.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/pipeline/_02_step_by_step_mobilised_pipeline.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_pipeline__02_step_by_step_mobilised_pipeline.py>`
        to download the full example code.

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

.. _sphx_glr_auto_examples_pipeline__02_step_by_step_mobilised_pipeline.py:


.. _mobilised_pipeline_step_by_step:

The Mobilise-D pipeline: Step-by-Step Breakdown
===============================================

This example shows how to build a full gait analysis pipeline using the mobgap package.
Note, that we provide pre-built pipelines for common use-cases.
Checkout the examples for those, if you want to understand how to use them.

This example is meant to provide a better understanding of the individual steps and should serve as a blueprint to
build completely custom pipelines.
We are following the pipeline explained in [1]_ (Fig. 7) step by step.

For more information about the individual steps, please refer to the respective examples for the algorithms.

.. [1] Kirk, C., Küderle, A., Micó-Amigo, M.E. et al. Mobilise-D insights to estimate real-world walking speed in
       multiple conditions with a wearable device. Sci Rep 14, 1754 (2024).
       https://doi.org/10.1038/s41598-024-51766-5

.. GENERATED FROM PYTHON SOURCE LINES 24-33

Load example data
-----------------
We load example data from the lab dataset, and we will use a single long-trail from an "MS" participant for this
example.

Note, that we directly convert it into the body frame, as bascially all algorithms require the body frame data
(and all others support it).
We can do that, because we know that the data is already well aligned with the sensor frame conventions.
If this would not be the case, the data would need to be rotated/algigned before running through the pipeline.

.. GENERATED FROM PYTHON SOURCE LINES 33-46

.. code-block:: Python

    import pandas as pd
    from mobgap.data import LabExampleDataset
    from mobgap.utils.conversions import to_body_frame
    from mobgap.utils.interpolation import naive_sec_paras_to_regions

    lab_example_data = LabExampleDataset(reference_system="INDIP")
    long_trial = lab_example_data.get_subset(
        cohort="MS", participant_id="001", test="Test11", trial="Trial1"
    )
    imu_data = to_body_frame(long_trial.data_ss)
    sampling_rate_hz = long_trial.sampling_rate_hz
    participant_metadata = long_trial.participant_metadata








.. GENERATED FROM PYTHON SOURCE LINES 47-49

Step 1: Gait Sequence Detection
-------------------------------

.. GENERATED FROM PYTHON SOURCE LINES 49-57

.. code-block:: Python

    from mobgap.gait_sequences import GsdIluz

    gsd = GsdIluz()
    gsd.detect(imu_data, sampling_rate_hz=sampling_rate_hz)

    gait_sequences = gsd.gs_list_
    gait_sequences






.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th>start</th>
          <th>end</th>
        </tr>
        <tr>
          <th>gs_id</th>
          <th></th>
          <th></th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>0</th>
          <td>900</td>
          <td>2101</td>
        </tr>
        <tr>
          <th>1</th>
          <td>4650</td>
          <td>6151</td>
        </tr>
        <tr>
          <th>2</th>
          <td>9600</td>
          <td>10801</td>
        </tr>
        <tr>
          <th>3</th>
          <td>11250</td>
          <td>12151</td>
        </tr>
        <tr>
          <th>4</th>
          <td>12300</td>
          <td>14851</td>
        </tr>
        <tr>
          <th>5</th>
          <td>19950</td>
          <td>21151</td>
        </tr>
        <tr>
          <th>6</th>
          <td>21300</td>
          <td>22501</td>
        </tr>
      </tbody>
    </table>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 58-60

Starting from here, all the processing will happen per gait sequence.
We will go through the steps just for a single gait sequence first and later put everything in a loop.

.. GENERATED FROM PYTHON SOURCE LINES 60-66

.. code-block:: Python

    first_gait_sequence = gait_sequences.iloc[0]
    first_gait_sequence_data = imu_data.iloc[
        first_gait_sequence.start : first_gait_sequence.end
    ]









.. GENERATED FROM PYTHON SOURCE LINES 67-69

Step 2: Initial Contact Detection
---------------------------------

.. GENERATED FROM PYTHON SOURCE LINES 69-77

.. code-block:: Python


    from mobgap.initial_contacts import IcdShinImproved

    icd = IcdShinImproved()
    icd.detect(first_gait_sequence_data, sampling_rate_hz=sampling_rate_hz)
    ic_list = icd.ic_list_
    ic_list






.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th>ic</th>
        </tr>
        <tr>
          <th>step_id</th>
          <th></th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>0</th>
          <td>86</td>
        </tr>
        <tr>
          <th>1</th>
          <td>158</td>
        </tr>
        <tr>
          <th>2</th>
          <td>216</td>
        </tr>
        <tr>
          <th>3</th>
          <td>271</td>
        </tr>
        <tr>
          <th>4</th>
          <td>326</td>
        </tr>
        <tr>
          <th>5</th>
          <td>381</td>
        </tr>
        <tr>
          <th>6</th>
          <td>441</td>
        </tr>
        <tr>
          <th>7</th>
          <td>496</td>
        </tr>
        <tr>
          <th>8</th>
          <td>560</td>
        </tr>
        <tr>
          <th>9</th>
          <td>621</td>
        </tr>
        <tr>
          <th>10</th>
          <td>696</td>
        </tr>
        <tr>
          <th>11</th>
          <td>795</td>
        </tr>
        <tr>
          <th>12</th>
          <td>870</td>
        </tr>
        <tr>
          <th>13</th>
          <td>949</td>
        </tr>
        <tr>
          <th>14</th>
          <td>1036</td>
        </tr>
        <tr>
          <th>15</th>
          <td>1131</td>
        </tr>
        <tr>
          <th>16</th>
          <td>1191</td>
        </tr>
      </tbody>
    </table>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 78-81

Step 2.5: Laterality Detection
------------------------------
For each IC we want to detect the laterality.

.. GENERATED FROM PYTHON SOURCE LINES 81-89

.. code-block:: Python

    from mobgap.laterality import LrcUllrich

    lrc = LrcUllrich()
    lrc.predict(
        first_gait_sequence_data, ic_list, sampling_rate_hz=sampling_rate_hz
    )
    ic_list = lrc.ic_lr_list_








.. GENERATED FROM PYTHON SOURCE LINES 90-95

Gait Sequence Refinement
------------------------
After detecting the ICs within the gait sequence, we can refine the gait sequence using the ICs.
Basically, we restrict the area of the gait sequence to the area between the first and the last IC.
This should ensure that the subsequent steps are only getting data that contains detectable gait.

