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

.. only:: html

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

        Click :ref:`here <sphx_glr_download_checks_gallery_tabular_methodology_plot_datasets_size_comparison.py>`
        to download the full example code

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

.. _sphx_glr_checks_gallery_tabular_methodology_plot_datasets_size_comparison.py:


Datasets Size Comparison
************************

.. GENERATED FROM PYTHON SOURCE LINES 8-16

.. code-block:: default


    import numpy as np
    import pandas as pd
    from sklearn.model_selection import train_test_split

    from deepchecks.tabular import Dataset
    from deepchecks.tabular.checks.methodology import DatasetsSizeComparison








.. GENERATED FROM PYTHON SOURCE LINES 17-32

.. code-block:: default


    df = pd.DataFrame(np.random.randn(1000, 3), columns=['x1', 'x2', 'x3'])
    df['label'] = df['x2'] + 0.1 * df['x1']

    train, test = train_test_split(df, test_size=0.4)
    train = Dataset(train, features=['x1', 'x2', 'x3'], label='label')
    test = Dataset(test, features=['x1', 'x2', 'x3'], label='label')

    check_instance = (
        DatasetsSizeComparison()
        .add_condition_train_dataset_not_smaller_than_test()
        .add_condition_test_size_not_smaller_than(100)
        .add_condition_test_train_size_ratio_not_smaller_than(0.2)
    )








.. GENERATED FROM PYTHON SOURCE LINES 33-35

.. code-block:: default


    check_instance.run(train, test)





.. raw:: html

    <div class="output_subarea output_html rendered_html output_result">

    <script
        src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.6/require.min.js"
        integrity="sha512-c3Nl8+7g4LMSTdrm621y7kf9v3SDPnhxLNhcjFJbKECVnmZHTdo+IRO05sNLTH/D3vA6u1X32ehoLC7WFVdheg=="
        crossorigin="anonymous"
        referrerpolicy="no-referrer">
    </script>

    <script type="text/javascript">window.PlotlyConfig = {MathJaxConfig: 'local'};</script>
    <script type="text/javascript">if (window.MathJax) {MathJax.Hub.Config({SVG: {font: "STIX-Web"}});}</script>
    <script type="text/javascript">
        if (typeof require !== 'undefined') {
            require.undef("plotly");
            requirejs.config({
                paths: {'plotly': ['https://cdn.plot.ly/plotly-2.8.3.min']}
            });
            require(
                ['plotly'],
                function(Plotly) {
                    window._Plotly = Plotly;
                    window.Plotly = Plotly;
                    console.log('Loaded plotly successfully');
                },
                function() {console.log('Failed to load plotly')}
            );
        } else {
            console.log('requirejs is not present');
        }
    </script>
    <h4><b>Datasets Size Comparison</b></h4><p>Verify test dataset size comparing it to the train dataset size.</p><h5><b>Conditions Summary</b></h5><style type="text/css">
    #T_a92b8 table {
      text-align: left;
      white-space: pre-wrap;
    }
    #T_a92b8 thead {
      text-align: left;
      white-space: pre-wrap;
    }
    #T_a92b8 tbody {
      text-align: left;
      white-space: pre-wrap;
    }
    #T_a92b8 th {
      text-align: left;
      white-space: pre-wrap;
    }
    #T_a92b8 td {
      text-align: left;
      white-space: pre-wrap;
    }
    </style>
    <table id="T_a92b8">
      <thead>
        <tr>
          <th id="T_a92b8_level0_col0" class="col_heading level0 col0" >Status</th>
          <th id="T_a92b8_level0_col1" class="col_heading level0 col1" >Condition</th>
          <th id="T_a92b8_level0_col2" class="col_heading level0 col2" >More Info</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <td id="T_a92b8_row0_col0" class="data row0 col0" ><div style="color: green;text-align: center">✓</div></td>
          <td id="T_a92b8_row0_col1" class="data row0 col1" >Train dataset is not smaller than test dataset</td>
          <td id="T_a92b8_row0_col2" class="data row0 col2" ></td>
        </tr>
        <tr>
          <td id="T_a92b8_row1_col0" class="data row1 col0" ><div style="color: green;text-align: center">✓</div></td>
          <td id="T_a92b8_row1_col1" class="data row1 col1" >Test dataset size is not smaller than 100</td>
          <td id="T_a92b8_row1_col2" class="data row1 col2" ></td>
        </tr>
        <tr>
          <td id="T_a92b8_row2_col0" class="data row2 col0" ><div style="color: green;text-align: center">✓</div></td>
          <td id="T_a92b8_row2_col1" class="data row2 col1" >Test-Train size ratio is not smaller than 0.2</td>
          <td id="T_a92b8_row2_col2" class="data row2 col2" ></td>
        </tr>
      </tbody>
    </table>
    <h5><b>Additional Outputs</b></h5><style type="text/css">
    #T_463ac table {
      text-align: left;
      white-space: pre-wrap;
    }
    #T_463ac thead {
      text-align: left;
      white-space: pre-wrap;
    }
    #T_463ac tbody {
      text-align: left;
      white-space: pre-wrap;
    }
    #T_463ac th {
      text-align: left;
      white-space: pre-wrap;
    }
    #T_463ac td {
      text-align: left;
      white-space: pre-wrap;
    }
    </style>
    <table id="T_463ac">
      <thead>
        <tr>
          <th class="blank level0" >&nbsp;</th>
          <th id="T_463ac_level0_col0" class="col_heading level0 col0" >Train</th>
          <th id="T_463ac_level0_col1" class="col_heading level0 col1" >Test</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th id="T_463ac_level0_row0" class="row_heading level0 row0" >Size</th>
          <td id="T_463ac_row0_col0" class="data row0 col0" >600</td>
          <td id="T_463ac_row0_col1" class="data row0 col1" >400</td>
        </tr>
      </tbody>
    </table>

    </div>
    <br />
    <br />


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

   **Total running time of the script:** ( 0 minutes  0.015 seconds)


.. _sphx_glr_download_checks_gallery_tabular_methodology_plot_datasets_size_comparison.py:


.. only :: html

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



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

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



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

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


.. only:: html

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

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