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

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

.. _sphx_glr_auto_examples_datasets_align.py:


.. _exa-align:

Align datasets
==============

Shows how to combine information from two datasets describing the same cases,
but not necessarily in the same order.

.. GENERATED FROM PYTHON SOURCE LINES 10-29

.. code-block:: Python

    # Author: Christian Brodbeck <christianbrodbeck@nyu.edu>
    import random
    import string

    from eelbrain import *


    # Generate a dataset with known sequence
    ds = Dataset()
    ds['ascii'] = Factor(string.ascii_lowercase)
    # Add an index variable to the dataset to later identify the cases
    ds.index()

    # Generate two shuffled copies of the dataset (and print them to confirm that
    # they are shuffled)
    ds1 = ds[random.sample(range(ds.n_cases), 15)]
    ds1.head()







.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <figure><table border="1" frame="hsides" rules="none" cellpadding="2"><tr>
    <td style="text-align:left">#</td>
    <td style="text-align:left">ascii</td>
    <td style="text-align:left">index</td>
    </tr>
    <tr>
    <td style="text-align:left">0</td>
    <td style="text-align:left">t</td>
    <td style="text-align:left">19</td>
    </tr>
    <tr>
    <td style="text-align:left">1</td>
    <td style="text-align:left">x</td>
    <td style="text-align:left">23</td>
    </tr>
    <tr>
    <td style="text-align:left">2</td>
    <td style="text-align:left">y</td>
    <td style="text-align:left">24</td>
    </tr>
    <tr>
    <td style="text-align:left">3</td>
    <td style="text-align:left">l</td>
    <td style="text-align:left">11</td>
    </tr>
    <tr>
    <td style="text-align:left">4</td>
    <td style="text-align:left">n</td>
    <td style="text-align:left">13</td>
    </tr>
    <tr>
    <td style="text-align:left">5</td>
    <td style="text-align:left">u</td>
    <td style="text-align:left">20</td>
    </tr>
    <tr>
    <td style="text-align:left">6</td>
    <td style="text-align:left">q</td>
    <td style="text-align:left">16</td>
    </tr>
    <tr>
    <td style="text-align:left">7</td>
    <td style="text-align:left">g</td>
    <td style="text-align:left">6</td>
    </tr>
    <tr>
    <td style="text-align:left">8</td>
    <td style="text-align:left">a</td>
    <td style="text-align:left">0</td>
    </tr>
    <tr>
    <td style="text-align:left">9</td>
    <td style="text-align:left">d</td>
    <td style="text-align:left">3</td>
    </tr></table></figure>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 30-34

.. code-block:: Python

    ds2 = ds[random.sample(range(ds.n_cases), 16)]
    ds2.head()







.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <figure><table border="1" frame="hsides" rules="none" cellpadding="2"><tr>
    <td style="text-align:left">#</td>
    <td style="text-align:left">ascii</td>
    <td style="text-align:left">index</td>
    </tr>
    <tr>
    <td style="text-align:left">0</td>
    <td style="text-align:left">m</td>
    <td style="text-align:left">12</td>
    </tr>
    <tr>
    <td style="text-align:left">1</td>
    <td style="text-align:left">o</td>
    <td style="text-align:left">14</td>
    </tr>
    <tr>
    <td style="text-align:left">2</td>
    <td style="text-align:left">b</td>
    <td style="text-align:left">1</td>
    </tr>
    <tr>
    <td style="text-align:left">3</td>
    <td style="text-align:left">y</td>
    <td style="text-align:left">24</td>
    </tr>
    <tr>
    <td style="text-align:left">4</td>
    <td style="text-align:left">s</td>
    <td style="text-align:left">18</td>
    </tr>
    <tr>
    <td style="text-align:left">5</td>
    <td style="text-align:left">v</td>
    <td style="text-align:left">21</td>
    </tr>
    <tr>
    <td style="text-align:left">6</td>
    <td style="text-align:left">a</td>
    <td style="text-align:left">0</td>
    </tr>
    <tr>
    <td style="text-align:left">7</td>
    <td style="text-align:left">p</td>
    <td style="text-align:left">15</td>
    </tr>
    <tr>
    <td style="text-align:left">8</td>
    <td style="text-align:left">w</td>
    <td style="text-align:left">22</td>
    </tr>
    <tr>
    <td style="text-align:left">9</td>
    <td style="text-align:left">j</td>
    <td style="text-align:left">9</td>
    </tr></table></figure>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 35-40

Align the datasets
------------------

Use the ``"index"`` variable added above to identify cases and align the two
datasets

.. GENERATED FROM PYTHON SOURCE LINES 40-47

.. code-block:: Python


    ds1_aligned, ds2_aligned = align(ds1, ds2, 'index')

    # show the ascii sequences for the two datasets next to each other to
    # demonstrate that they are aligned
    ds1_aligned['ascii_ds2'] = ds2_aligned['ascii']
    ds1_aligned





.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">
    <figure><table border="1" frame="hsides" rules="none" cellpadding="2"><tr>
    <td style="text-align:left">#</td>
    <td style="text-align:left">ascii</td>
    <td style="text-align:left">index</td>
    <td style="text-align:left">ascii_ds2</td>
    </tr>
    <tr>
    <td style="text-align:left">0</td>
    <td style="text-align:left">t</td>
    <td style="text-align:left">19</td>
    <td style="text-align:left">t</td>
    </tr>
    <tr>
    <td style="text-align:left">1</td>
    <td style="text-align:left">y</td>
    <td style="text-align:left">24</td>
    <td style="text-align:left">y</td>
    </tr>
    <tr>
    <td style="text-align:left">2</td>
    <td style="text-align:left">q</td>
    <td style="text-align:left">16</td>
    <td style="text-align:left">q</td>
    </tr>
    <tr>
    <td style="text-align:left">3</td>
    <td style="text-align:left">a</td>
    <td style="text-align:left">0</td>
    <td style="text-align:left">a</td>
    </tr>
    <tr>
    <td style="text-align:left">4</td>
    <td style="text-align:left">d</td>
    <td style="text-align:left">3</td>
    <td style="text-align:left">d</td>
    </tr>
    <tr>
    <td style="text-align:left">5</td>
    <td style="text-align:left">k</td>
    <td style="text-align:left">10</td>
    <td style="text-align:left">k</td>
    </tr>
    <tr>
    <td style="text-align:left">6</td>
    <td style="text-align:left">m</td>
    <td style="text-align:left">12</td>
    <td style="text-align:left">m</td>
    </tr>
    <tr>
    <td style="text-align:left">7</td>
    <td style="text-align:left">j</td>
    <td style="text-align:left">9</td>
    <td style="text-align:left">j</td>
    </tr>
    <tr>
    <td style="text-align:left">8</td>
    <td style="text-align:left">v</td>
    <td style="text-align:left">21</td>
    <td style="text-align:left">v</td>
    </tr></table></figure>
    </div>
    <br />
    <br />


.. _sphx_glr_download_auto_examples_datasets_align.py:

.. only:: html

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

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

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

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

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

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

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


.. only:: html

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

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