.. GENERATED FROM PYTHON SOURCE LINES 95-103

.. code-block:: Python

    from mobgap.initial_contacts import refine_gs

    refined_gait_sequence, refined_ic_list = refine_gs(ic_list)
    refined_gait_sequence_data = first_gait_sequence_data.iloc[
        refined_gait_sequence.iloc[0].start : refined_gait_sequence.iloc[0].end
    ]









.. GENERATED FROM PYTHON SOURCE LINES 104-106

Step 3: Cadence Calculation
---------------------------

.. GENERATED FROM PYTHON SOURCE LINES 106-118

.. code-block:: Python

    from mobgap.cadence import CadFromIc

    cad = CadFromIc()
    cad.calculate(
        refined_gait_sequence_data,
        initial_contacts=refined_ic_list,
        sampling_rate_hz=sampling_rate_hz,
    )

    cad_per_sec = cad.cadence_per_sec_
    cad_per_sec






.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th>cadence_spm</th>
        </tr>
        <tr>
          <th>sec_center_samples</th>
          <th></th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>50</th>
          <td>109.090909</td>
        </tr>
        <tr>
          <th>150</th>
          <td>109.090909</td>
        </tr>
        <tr>
          <th>250</th>
          <td>109.090909</td>
        </tr>
        <tr>
          <th>350</th>
          <td>109.090909</td>
        </tr>
        <tr>
          <th>450</th>
          <td>96.000000</td>
        </tr>
        <tr>
          <th>550</th>
          <td>80.000000</td>
        </tr>
        <tr>
          <th>650</th>
          <td>80.000000</td>
        </tr>
        <tr>
          <th>750</th>
          <td>77.922078</td>
        </tr>
        <tr>
          <th>850</th>
          <td>68.965517</td>
        </tr>
        <tr>
          <th>950</th>
          <td>63.157895</td>
        </tr>
        <tr>
          <th>1050</th>
          <td>100.000000</td>
        </tr>
        <tr>
          <th>1150</th>
          <td>100.000000</td>
        </tr>
      </tbody>
    </table>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 119-121

Step 4: Stride Length Calculation
---------------------------------

.. GENERATED FROM PYTHON SOURCE LINES 121-134

.. code-block:: Python

    from mobgap.stride_length import SlZijlstra

    sl = SlZijlstra()
    sl.calculate(
        refined_gait_sequence_data,
        initial_contacts=refined_ic_list,
        sampling_rate_hz=sampling_rate_hz,
        **participant_metadata,
    )

    sl_per_sec = sl.stride_length_per_sec_
    sl_per_sec






.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th>stride_length_m</th>
        </tr>
        <tr>
          <th>sec_center_samples</th>
          <th></th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>50</th>
          <td>1.164494</td>
        </tr>
        <tr>
          <th>150</th>
          <td>1.180049</td>
        </tr>
        <tr>
          <th>250</th>
          <td>1.098622</td>
        </tr>
        <tr>
          <th>350</th>
          <td>1.031178</td>
        </tr>
        <tr>
          <th>450</th>
          <td>0.922796</td>
        </tr>
        <tr>
          <th>550</th>
          <td>0.801989</td>
        </tr>
        <tr>
          <th>650</th>
          <td>0.514388</td>
        </tr>
        <tr>
          <th>750</th>
          <td>0.590646</td>
        </tr>
        <tr>
          <th>850</th>
          <td>0.664410</td>
        </tr>
        <tr>
          <th>950</th>
          <td>0.305513</td>
        </tr>
        <tr>
          <th>1050</th>
          <td>0.327321</td>
        </tr>
        <tr>
          <th>1150</th>
          <td>0.327321</td>
        </tr>
      </tbody>
    </table>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 135-144

Step 5: Walking Speed Calculation
---------------------------------
Finally, we can calculate the walking speed.
This could be done by another sophisticated algorithm that uses the raw data to estimate the walking speed.
However, in the Mobilise-D pipeline we opted to base the walking speed calculation on the cadence and stride length
to avoid adding a walking speed that would not be coherent with the other results.

To allow to modify this in the future and to allow for different walking speed calculation algorithms, we still
encapsulate the walking speed calculation in a separate class that takes all the previous results as input.

.. GENERATED FROM PYTHON SOURCE LINES 144-158

.. code-block:: Python

    from mobgap.walking_speed import WsNaive

    ws = WsNaive()
    ws.calculate(
        refined_gait_sequence_data,
        initial_contacts=refined_ic_list,
        cadence_per_sec=cad_per_sec,
        stride_length_per_sec=sl_per_sec,
        sampling_rate_hz=sampling_rate_hz,
        **participant_metadata,
    )
    ws_per_sec = ws.walking_speed_per_sec_
    ws_per_sec






.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th>walking_speed_mps</th>
        </tr>
        <tr>
          <th>sec_center_samples</th>
          <th></th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>50</th>
          <td>1.058631</td>
        </tr>
        <tr>
          <th>150</th>
          <td>1.072771</td>
        </tr>
        <tr>
          <th>250</th>
          <td>0.998748</td>
        </tr>
        <tr>
          <th>350</th>
          <td>0.937434</td>
        </tr>
        <tr>
          <th>450</th>
          <td>0.738237</td>
        </tr>
        <tr>
          <th>550</th>
          <td>0.534659</td>
        </tr>
        <tr>
          <th>650</th>
          <td>0.342925</td>
        </tr>
        <tr>
          <th>750</th>
          <td>0.383536</td>
        </tr>
        <tr>
          <th>850</th>
          <td>0.381845</td>
        </tr>
        <tr>
          <th>950</th>
          <td>0.160796</td>
        </tr>
        <tr>
          <th>1050</th>
          <td>0.272768</td>
        </tr>
        <tr>
          <th>1150</th>
          <td>0.272768</td>
        </tr>
      </tbody>
    </table>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 159-168

Step 6: Turn Detection
----------------------
Independent of all other parameters, we detect turns in the gait sequence.
This does not influence the calculation of the other parameters, and is only used to gather the ``n_turns`` parameter.
Note, that the turning detection is usually done on the non-refined gs.
But this shouldn't really matter.

.. warning:: The turning algorithm is not evaluated. If you are planning to use detailed turning information, you
             should perform your own evaluation for your specific use-case.

.. GENERATED FROM PYTHON SOURCE LINES 168-175

.. code-block:: Python

    from mobgap.turning import TdElGohary

    turn = TdElGohary()
    turn.detect(first_gait_sequence_data, sampling_rate_hz=sampling_rate_hz)
    turn_list = turn.turn_list_
    turn_list






.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th>start</th>
          <th>end</th>
          <th>duration_s</th>
          <th>angle_deg</th>
          <th>direction</th>
        </tr>
        <tr>
          <th>turn_id</th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>0</th>
          <td>392</td>
          <td>715</td>
          <td>3.23</td>
          <td>-71.588625</td>
          <td>right</td>
        </tr>
        <tr>
          <th>1</th>
          <td>727</td>
          <td>942</td>
          <td>2.15</td>
          <td>77.106703</td>
          <td>left</td>
        </tr>
      </tbody>
    </table>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 176-183

After going through the steps for a single gait sequence,
we would then put all the data together to calculate the final results per WB.
But let's first put all the processing into an easy-to-read loop.

Actual Pipeline
---------------
We first define all the algorithms we want to use.

.. GENERATED FROM PYTHON SOURCE LINES 183-199

.. code-block:: Python

    from mobgap.cadence import CadFromIc
    from mobgap.gait_sequences import GsdIluz
    from mobgap.initial_contacts import IcdShinImproved, refine_gs
    from mobgap.laterality import LrcUllrich
    from mobgap.stride_length import SlZijlstra
    from mobgap.turning import TdElGohary
    from mobgap.walking_speed import WsNaive

    gsd = GsdIluz()
    icd = IcdShinImproved()
    lrc = LrcUllrich()
    cad = CadFromIc()
    sl = SlZijlstra()
    speed = WsNaive()
    turn = TdElGohary()








.. GENERATED FROM PYTHON SOURCE LINES 200-204

Then we calculate the gait sequences as before.

