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

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

.. _sphx_glr_auto_examples_technical_details_plot_skore_hub_project.py:


.. _example_skore_hub_project:

=================
Hub skore Project
=================

This example shows how to use :class:`~skore.Project` in **hub** mode: store
reports remotely and inspect them. A key point is that
:meth:`~skore.Project.summarize` returns a :class:`~skore.project._summary.Summary`,
which is a :class:`pandas.DataFrame`. In Jupyter you get an interactive widget, but
you can always inspect and filter the summary as a DataFrame if you prefer.

Examples
--------

To run this example and push in your own Skore Hub workspace and project, you can run
this example with the following command:

.. code-block:: bash

    WORKSPACE=<workspace> PROJECT=<project> python plot_skore_hub_project.py

In this gallery, we are going to push the different reports into a public
workspace.

.. GENERATED FROM PYTHON SOURCE LINES 27-34

.. code-block:: Python



    from skore import login

    login()






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

 .. code-block:: none

    ╭───────────────────────────────── Login to Skore Hub ─────────────────────────────────╮
    │                                                                                      │
    │                        Successfully logged in, using API key.                        │
    │                                                                                      │
    ╰──────────────────────────────────────────────────────────────────────────────────────╯




.. GENERATED FROM PYTHON SOURCE LINES 69-78

.. code-block:: Python

    from sklearn.datasets import load_breast_cancer
    from sklearn.linear_model import LogisticRegression
    from skore import train_test_split
    from skrub import tabular_pipeline

    X, y = load_breast_cancer(return_X_y=True, as_frame=True)
    split_data = train_test_split(X=X, y=y, random_state=42, as_dict=True)
    estimator = tabular_pipeline(LogisticRegression(max_iter=1_000))





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

 .. code-block:: none

    ╭────────────────────── HighClassImbalanceTooFewExamplesWarning ───────────────────────╮
    │ It seems that you have a classification problem with at least one class with fewer   │
    │ than 100 examples in the test set. In this case, using train_test_split may not be a │
    │ good idea because of high variability in the scores obtained on the test set. We     │
    │ suggest three options to tackle this challenge: you can increase test_size, collect  │
    │ more data, or use skore's CrossValidationReport with the `splitter` parameter of     │
    │ your choice.                                                                         │
    ╰──────────────────────────────────────────────────────────────────────────────────────╯
    ╭───────────────────────────────── ShuffleTrueWarning ─────────────────────────────────╮
    │ We detected that the `shuffle` parameter is set to `True` either explicitly or from  │
    │ its default value. In case of time-ordered events (even if they are independent),    │
    │ this will result in inflated model performance evaluation because natural drift will │
    │ not be taken into account. We recommend setting the shuffle parameter to `False` in  │
    │ order to ensure the evaluation process is really representative of your production   │
    │ release process.                                                                     │
    ╰──────────────────────────────────────────────────────────────────────────────────────╯




.. GENERATED FROM PYTHON SOURCE LINES 79-95

.. code-block:: Python

    from numpy import logspace
    from sklearn.base import clone
    from skore import EstimatorReport, Project

    project = Project(f"{WORKSPACE}/{PROJECT}", mode="hub")

    for regularization in logspace(-3, 3, 5):
        project.put(
            f"lr-regularization-{regularization:.1e}",
            EstimatorReport(
                clone(estimator).set_params(logisticregression__C=regularization),
                **split_data,
                pos_label=1,
            ),
        )





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

 .. code-block:: none



      Putting lr-regularization-1.0e-03 0:00:38
    Consult your report at 
    https://skore.probabl.ai/skore/example-skore-hub-project-dev/estimators/1448


      Putting lr-regularization-3.2e-02 0:00:36
    Consult your report at 
    https://skore.probabl.ai/skore/example-skore-hub-project-dev/estimators/1449


      Putting lr-regularization-1.0e+00 0:00:37
    Consult your report at 
    https://skore.probabl.ai/skore/example-skore-hub-project-dev/estimators/1450


      Putting lr-regularization-3.2e+01 0:00:35
    Consult your report at 
    https://skore.probabl.ai/skore/example-skore-hub-project-dev/estimators/1451


      Putting lr-regularization-1.0e+03 0:00:36
    Consult your report at 
    https://skore.probabl.ai/skore/example-skore-hub-project-dev/estimators/1452




.. GENERATED FROM PYTHON SOURCE LINES 96-102

Summarize: you get a DataFrame
==============================

:meth:`~skore.Project.summarize` returns a :class:`~skore.project._summary.Summary`,
which subclasses :class:`pandas.DataFrame`. In a Jupyter environment it renders
an interactive parallel-coordinates widget by default.

