.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "checks_gallery/tabular/methodology/plot_date_train_test_leakage_duplicates.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_date_train_test_leakage_duplicates.py>`
        to download the full example code

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

.. _sphx_glr_checks_gallery_tabular_methodology_plot_date_train_test_leakage_duplicates.py:


Date Train Validation Leakage Duplicates
****************************************

.. GENERATED FROM PYTHON SOURCE LINES 8-22

.. code-block:: default


    from datetime import datetime

    import pandas as pd

    from deepchecks.tabular import Dataset, Suite
    from deepchecks.tabular.checks.methodology import \
        DateTrainTestLeakageDuplicates


    def dataset_from_dict(d: dict, datetime_name: str = None) -> Dataset:
        dataframe = pd.DataFrame(data=d)
        return Dataset(dataframe, datetime_name=datetime_name)








.. GENERATED FROM PYTHON SOURCE LINES 23-25

Synthetic example with date leakage
===================================

.. GENERATED FROM PYTHON SOURCE LINES 25-58

.. code-block:: default


    train_ds = dataset_from_dict({'col1': [
            datetime(2021, 10, 1, 0, 0),
            datetime(2021, 10, 1, 0, 0),
            datetime(2021, 10, 1, 0, 0),
            datetime(2021, 10, 2, 0, 0),
            datetime(2021, 10, 2, 0, 0),
            datetime(2021, 10, 2, 0, 0),
            datetime(2021, 10, 3, 0, 0),
            datetime(2021, 10, 3, 0, 0),
            datetime(2021, 10, 3, 0, 0),
            datetime(2021, 10, 4, 0, 0),
            datetime(2021, 10, 4, 0, 0),
            datetime(2021, 10, 4, 0, 0),
            datetime(2021, 10, 5, 0, 0),
            datetime(2021, 10, 5, 0, 0)
        ]}, 'col1')
    test_ds = dataset_from_dict({'col1': [
            datetime(2021, 9, 4, 0, 0),
            datetime(2021, 10, 4, 0, 0),
            datetime(2021, 10, 5, 0, 0),
            datetime(2021, 10, 6, 0, 0),
            datetime(2021, 10, 6, 0, 0),
            datetime(2021, 10, 7, 0, 0),
            datetime(2021, 10, 7, 0, 0),
            datetime(2021, 10, 8, 0, 0),
            datetime(2021, 10, 8, 0, 0),
            datetime(2021, 10, 9, 0, 0),
            datetime(2021, 10, 9, 0, 0)
        ]}, 'col1')

    DateTrainTestLeakageDuplicates(n_to_show=3).run(train_dataset=train_ds, test_dataset=test_ds)






.. 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>Date Train-Test Leakage (duplicates)</b></h4><p>Check if test dates are present in train data.</p><h5><b>Additional Outputs</b></h5><div>18.18% of test data dates appear in training data</div><style type="text/css">
    #T_a2474 table {
      text-align: left;
      white-space: pre-wrap;
    }
    #T_a2474 thead {
      text-align: left;
      white-space: pre-wrap;
    }
    #T_a2474 tbody {
      text-align: left;
      white-space: pre-wrap;
    }
    #T_a2474 th {
      text-align: left;
      white-space: pre-wrap;
    }
    #T_a2474 td {
      text-align: left;
      white-space: pre-wrap;
    }
    </style>
    <table id="T_a2474">
      <thead>
        <tr>
          <th class="blank level0" >&nbsp;</th>
          <th id="T_a2474_level0_col0" class="col_heading level0 col0" >0</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th id="T_a2474_level0_row0" class="row_heading level0 row0" >Sample of test dates in train:</th>
          <td id="T_a2474_row0_col0" class="data row0 col0" >['2021/10/05 00:00:00.000000 ', '2021/10/04 00:00:00.000000 ']</td>
        </tr>
      </tbody>
    </table>

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

.. GENERATED FROM PYTHON SOURCE LINES 59-61

Synthetic example no date leakage
=================================

.. GENERATED FROM PYTHON SOURCE LINES 61-80

.. code-block:: default


    train_ds = dataset_from_dict({'col1': [
            datetime(2021, 10, 3, 0, 0),
            datetime(2021, 10, 3, 0, 0),
            datetime(2021, 10, 4, 0, 0),
            datetime(2021, 10, 4, 0, 0),
            datetime(2021, 10, 4, 0, 0),
            datetime(2021, 10, 5, 0, 0),
            datetime(2021, 10, 5, 0, 0)
        ]}, 'col1')
    test_ds = dataset_from_dict({'col1': [
            datetime(2021, 11, 4, 0, 0),
            datetime(2021, 11, 4, 0, 0),
            datetime(2021, 11, 5, 0, 0),
            datetime(2021, 11, 6, 0, 0),

        ]}, 'col1')

    DateTrainTestLeakageDuplicates().run(train_dataset=train_ds, test_dataset=test_ds)





.. 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>Date Train-Test Leakage (duplicates)</b></h4><p>Check if test dates are present in train data.</p><h5><b>Additional Outputs</b></h5><p><b>&#x2713;</b>Nothing to display</p>
    </div>
    <br />
    <br />


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

   **Total running time of the script:** ( 0 minutes  0.013 seconds)


.. _sphx_glr_download_checks_gallery_tabular_methodology_plot_date_train_test_leakage_duplicates.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_date_train_test_leakage_duplicates.py <plot_date_train_test_leakage_duplicates.py>`



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

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


.. only:: html

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

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