Note that some of the algorithms might need the participant metadata.
Hence, we pass it as keyword argument to all the algorithms.

.. GENERATED FROM PYTHON SOURCE LINES 204-207

.. code-block:: Python

    gsd.detect(imu_data, sampling_rate_hz=sampling_rate_hz, **participant_metadata)
    gait_sequences = gsd.gs_list_








.. GENERATED FROM PYTHON SOURCE LINES 208-213

Then we use a nested iterator to go through all the gait sequences and process them.
To learn more about this iterator,
check out the example about the :ref:`Gait Sequence Iterator <gs_iterator_example>`.
Note, that we use the special ``r`` object to store the results of each step and the ``subregion`` method to
elegantly handle the refined gait sequence.

.. GENERATED FROM PYTHON SOURCE LINES 213-255

.. code-block:: Python

    from mobgap.pipeline import GsIterator

    gs_iterator = GsIterator()

    for (_, gs_data), r in gs_iterator.iterate(imu_data, gait_sequences):
        icd = icd.clone().detect(
            gs_data, sampling_rate_hz=sampling_rate_hz, **participant_metadata
        )
        lrc = lrc.clone().predict(
            gs_data, icd.ic_list_, sampling_rate_hz=sampling_rate_hz
        )
        r.ic_list = lrc.ic_lr_list_
        turn = turn.clone().detect(gs_data, sampling_rate_hz=sampling_rate_hz)
        r.turn_list = turn.turn_list_

        refined_gs, refined_ic_list = refine_gs(r.ic_list)

        with gs_iterator.subregion(refined_gs) as ((_, refined_gs_data), rr):
            cad = cad.clone().calculate(
                refined_gs_data,
                initial_contacts=refined_ic_list,
                sampling_rate_hz=sampling_rate_hz,
                **participant_metadata,
            )
            rr.cadence_per_sec = cad.cadence_per_sec_
            sl = sl.clone().calculate(
                refined_gs_data,
                initial_contacts=refined_ic_list,
                sampling_rate_hz=sampling_rate_hz,
                **participant_metadata,
            )
            rr.stride_length_per_sec = sl.stride_length_per_sec_
            speed = speed.clone().calculate(
                refined_gs_data,
                initial_contacts=refined_ic_list,
                cadence_per_sec=cad.cadence_per_sec_,
                stride_length_per_sec=sl.stride_length_per_sec_,
                sampling_rate_hz=sampling_rate_hz,
                **participant_metadata,
            )
            rr.walking_speed_per_sec = speed.walking_speed_per_sec_








.. GENERATED FROM PYTHON SOURCE LINES 256-257

Now we can access all accumulated and offset-corrected results from the iterator.

.. GENERATED FROM PYTHON SOURCE LINES 257-261

.. code-block:: Python

    results = gs_iterator.results_

    results.ic_list






.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th></th>
          <th>ic</th>
          <th>lr_label</th>
        </tr>
        <tr>
          <th>gs_id</th>
          <th>step_id</th>
          <th></th>
          <th></th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th rowspan="5" valign="top">0</th>
          <th>0</th>
          <td>986</td>
          <td>right</td>
        </tr>
        <tr>
          <th>1</th>
          <td>1058</td>
          <td>left</td>
        </tr>
        <tr>
          <th>2</th>
          <td>1116</td>
          <td>right</td>
        </tr>
        <tr>
          <th>3</th>
          <td>1171</td>
          <td>left</td>
        </tr>
        <tr>
          <th>4</th>
          <td>1226</td>
          <td>right</td>
        </tr>
        <tr>
          <th>...</th>
          <th>...</th>
          <td>...</td>
          <td>...</td>
        </tr>
        <tr>
          <th rowspan="5" valign="top">6</th>
          <th>10</th>
          <td>22094</td>
          <td>left</td>
        </tr>
        <tr>
          <th>11</th>
          <td>22219</td>
          <td>left</td>
        </tr>
        <tr>
          <th>12</th>
          <td>22313</td>
          <td>right</td>
        </tr>
        <tr>
          <th>13</th>
          <td>22348</td>
          <td>left</td>
        </tr>
        <tr>
          <th>14</th>
          <td>22436</td>
          <td>left</td>
        </tr>
      </tbody>
    </table>
    <p>136 rows × 2 columns</p>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 262-267

We combine all per-sec results into one.

Note, that we remove the ``r_gs_id`` index, as we don't need it anymore and each normal ``gs`` is mapped to a single
refined ``gs`` anyway.
In case we would have multiple refined ``gs`` per normal ``gs``, we might need to keep the ``r_gs_id`` index around.

.. GENERATED FROM PYTHON SOURCE LINES 267-277

.. code-block:: Python

    combined_results = pd.concat(
        [
            results.cadence_per_sec,
            results.stride_length_per_sec,
            results.walking_speed_per_sec,
        ],
        axis=1,
    ).reset_index("r_gs_id", drop=True)
    combined_results






.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th></th>
          <th>cadence_spm</th>
          <th>stride_length_m</th>
          <th>walking_speed_mps</th>
        </tr>
        <tr>
          <th>gs_id</th>
          <th>sec_center_samples</th>
          <th></th>
          <th></th>
          <th></th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th rowspan="5" valign="top">0</th>
          <th>1036</th>
          <td>109.090909</td>
          <td>1.164494</td>
          <td>1.058631</td>
        </tr>
        <tr>
          <th>1136</th>
          <td>109.090909</td>
          <td>1.180049</td>
          <td>1.072771</td>
        </tr>
        <tr>
          <th>1236</th>
          <td>109.090909</td>
          <td>1.098622</td>
          <td>0.998748</td>
        </tr>
        <tr>
          <th>1336</th>
          <td>109.090909</td>
          <td>1.031178</td>
          <td>0.937434</td>
        </tr>
        <tr>
          <th>1436</th>
          <td>96.000000</td>
          <td>0.922796</td>
          <td>0.738237</td>
        </tr>
        <tr>
          <th>...</th>
          <th>...</th>
          <td>...</td>
          <td>...</td>
          <td>...</td>
        </tr>
        <tr>
          <th rowspan="5" valign="top">6</th>
          <th>22016</th>
          <td>63.829787</td>
          <td>0.974711</td>
          <td>0.518463</td>
        </tr>
        <tr>
          <th>22116</th>
          <td>63.829787</td>
          <td>1.045141</td>
          <td>0.555926</td>
        </tr>
        <tr>
          <th>22216</th>
          <td>63.829787</td>
          <td>1.076485</td>
          <td>0.572598</td>
        </tr>
        <tr>
          <th>22316</th>
          <td>68.181818</td>
          <td>0.611750</td>
          <td>0.347585</td>
        </tr>
        <tr>
          <th>22416</th>
          <td>68.181818</td>
          <td>0.783434</td>
          <td>0.445133</td>
        </tr>
      </tbody>
    </table>
    <p>94 rows × 3 columns</p>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 278-282

Using the combined results, we want to define walking bouts.
As walking bouts in the context of Mobilise-D are defined based on strides, we need to turn the ICs into strides and
the per-second values into per-stride values by using interpolation.
We also calculate the stride duration here.