.. GENERATED FROM PYTHON SOURCE LINES 102-104

.. code-block:: Python

    summary = project.summarize()








.. GENERATED FROM PYTHON SOURCE LINES 105-107

To see the normal DataFrame table instead of the widget (e.g. in scripts or
when you prefer the table), wrap the summary in :class:`pandas.DataFrame`:

.. GENERATED FROM PYTHON SOURCE LINES 107-112

.. code-block:: Python

    import pandas as pd

    pandas_summary = pd.DataFrame(summary)
    pandas_summary






.. 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>key</th>
          <th>date</th>
          <th>learner</th>
          <th>ml_task</th>
          <th>report_type</th>
          <th>dataset</th>
          <th>rmse</th>
          <th>log_loss</th>
          <th>roc_auc</th>
          <th>fit_time</th>
          <th>predict_time</th>
          <th>rmse_mean</th>
          <th>log_loss_mean</th>
          <th>roc_auc_mean</th>
          <th>fit_time_mean</th>
          <th>predict_time_mean</th>
        </tr>
        <tr>
          <th></th>
          <th>id</th>
          <th></th>
          <th></th>
          <th></th>
          <th></th>
          <th></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>
          <th>skore:report:estimator:1448</th>
          <td>lr-regularization-1.0e-03</td>
          <td>2026-03-12T17:29:05.051852+00:00</td>
          <td>LogisticRegression</td>
          <td>binary-classification</td>
          <td>estimator</td>
          <td>0966e6e4b6a8c8bd5b0e6bd95f36939d</td>
          <td>None</td>
          <td>0.388992</td>
          <td>0.995214</td>
          <td>0.134774</td>
          <td>0.080897</td>
          <td>None</td>
          <td>None</td>
          <td>None</td>
          <td>None</td>
          <td>None</td>
        </tr>
        <tr>
          <th>1</th>
          <th>skore:report:estimator:1449</th>
          <td>lr-regularization-3.2e-02</td>
          <td>2026-03-12T17:29:42.214998+00:00</td>
          <td>LogisticRegression</td>
          <td>binary-classification</td>
          <td>estimator</td>
          <td>0966e6e4b6a8c8bd5b0e6bd95f36939d</td>
          <td>None</td>
          <td>0.114416</td>
          <td>0.998752</td>
          <td>0.287037</td>
          <td>0.044496</td>
          <td>None</td>
          <td>None</td>
          <td>None</td>
          <td>None</td>
          <td>None</td>
        </tr>
        <tr>
          <th>2</th>
          <th>skore:report:estimator:1450</th>
          <td>lr-regularization-1.0e+00</td>
          <td>2026-03-12T17:30:19.698017+00:00</td>
          <td>LogisticRegression</td>
          <td>binary-classification</td>
          <td>estimator</td>
          <td>0966e6e4b6a8c8bd5b0e6bd95f36939d</td>
          <td>None</td>
          <td>0.054072</td>
          <td>0.997919</td>
          <td>0.081626</td>
          <td>0.052578</td>
          <td>None</td>
          <td>None</td>
          <td>None</td>
          <td>None</td>
          <td>None</td>
        </tr>
        <tr>
          <th>3</th>
          <th>skore:report:estimator:1451</th>
          <td>lr-regularization-3.2e+01</td>
          <td>2026-03-12T17:30:55.592403+00:00</td>
          <td>LogisticRegression</td>
          <td>binary-classification</td>
          <td>estimator</td>
          <td>0966e6e4b6a8c8bd5b0e6bd95f36939d</td>
          <td>None</td>
          <td>0.084849</td>
          <td>0.996255</td>
          <td>0.074412</td>
          <td>0.042013</td>
          <td>None</td>
          <td>None</td>
          <td>None</td>
          <td>None</td>
          <td>None</td>
        </tr>
        <tr>
          <th>4</th>
          <th>skore:report:estimator:1452</th>
          <td>lr-regularization-1.0e+03</td>
          <td>2026-03-12T17:31:31.819065+00:00</td>
          <td>LogisticRegression</td>
          <td>binary-classification</td>
          <td>estimator</td>
          <td>0966e6e4b6a8c8bd5b0e6bd95f36939d</td>
          <td>None</td>
          <td>0.584540</td>
          <td>0.988140</td>
          <td>0.077690</td>
          <td>0.040308</td>
          <td>None</td>
          <td>None</td>
          <td>None</td>
          <td>None</td>
          <td>None</td>
        </tr>
      </tbody>
    </table>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 113-115

Basically, our summary contains metadata related to various information that we need
to quickly help filtering the reports.

