples_gait_sequences__05_tvs_evaluation_no_exc.py:


GSD TVS Evaluation
==================
This script shows the actual performance evaluation that is run to benchmark the GSD algorithms on the TVS dataset.
As this is run on the TVS dataset and has a long runtime, this example needs to be downloaded and run locally.

.. GENERATED FROM PYTHON SOURCE LINES 7-30

.. code-block:: default


    import os
    from pathlib import Path

    from joblib import Memory
    from mobgap import PACKAGE_ROOT
    from mobgap.data import TVSFreeLivingDataset

    if "MOBGAP_TVS_DATASET_PATH" not in os.environ:
        raise ValueError(
            "Please set the environmental variable MOBGAP_TVS_DATASET_PATH to the path of the TVS dataset."
        )

    dataset_path = Path(os.getenv("MOBGAP_TVS_DATASET_PATH"))
    n_jobs = os.environ.get("MOBGAP_N_JOBS", 1)

    free_living_data = TVSFreeLivingDataset(
        dataset_path,
        reference_system="INDIP",
        memory=Memory(PACKAGE_ROOT.parent / ".cache"),
        missing_reference_error_type="skip",
    ).get_subset(recording="Recording4")


.. GENERATED FROM PYTHON SOURCE LINES 31-32

Run the non-CV evaluation for all implemented algorithms

.. GENERATED FROM PYTHON SOURCE LINES 32-49

.. code-block:: default

    from mobgap.gait_sequences import GsdAdaptiveIonescu, GsdIluz, GsdIonescu
    from mobgap.gait_sequences.pipeline import (
        GsdEmulationPipeline,
        GsdEvaluation,
        gsd_evaluation_scorer,
    )

    results = {}
    for algo in (GsdIluz(), GsdIonescu(), GsdAdaptiveIonescu()):
        print(f"Running evaluation for {algo.__class__.__name__}")
        pipe = GsdEmulationPipeline(algo)
        eval_pipe = GsdEvaluation(
            free_living_data,
            scoring=gsd_evaluation_scorer,
            validate_paras={"n_jobs": n_jobs},
        ).run(pipe)
        results[algo.__class__.__name__] = eval_pipe.results_


.. rst-class:: sphx-glr-timing

   **Total running time of the script:** (0 minutes 0.000 seconds)

**Estimated memory usage:**  0 MB


.. _sphx_glr_download_auto_examples_gait_sequences__05_tvs_evaluation_no_exc.py:

.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-example




    .. container:: sphx-glr-download sphx-glr-download-python

      :download:`Download Python source code: _05_tvs_evaluation_no_exc.py <_05_tvs_evaluation_no_exc.py>`

    .. container:: sphx-glr-download sphx-glr-download-jupyter

      :download:`Download Jupyter notebook: _05_tvs_evaluation_no_exc.ipynb <_05_tvs_evaluation_no_exc.ipynb>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_