.. GENERATED FROM PYTHON SOURCE LINES 282-293

.. code-block:: Python

    from mobgap.laterality import strides_list_from_ic_lr_list

    stride_list = (
        results.ic_list.groupby("gs_id", group_keys=False)
        .apply(strides_list_from_ic_lr_list)
        .assign(
            stride_duration_s=lambda df_: (df_.end - df_.start) / sampling_rate_hz
        )
    )
    stride_list






.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th></th>
          <th>start</th>
          <th>end</th>
          <th>lr_label</th>
          <th>stride_duration_s</th>
        </tr>
        <tr>
          <th>gs_id</th>
          <th>s_id</th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th rowspan="5" valign="top">0</th>
          <th>0</th>
          <td>986</td>
          <td>1116</td>
          <td>right</td>
          <td>1.30</td>
        </tr>
        <tr>
          <th>1</th>
          <td>1058</td>
          <td>1171</td>
          <td>left</td>
          <td>1.13</td>
        </tr>
        <tr>
          <th>2</th>
          <td>1116</td>
          <td>1226</td>
          <td>right</td>
          <td>1.10</td>
        </tr>
        <tr>
          <th>3</th>
          <td>1171</td>
          <td>1281</td>
          <td>left</td>
          <td>1.10</td>
        </tr>
        <tr>
          <th>4</th>
          <td>1226</td>
          <td>1341</td>
          <td>right</td>
          <td>1.15</td>
        </tr>
        <tr>
          <th>...</th>
          <th>...</th>
          <td>...</td>
          <td>...</td>
          <td>...</td>
          <td>...</td>
        </tr>
        <tr>
          <th rowspan="5" valign="top">6</th>
          <th>8</th>
          <td>21920</td>
          <td>22313</td>
          <td>right</td>
          <td>3.93</td>
        </tr>
        <tr>
          <th>9</th>
          <td>22017</td>
          <td>22094</td>
          <td>left</td>
          <td>0.77</td>
        </tr>
        <tr>
          <th>10</th>
          <td>22094</td>
          <td>22219</td>
          <td>left</td>
          <td>1.25</td>
        </tr>
        <tr>
          <th>11</th>
          <td>22219</td>
          <td>22348</td>
          <td>left</td>
          <td>1.29</td>
        </tr>
        <tr>
          <th>13</th>
          <td>22348</td>
          <td>22436</td>
          <td>left</td>
          <td>0.88</td>
        </tr>
      </tbody>
    </table>
    <p>122 rows × 4 columns</p>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 294-300

This initial stride list is completely unfiltered, and might contain very long strides, in areas where initial
contacts were not detected, or the participant was not walking for a short moment.
The stride list will be filtered later as part of the WB assembly.

For now, we are using linear interpolation to map the per-second cadence values to per-stride values and derive
approximated stride parameters.

.. GENERATED FROM PYTHON SOURCE LINES 300-310

.. code-block:: Python

    from mobgap.utils.df_operations import create_multi_groupby

    stride_list_with_approx_paras = create_multi_groupby(
        stride_list,
        combined_results,
        "gs_id",
        group_keys=False,
    ).apply(naive_sec_paras_to_regions, sampling_rate_hz=sampling_rate_hz)

    stride_list_with_approx_paras





.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th></th>
          <th>start</th>
          <th>end</th>
          <th>lr_label</th>
          <th>stride_duration_s</th>
          <th>cadence_spm</th>
          <th>stride_length_m</th>
          <th>walking_speed_mps</th>
        </tr>
        <tr>
          <th>gs_id</th>
          <th>s_id</th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th rowspan="5" valign="top">0</th>
          <th>0</th>
          <td>986</td>
          <td>1116</td>
          <td>right</td>
          <td>1.30</td>
          <td>109.090909</td>
          <td>1.168084</td>
          <td>1.061894</td>
        </tr>
        <tr>
          <th>1</th>
          <td>1058</td>
          <td>1171</td>
          <td>left</td>
          <td>1.13</td>
          <td>109.090909</td>
          <td>1.176194</td>
          <td>1.069268</td>
        </tr>
        <tr>
          <th>2</th>
          <td>1116</td>
          <td>1226</td>
          <td>right</td>
          <td>1.10</td>
          <td>109.090909</td>
          <td>1.150439</td>
          <td>1.045854</td>
        </tr>
        <tr>
          <th>3</th>
          <td>1171</td>
          <td>1281</td>
          <td>left</td>
          <td>1.10</td>
          <td>109.090909</td>
          <td>1.109726</td>
          <td>1.008842</td>
        </tr>
        <tr>
          <th>4</th>
          <td>1226</td>
          <td>1341</td>
          <td>right</td>
          <td>1.15</td>
          <td>109.090909</td>
          <td>1.066366</td>
          <td>0.969424</td>
        </tr>
        <tr>
          <th>...</th>
          <th>...</th>
          <td>...</td>
          <td>...</td>
          <td>...</td>
          <td>...</td>
          <td>...</td>
          <td>...</td>
          <td>...</td>
        </tr>
        <tr>
          <th rowspan="5" valign="top">6</th>
          <th>8</th>
          <td>21920</td>
          <td>22313</td>
          <td>right</td>
          <td>3.93</td>
          <td>64.119192</td>
          <td>0.974239</td>
          <td>0.519003</td>
        </tr>
        <tr>
          <th>9</th>
          <td>22017</td>
          <td>22094</td>
          <td>left</td>
          <td>0.77</td>
          <td>63.829787</td>
          <td>1.000322</td>
          <td>0.532086</td>
        </tr>
        <tr>
          <th>10</th>
          <td>22094</td>
          <td>22219</td>
          <td>left</td>
          <td>1.25</td>
          <td>63.829787</td>
          <td>1.058431</td>
          <td>0.562995</td>
        </tr>
        <tr>
          <th>11</th>
          <td>22219</td>
          <td>22348</td>
          <td>left</td>
          <td>1.29</td>
          <td>66.596195</td>
          <td>0.781072</td>
          <td>0.429567</td>
        </tr>
        <tr>
          <th>13</th>
          <td>22348</td>
          <td>22436</td>
          <td>left</td>
          <td>0.88</td>
          <td>68.181818</td>
          <td>0.748316</td>
          <td>0.425180</td>
        </tr>
      </tbody>
    </table>
    <p>122 rows × 7 columns</p>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 311-314

Now the final strides are regrouped into walking bouts.
For this we ignore which gait sequence the strides belong to, hence we remove the ``gs_id`` from the index, but keep
it around as column for debugging.

.. GENERATED FROM PYTHON SOURCE LINES 314-329

.. code-block:: Python

    from mobgap.wba import StrideSelection, WbAssembly

    flat_index = pd.Index(
        [
            "_".join(str(e) for e in s_id)
            for s_id in stride_list_with_approx_paras.index
        ],
        name="s_id",
    )
    stride_list_with_approx_paras = (
        stride_list_with_approx_paras.reset_index("gs_id")
        .rename(columns={"gs_id": "original_gs_id"})
        .set_index(flat_index)
    )








.. GENERATED FROM PYTHON SOURCE LINES 330-332

Then we apply the stride selection (note that we have additional rules in case the stride length is available) and
then group the remaining strides into walking bouts.