.. GENERATED FROM PYTHON SOURCE LINES 115-117

.. code-block:: Python

    summary.info()





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

 .. code-block:: none

    <class 'skore._project._summary.Summary'>
    MultiIndex: 5 entries, (0, 'skore:report:estimator:1448') to (4, 'skore:report:estimator:1452')
    Data columns (total 16 columns):
     #   Column             Non-Null Count  Dtype   
    ---  ------             --------------  -----   
     0   key                5 non-null      object  
     1   date               5 non-null      object  
     2   learner            5 non-null      category
     3   ml_task            5 non-null      object  
     4   report_type        5 non-null      object  
     5   dataset            5 non-null      object  
     6   rmse               0 non-null      object  
     7   log_loss           5 non-null      float64 
     8   roc_auc            5 non-null      float64 
     9   fit_time           5 non-null      float64 
     10  predict_time       5 non-null      float64 
     11  rmse_mean          0 non-null      object  
     12  log_loss_mean      0 non-null      object  
     13  roc_auc_mean       0 non-null      object  
     14  fit_time_mean      0 non-null      object  
     15  predict_time_mean  0 non-null      object  
    dtypes: category(1), float64(4), object(11)
    memory usage: 1.1+ KB




.. GENERATED FROM PYTHON SOURCE LINES 118-120

Filter reports by metric (e.g. keep only those above a given accuracy) and
work with the result as a table.

.. GENERATED FROM PYTHON SOURCE LINES 120-122

.. code-block:: Python

    summary.query("log_loss < 0.1")["key"].tolist()





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

 .. code-block:: none


    ['lr-regularization-1.0e+00', 'lr-regularization-3.2e+01']



.. GENERATED FROM PYTHON SOURCE LINES 123-125

Use :meth:`~skore.project._summary.Summary.reports` to load the corresponding
reports from the project (optionally after filtering the summary).

.. GENERATED FROM PYTHON SOURCE LINES 125-128

.. code-block:: Python

    reports = summary.query("log_loss < 0.1").reports(return_as="comparison")
    len(reports.reports_)





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

 .. code-block:: none


    2



.. GENERATED FROM PYTHON SOURCE LINES 129-131

Since we got a :class:`~skore.ComparisonReport`, we can use the metrics accessor
to summarize the metrics across the reports.

.. GENERATED FROM PYTHON SOURCE LINES 131-133

.. code-block:: Python

    reports.metrics.summarize().frame()






.. 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>Estimator</th>
          <th>LogisticRegression_1</th>
          <th>LogisticRegression_2</th>
        </tr>
        <tr>
          <th>Metric</th>
          <th></th>
          <th></th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>Accuracy</th>
          <td>0.993007</td>
          <td>0.965035</td>
        </tr>
        <tr>
          <th>Precision</th>
          <td>0.988889</td>
          <td>0.988372</td>
        </tr>
        <tr>
          <th>Recall</th>
          <td>1.000000</td>
          <td>0.955056</td>
        </tr>
        <tr>
          <th>ROC AUC</th>
          <td>0.997919</td>
          <td>0.996255</td>
        </tr>
        <tr>
          <th>Brier score</th>
          <td>0.013810</td>
          <td>0.023881</td>
        </tr>
        <tr>
          <th>Fit time (s)</th>
          <td>0.081626</td>
          <td>0.074412</td>
        </tr>
        <tr>
          <th>Predict time (s)</th>
          <td>0.040488</td>
          <td>0.039703</td>
        </tr>
      </tbody>
    </table>
    </div>
    </div>
    <br />
    <br />

.. GENERATED FROM PYTHON SOURCE LINES 134-135

.. code-block:: Python

    reports.metrics.roc().plot(subplot_by=None)



.. image-sg:: /auto_examples/technical_details/images/sphx_glr_plot_skore_hub_project_001.png
   :alt: ROC Curve Positive label: 1 Data source: Test set
   :srcset: /auto_examples/technical_details/images/sphx_glr_plot_skore_hub_project_001.png
   :class: sphx-glr-single-img






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

   **Total running time of the script:** (3 minutes 14.090 seconds)


.. _sphx_glr_download_auto_examples_technical_details_plot_skore_hub_project.py:

.. only:: html

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

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

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

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

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

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

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


.. only:: html

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

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