.. GENERATED FROM PYTHON SOURCE LINES 332-344

.. code-block:: Python

    ss = StrideSelection().filter(
        stride_list_with_approx_paras, sampling_rate_hz=sampling_rate_hz
    )
    wba = WbAssembly().assemble(
        ss.filtered_stride_list_,
        raw_initial_contacts=results.ic_list,
        sampling_rate_hz=sampling_rate_hz,
    )

    final_strides = wba.annotated_stride_list_
    final_strides






.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th></th>
          <th>original_gs_id</th>
          <th>start</th>
          <th>end</th>
          <th>lr_label</th>
          <th>stride_duration_s</th>
          <th>cadence_spm</th>
          <th>stride_length_m</th>
          <th>walking_speed_mps</th>
        </tr>
        <tr>
          <th>wb_id</th>
          <th>s_id</th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th rowspan="5" valign="top">0</th>
          <th>0_0</th>
          <td>0</td>
          <td>986</td>
          <td>1116</td>
          <td>right</td>
          <td>1.30</td>
          <td>109.090909</td>
          <td>1.168084</td>
          <td>1.061894</td>
        </tr>
        <tr>
          <th>0_1</th>
          <td>0</td>
          <td>1058</td>
          <td>1171</td>
          <td>left</td>
          <td>1.13</td>
          <td>109.090909</td>
          <td>1.176194</td>
          <td>1.069268</td>
        </tr>
        <tr>
          <th>0_2</th>
          <td>0</td>
          <td>1116</td>
          <td>1226</td>
          <td>right</td>
          <td>1.10</td>
          <td>109.090909</td>
          <td>1.150439</td>
          <td>1.045854</td>
        </tr>
        <tr>
          <th>0_3</th>
          <td>0</td>
          <td>1171</td>
          <td>1281</td>
          <td>left</td>
          <td>1.10</td>
          <td>109.090909</td>
          <td>1.109726</td>
          <td>1.008842</td>
        </tr>
        <tr>
          <th>0_4</th>
          <td>0</td>
          <td>1226</td>
          <td>1341</td>
          <td>right</td>
          <td>1.15</td>
          <td>109.090909</td>
          <td>1.066366</td>
          <td>0.969424</td>
        </tr>
        <tr>
          <th>...</th>
          <th>...</th>
          <td>...</td>
          <td>...</td>
          <td>...</td>
          <td>...</td>
          <td>...</td>
          <td>...</td>
          <td>...</td>
          <td>...</td>
        </tr>
        <tr>
          <th rowspan="5" valign="top">4</th>
          <th>6_7</th>
          <td>6</td>
          <td>21827</td>
          <td>21920</td>
          <td>right</td>
          <td>0.93</td>
          <td>62.971346</td>
          <td>0.889741</td>
          <td>0.465905</td>
        </tr>
        <tr>
          <th>6_9</th>
          <td>6</td>
          <td>22017</td>
          <td>22094</td>
          <td>left</td>
          <td>0.77</td>
          <td>63.829787</td>
          <td>1.000322</td>
          <td>0.532086</td>
        </tr>
        <tr>
          <th>6_10</th>
          <td>6</td>
          <td>22094</td>
          <td>22219</td>
          <td>left</td>
          <td>1.25</td>
          <td>63.829787</td>
          <td>1.058431</td>
          <td>0.562995</td>
        </tr>
        <tr>
          <th>6_11</th>
          <td>6</td>
          <td>22219</td>
          <td>22348</td>
          <td>left</td>
          <td>1.29</td>
          <td>66.596195</td>
          <td>0.781072</td>
          <td>0.429567</td>
        </tr>
        <tr>
          <th>6_13</th>
          <td>6</td>
          <td>22348</td>
          <td>22436</td>
          <td>left</td>
          <td>0.88</td>
          <td>68.181818</td>
          <td>0.748316</td>
          <td>0.425180</td>
        </tr>
      </tbody>
    </table>
    <p>120 rows × 8 columns</p>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 345-346

We also have meta information about the WBs available.

.. GENERATED FROM PYTHON SOURCE LINES 346-349

.. code-block:: Python

    per_wb_params = wba.wb_meta_parameters_
    per_wb_params.drop(columns="rule_obj").T






.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th>wb_id</th>
          <th>0</th>
          <th>1</th>
          <th>2</th>
          <th>3</th>
          <th>4</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>start</th>
          <td>986</td>
          <td>4668</td>
          <td>9707</td>
          <td>11304</td>
          <td>19996</td>
        </tr>
        <tr>
          <th>end</th>
          <td>2091</td>
          <td>6049</td>
          <td>10794</td>
          <td>14796</td>
          <td>22436</td>
        </tr>
        <tr>
          <th>n_strides</th>
          <td>15</td>
          <td>17</td>
          <td>13</td>
          <td>47</td>
          <td>28</td>
        </tr>
        <tr>
          <th>rule_name</th>
          <td>max_break</td>
          <td>max_break</td>
          <td>max_break</td>
          <td>max_break</td>
          <td>max_break</td>
        </tr>
        <tr>
          <th>duration_s</th>
          <td>11.05</td>
          <td>13.81</td>
          <td>10.87</td>
          <td>34.92</td>
          <td>24.4</td>
        </tr>
        <tr>
          <th>n_raw_initial_contacts</th>
          <td>17</td>
          <td>19</td>
          <td>15</td>
          <td>52</td>
          <td>33</td>
        </tr>
      </tbody>
    </table>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 350-351

We extend them further with the per-stride parameters.

.. GENERATED FROM PYTHON SOURCE LINES 351-369

.. code-block:: Python

    params_to_aggregate = [
        "stride_duration_s",
        "cadence_spm",
        "stride_length_m",
        "walking_speed_mps",
    ]
    per_wb_params = pd.concat(
        [
            per_wb_params,
            final_strides.reindex(columns=params_to_aggregate)
            .groupby(["wb_id"])
            .mean(),
        ],
        axis=1,
    )

    per_wb_params.drop(columns="rule_obj").T






.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th>wb_id</th>
          <th>0</th>
          <th>1</th>
          <th>2</th>
          <th>3</th>
          <th>4</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>start</th>
          <td>986</td>
          <td>4668</td>
          <td>9707</td>
          <td>11304</td>
          <td>19996</td>
        </tr>
        <tr>
          <th>end</th>
          <td>2091</td>
          <td>6049</td>
          <td>10794</td>
          <td>14796</td>
          <td>22436</td>
        </tr>
        <tr>
          <th>n_strides</th>
          <td>15</td>
          <td>17</td>
          <td>13</td>
          <td>47</td>
          <td>28</td>
        </tr>
        <tr>
          <th>rule_name</th>
          <td>max_break</td>
          <td>max_break</td>
          <td>max_break</td>
          <td>max_break</td>
          <td>max_break</td>
        </tr>
        <tr>
          <th>duration_s</th>
          <td>11.05</td>
          <td>13.81</td>
          <td>10.87</td>
          <td>34.92</td>
          <td>24.4</td>
        </tr>
        <tr>
          <th>n_raw_initial_contacts</th>
          <td>17</td>
          <td>19</td>
          <td>15</td>
          <td>52</td>
          <td>33</td>
        </tr>
        <tr>
          <th>stride_duration_s</th>
          <td>1.211333</td>
          <td>1.462353</td>
          <td>1.424615</td>
          <td>1.235106</td>
          <td>1.292143</td>
        </tr>
        <tr>
          <th>cadence_spm</th>
          <td>93.902776</td>
          <td>81.553515</td>
          <td>82.836029</td>
          <td>97.107214</td>
          <td>87.62698</td>
        </tr>
        <tr>
          <th>stride_length_m</th>
          <td>0.814055</td>
          <td>0.81388</td>
          <td>0.662401</td>
          <td>0.736345</td>
          <td>0.83613</td>
        </tr>
        <tr>
          <th>walking_speed_mps</th>
          <td>0.667326</td>
          <td>0.535375</td>
          <td>0.46741</td>
          <td>0.59769</td>
          <td>0.601725</td>
        </tr>
      </tbody>
    </table>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 370-371

For each WB we can then apply thresholds to check if the calculated parameters are within the expected range.

.. GENERATED FROM PYTHON SOURCE LINES 371-386

.. code-block:: Python

    from mobgap.aggregation import apply_thresholds, get_mobilised_dmo_thresholds

    thresholds = get_mobilised_dmo_thresholds()

    per_wb_params_mask = apply_thresholds(
        per_wb_params,
        thresholds,
        cohort=long_trial.participant_metadata["cohort"],
        height_m=long_trial.participant_metadata["height_m"],
        measurement_condition=long_trial.recording_metadata[
            "measurement_condition"
        ],
    )
    per_wb_params_mask.T






.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th>wb_id</th>
          <th>0</th>
          <th>1</th>
          <th>2</th>
          <th>3</th>
          <th>4</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>start</th>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
        </tr>
        <tr>
          <th>end</th>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
        </tr>
        <tr>
          <th>n_strides</th>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
        </tr>
        <tr>
          <th>rule_name</th>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
        </tr>
        <tr>
          <th>rule_obj</th>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
        </tr>
        <tr>
          <th>duration_s</th>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
        </tr>
        <tr>
          <th>n_raw_initial_contacts</th>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
          <td>NaN</td>
        </tr>
        <tr>
          <th>stride_duration_s</th>
          <td>True</td>
          <td>True</td>
          <td>True</td>
          <td>True</td>
          <td>True</td>
        </tr>
        <tr>
          <th>cadence_spm</th>
          <td>True</td>
          <td>True</td>
          <td>True</td>
          <td>True</td>
          <td>True</td>
        </tr>
        <tr>
          <th>stride_length_m</th>
          <td>True</td>
          <td>True</td>
          <td>True</td>
          <td>True</td>
          <td>True</td>
        </tr>
        <tr>
          <th>walking_speed_mps</th>
          <td>True</td>
          <td>True</td>
          <td>True</td>
          <td>True</td>
          <td>True</td>
        </tr>
      </tbody>
    </table>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 387-395

We can see that we either get NaN (for parameters that are not checked) or True/False values for each parameter.

This output together with the per-WB parameters would then normally be used in some aggregation step to calculate
single values per participant, day, or other grouping criteria.
Depending on the use-case, this aggregation can be performed withing the "per-recording" pipeline or as a separate
step after processing all recordings.

Here, we perform it per recording and calculate a single values from all the WBs.

.. GENERATED FROM PYTHON SOURCE LINES 395-406

.. code-block:: Python

    from mobgap.aggregation import MobilisedAggregator

    agg = MobilisedAggregator(
        **MobilisedAggregator.PredefinedParameters.single_recording
    )
    agg_results = agg.aggregate(
        per_wb_params, wb_dmos_mask=per_wb_params_mask
    ).aggregated_data_
    agg_results.T







.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th>all_wbs</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>wb_all__count</th>
          <td>5</td>
        </tr>
        <tr>
          <th>total_walking_duration_min</th>
          <td>1.584167</td>
        </tr>
        <tr>
          <th>wb_all__n_raw_initial_contacts__sum</th>
          <td>136</td>
        </tr>
        <tr>
          <th>wb_all__duration_s__avg</th>
          <td>13.81</td>
        </tr>
        <tr>
          <th>wb_all__duration_s__p90</th>
          <td>30.712</td>
        </tr>
        <tr>
          <th>wb_all__duration_s__var</th>
          <td>0.550987</td>
        </tr>
        <tr>
          <th>wb_all__cadence_spm__avg</th>
          <td>88.605303</td>
        </tr>
        <tr>
          <th>wb_all__stride_duration_s__avg</th>
          <td>1.32511</td>
        </tr>
        <tr>
          <th>wb_all__cadence_spm__var</th>
          <td>0.076611</td>
        </tr>
        <tr>
          <th>wb_all__stride_duration_s__var</th>
          <td>0.085103</td>
        </tr>
        <tr>
          <th>wb_10_30__count</th>
          <td>4</td>
        </tr>
        <tr>
          <th>wb_10_30__walking_speed_mps__avg</th>
          <td>0.567959</td>
        </tr>
        <tr>
          <th>wb_10_30__stride_length_m__avg</th>
          <td>0.781617</td>
        </tr>
        <tr>
          <th>wb_10__count</th>
          <td>5</td>
        </tr>
        <tr>
          <th>wb_10__walking_speed_mps__p90</th>
          <td>0.641085</td>
        </tr>
        <tr>
          <th>wb_30__count</th>
          <td>1</td>
        </tr>
        <tr>
          <th>wb_30__walking_speed_mps__avg</th>
          <td>0.59769</td>
        </tr>
        <tr>
          <th>wb_30__stride_length_m__avg</th>
          <td>0.736345</td>
        </tr>
        <tr>
          <th>wb_30__cadence_spm__avg</th>
          <td>97.107214</td>
        </tr>
        <tr>
          <th>wb_30__stride_duration_s__avg</th>
          <td>1.235106</td>
        </tr>
        <tr>
          <th>wb_30__walking_speed_mps__p90</th>
          <td>0.59769</td>
        </tr>
        <tr>
          <th>wb_30__cadence_spm__p90</th>
          <td>97.107214</td>
        </tr>
        <tr>
          <th>wb_30__walking_speed_mps__var</th>
          <td>NaN</td>
        </tr>
        <tr>
          <th>wb_30__stride_length_m__var</th>
          <td>NaN</td>
        </tr>
        <tr>
          <th>wb_60__count</th>
          <td>0</td>
        </tr>
      </tbody>
    </table>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 407-412

Running as a single pipeline
----------------------------
The steps that are shown above, are exactly the steps that are performed in the Mobilise-D pipeline.
Hence, we can also use the pre-built pipeline to perform the same steps.
This is shown below.

.. GENERATED FROM PYTHON SOURCE LINES 412-430

.. code-block:: Python

    from mobgap.pipeline import GenericMobilisedPipeline

    pipeline = GenericMobilisedPipeline(
        gait_sequence_detection=gsd,
        initial_contact_detection=icd,
        laterality_classification=lrc,
        cadence_calculation=cad,
        stride_length_calculation=sl,
        turn_detection=turn,
        walking_speed_calculation=ws,
        stride_selection=ss,
        wba=wba,
        dmo_thresholds=thresholds,
        dmo_aggregation=agg,
    )

    pipeline.safe_run(long_trial)





.. rst-class:: sphx-glr-script-out

 .. code-block:: none


    GenericMobilisedPipeline(cadence_calculation=CadFromIc(max_interpolation_gap_s=3, step_time_smoothing=HampelFilter(half_window_size=2, n_sigmas=3.0)), dmo_aggregation=MobilisedAggregator(groupby=None, unique_wb_id_column='wb_id', use_original_names=False), dmo_thresholds=condition                free_living              ...     global         
    threshold_type                   min         max  ...        min      max
    dmo               cohort                          ...                    
    cadence_spm       CHF      40.594770  167.942930  ...  40.000000  172.900
                      COPD     38.880484  151.558718  ...  40.000000  172.900
                      HA       35.751898  156.946955  ...  40.000000  172.900
                      MS       38.443211  155.394496  ...  40.000000  172.900
                      PD       40.957969  142.121947  ...  40.000000  172.900
                      PFF      42.191719  157.613665  ...  40.000000  172.900
    walking_speed_mps CHF       0.112478    1.757103  ...   0.081515    2.220
                      COPD      0.090731    1.641773  ...   0.081515    2.220
                      HA        0.097413    1.965728  ...   0.081515    2.220
                      MS        0.085918    1.920262  ...   0.081515    2.220
                      PD        0.081515    1.735348  ...   0.081515    2.220
                      PFF       0.104547    1.553186  ...   0.081515    2.220
    stride_length_m   CHF       0.185308    2.166646  ...   0.150523    2.190
                      COPD      0.176403    1.711645  ...   0.150523    2.190
                      HA        0.155126    2.024694  ...   0.150523    2.190
                      MS        0.191099    1.940537  ...   0.150523    2.190
                      PD        0.150523    1.982926  ...   0.150523    2.190
                      PFF       0.206787    1.697251  ...   0.150523    2.190
    stride_duration_s CHF       0.702000    3.030857  ...   0.460000    3.000
                      COPD      0.770000    3.000000  ...   0.460000    3.000
                      HA        0.735435    3.254400  ...   0.460000    3.000
                      MS        0.775597    3.057750  ...   0.460000    3.000
                      PD        0.836253    2.928000  ...   0.460000    3.000
                      PFF       0.744000    2.769000  ...   0.460000    3.000
    step_duration_s   CHF       0.376000    1.504500  ...   0.140000    2.124
                      COPD      0.390400    1.788000  ...   0.140000    2.124
                      HA        0.367972    1.730400  ...   0.140000    2.124
                      MS        0.388084    1.905000  ...   0.140000    2.124
                      PD        0.417216    1.605600  ...   0.140000    2.124
                      PFF       0.371429    2.124000  ...   0.140000    2.124

    [30 rows x 8 columns], gait_sequence_detection=GsdIluz(acc_v_standing_threshold=4.903325, allowed_acc_v_change_per_window=0.15, allowed_steps_per_s=(0.6666666666666666, 3), mean_activity_threshold=-0.980665, min_gsd_duration_s=5, pre_filter=FirFilter(cutoff_freq_hz=(0.5, 3), filter_type='bandpass', order=100, window='hamming', zero_phase=True), sin_template_freq_hz=2, std_activity_threshold=0.0980665, step_detection_thresholds=(0.0392266, 0.04903325), use_original_peak_detection=False, window_length_s=3, window_overlap=0.5), initial_contact_detection=IcdShinImproved(axis='norm'), laterality_classification=LrcUllrich(clf_pipe=Pipeline(steps=[('scaler', MinMaxScaler()), ('clf', SVC(C=1, kernel='linear'))]), smoothing_filter=ButterworthFilter(cutoff_freq_hz=(0.5, 2), filter_type='bandpass', order=4, zero_phase=True)), recommended_cohorts=None, stride_length_calculation=SlZijlstra(acc_smoothing=ButterworthFilter(cutoff_freq_hz=0.1, filter_type='highpass', order=4, zero_phase=True), max_interpolation_gap_s=3, orientation_method=None, speed_smoothing=ButterworthFilter(cutoff_freq_hz=1, filter_type='highpass', order=4, zero_phase=True), step_length_scaling_factor=1.14675, step_length_smoothing=HampelFilter(half_window_size=2, n_sigmas=3.0)), stride_selection=StrideSelection(incompatible_rules='warn', rules=[('stride_duration_thres', IntervalDurationCriteria(inclusive=(False, True), max_duration_s=3.0, min_duration_s=0.2)), ('stride_length_thres', IntervalParameterCriteria(inclusive=(False, True), lower_threshold=0.15, parameter='stride_length_m', upper_threshold=None))]), turn_detection=TdElGohary(allowed_turn_angle_deg=(45, inf), allowed_turn_duration_s=(0.5, 10), lower_threshold_velocity_dps=5, min_gap_between_turns_s=0.05, min_peak_angle_velocity_dps=15, orientation_estimation=None, smoothing_filter=ButterworthFilter(cutoff_freq_hz=0.5, filter_type='lowpass', order=4, zero_phase=True)), walking_speed_calculation=WsNaive(), wba=WbAssembly(rules=[('min_strides', NStridesCriteria(min_strides=4, min_strides_left=3, min_strides_right=3)), ('max_break', MaxBreakCriteria(consider_end_as_break=True, max_break_s=3, remove_last_ic=False))]))



.. GENERATED FROM PYTHON SOURCE LINES 431-435

The results are stored in the pipeline object.
And basically all the individual results that are shown above are also available in the pipeline object.

For example the per stride parameters:

.. GENERATED FROM PYTHON SOURCE LINES 435-437

.. code-block:: Python

    pipeline.raw_per_stride_parameters_






.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th></th>
          <th>start</th>
          <th>end</th>
          <th>lr_label</th>
          <th>stride_duration_s</th>
          <th>cadence_spm</th>
          <th>stride_length_m</th>
          <th>walking_speed_mps</th>
        </tr>
        <tr>
          <th>gs_id</th>
          <th>s_id</th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th rowspan="5" valign="top">0</th>
          <th>0</th>
          <td>986</td>
          <td>1116</td>
          <td>right</td>
          <td>1.30</td>
          <td>109.090909</td>
          <td>1.168084</td>
          <td>1.061894</td>
        </tr>
        <tr>
          <th>1</th>
          <td>1058</td>
          <td>1171</td>
          <td>left</td>
          <td>1.13</td>
          <td>109.090909</td>
          <td>1.176194</td>
          <td>1.069268</td>
        </tr>
        <tr>
          <th>2</th>
          <td>1116</td>
          <td>1226</td>
          <td>right</td>
          <td>1.10</td>
          <td>109.090909</td>
          <td>1.150439</td>
          <td>1.045854</td>
        </tr>
        <tr>
          <th>3</th>
          <td>1171</td>
          <td>1281</td>
          <td>left</td>
          <td>1.10</td>
          <td>109.090909</td>
          <td>1.109726</td>
          <td>1.008842</td>
        </tr>
        <tr>
          <th>4</th>
          <td>1226</td>
          <td>1341</td>
          <td>right</td>
          <td>1.15</td>
          <td>109.090909</td>
          <td>1.066366</td>
          <td>0.969424</td>
        </tr>
        <tr>
          <th>...</th>
          <th>...</th>
          <td>...</td>
          <td>...</td>
          <td>...</td>
          <td>...</td>
          <td>...</td>
          <td>...</td>
          <td>...</td>
        </tr>
        <tr>
          <th rowspan="5" valign="top">6</th>
          <th>8</th>
          <td>21920</td>
          <td>22313</td>
          <td>right</td>
          <td>3.93</td>
          <td>64.119192</td>
          <td>0.974239</td>
          <td>0.519003</td>
        </tr>
        <tr>
          <th>9</th>
          <td>22017</td>
          <td>22094</td>
          <td>left</td>
          <td>0.77</td>
          <td>63.829787</td>
          <td>1.000322</td>
          <td>0.532086</td>
        </tr>
        <tr>
          <th>10</th>
          <td>22094</td>
          <td>22219</td>
          <td>left</td>
          <td>1.25</td>
          <td>63.829787</td>
          <td>1.058431</td>
          <td>0.562995</td>
        </tr>
        <tr>
          <th>11</th>
          <td>22219</td>
          <td>22348</td>
          <td>left</td>
          <td>1.29</td>
          <td>66.596195</td>
          <td>0.781072</td>
          <td>0.429567</td>
        </tr>
        <tr>
          <th>13</th>
          <td>22348</td>
          <td>22436</td>
          <td>left</td>
          <td>0.88</td>
          <td>68.181818</td>
          <td>0.748316</td>
          <td>0.425180</td>
        </tr>
      </tbody>
    </table>
    <p>122 rows × 7 columns</p>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 438-439

The per-wb parameters:

.. GENERATED FROM PYTHON SOURCE LINES 439-441

.. code-block:: Python

    pipeline.per_wb_parameters_






.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th>start</th>
          <th>end</th>
          <th>n_strides</th>
          <th>rule_name</th>
          <th>rule_obj</th>
          <th>duration_s</th>
          <th>n_raw_initial_contacts</th>
          <th>stride_duration_s</th>
          <th>cadence_spm</th>
          <th>stride_length_m</th>
          <th>walking_speed_mps</th>
        </tr>
        <tr>
          <th>wb_id</th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>0</th>
          <td>986</td>
          <td>2091</td>
          <td>15</td>
          <td>max_break</td>
          <td>MaxBreakCriteria(consider_end_as_break=True, m...</td>
          <td>11.05</td>
          <td>17</td>
          <td>1.211333</td>
          <td>93.902776</td>
          <td>0.814055</td>
          <td>0.667326</td>
        </tr>
        <tr>
          <th>1</th>
          <td>4668</td>
          <td>6049</td>
          <td>17</td>
          <td>max_break</td>
          <td>MaxBreakCriteria(consider_end_as_break=True, m...</td>
          <td>13.81</td>
          <td>19</td>
          <td>1.462353</td>
          <td>81.553515</td>
          <td>0.813880</td>
          <td>0.535375</td>
        </tr>
        <tr>
          <th>2</th>
          <td>9707</td>
          <td>10794</td>
          <td>13</td>
          <td>max_break</td>
          <td>MaxBreakCriteria(consider_end_as_break=True, m...</td>
          <td>10.87</td>
          <td>15</td>
          <td>1.424615</td>
          <td>82.836029</td>
          <td>0.662401</td>
          <td>0.467410</td>
        </tr>
        <tr>
          <th>3</th>
          <td>11304</td>
          <td>14796</td>
          <td>47</td>
          <td>max_break</td>
          <td>MaxBreakCriteria(consider_end_as_break=True, m...</td>
          <td>34.92</td>
          <td>52</td>
          <td>1.235106</td>
          <td>97.107214</td>
          <td>0.736345</td>
          <td>0.597690</td>
        </tr>
        <tr>
          <th>4</th>
          <td>19996</td>
          <td>22436</td>
          <td>28</td>
          <td>max_break</td>
          <td>MaxBreakCriteria(consider_end_as_break=True, m...</td>
          <td>24.40</td>
          <td>33</td>
          <td>1.292143</td>
          <td>87.626980</td>
          <td>0.836130</td>
          <td>0.601725</td>
        </tr>
      </tbody>
    </table>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 442-443

And the aggregated parameters:

.. GENERATED FROM PYTHON SOURCE LINES 443-444

.. code-block:: Python

    pipeline.aggregated_parameters_





.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }

        .dataframe tbody tr th {
            vertical-align: top;
        }

        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th>wb_all__count</th>
          <th>total_walking_duration_min</th>
          <th>wb_all__n_raw_initial_contacts__sum</th>
          <th>wb_all__duration_s__avg</th>
          <th>wb_all__duration_s__p90</th>
          <th>wb_all__duration_s__var</th>
          <th>wb_all__cadence_spm__avg</th>
          <th>wb_all__stride_duration_s__avg</th>
          <th>wb_all__cadence_spm__var</th>
          <th>wb_all__stride_duration_s__var</th>
          <th>wb_10_30__count</th>
          <th>wb_10_30__walking_speed_mps__avg</th>
          <th>wb_10_30__stride_length_m__avg</th>
          <th>wb_10__count</th>
          <th>wb_10__walking_speed_mps__p90</th>
          <th>wb_30__count</th>
          <th>wb_30__walking_speed_mps__avg</th>
          <th>wb_30__stride_length_m__avg</th>
          <th>wb_30__cadence_spm__avg</th>
          <th>wb_30__stride_duration_s__avg</th>
          <th>wb_30__walking_speed_mps__p90</th>
          <th>wb_30__cadence_spm__p90</th>
          <th>wb_30__walking_speed_mps__var</th>
          <th>wb_30__stride_length_m__var</th>
          <th>wb_60__count</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>all_wbs</th>
          <td>5</td>
          <td>1.584167</td>
          <td>136</td>
          <td>13.81</td>
          <td>30.712</td>
          <td>0.550987</td>
          <td>88.605303</td>
          <td>1.32511</td>
          <td>0.076611</td>
          <td>0.085103</td>
          <td>4</td>
          <td>0.567959</td>
          <td>0.781617</td>
          <td>5</td>
          <td>0.641085</td>
          <td>1</td>
          <td>0.59769</td>
          <td>0.736345</td>
          <td>97.107214</td>
          <td>1.235106</td>
          <td>0.59769</td>
          <td>97.107214</td>
          <td>NaN</td>
          <td>NaN</td>
          <td>0</td>
        </tr>
      </tbody>
    </table>
    </div>
    </div>
    <br />
    <br />


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

   **Total running time of the script:** (0 minutes 6.823 seconds)

**Estimated memory usage:**  86 MB


.. _sphx_glr_download_auto_examples_pipeline__02_step_by_step_mobilised_pipeline.py:

.. only:: html

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

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

      :download:`Download Jupyter notebook: _02_step_by_step_mobilised_pipeline.ipynb <_02_step_by_step_mobilised_pipeline.ipynb>`

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

      :download:`Download Python source code: _02_step_by_step_mobilised_pipeline.py <_02_step_by_step_mobilised_pipeline.py>`

    .. container:: sphx-glr-download sphx-glr-download-zip

      :download:`Download zipped: _02_step_by_step_mobilised_pipeline.zip <_02_step_by_step_mobilised_pipeline.zip>`


.. only:: html

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

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