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

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

.. _sphx_glr_auto_examples_plot_search_space.py:


Search space graph
====================================
mloptimizer provides a function to plot the search space of the optimization.

.. GENERATED FROM PYTHON SOURCE LINES 6-17

.. code-block:: default


    from sklearn.tree import DecisionTreeClassifier
    from mloptimizer.application.reporting.plots import plotly_search_space
    import plotly
    import os
    from sklearn.datasets import load_iris
    from mloptimizer.interfaces import GeneticSearch
    from mloptimizer.domain.hyperspace import HyperparameterSpace, Hyperparam
    from sklearn.model_selection import StratifiedKFold









.. GENERATED FROM PYTHON SOURCE LINES 18-20

Load the iris dataset to obtain a vector of features X and a vector of labels y.
Another dataset or a custom one can be used

.. GENERATED FROM PYTHON SOURCE LINES 20-22

.. code-block:: default

    X, y = load_iris(return_X_y=True)








.. GENERATED FROM PYTHON SOURCE LINES 23-27

Define the HyperparameterSpace using the dictionary approach
-------------------------------------------------------------
This demonstrates the direct way to define hyperparameters as the library specifies.
Each Hyperparam defines: name, min_value, max_value, type, and optional scale.

.. GENERATED FROM PYTHON SOURCE LINES 27-36

.. code-block:: default

    fixed_hyperparams = {}
    evolvable_hyperparams = {
        'max_depth': Hyperparam('max_depth', 1, 20, 'int'),
        'min_samples_split': Hyperparam('min_samples_split', 2, 20, 'int'),
        'min_samples_leaf': Hyperparam('min_samples_leaf', 1, 20, 'int'),
        'max_features': Hyperparam('max_features', 10, 100, 'float', 100)
    }
    hyperparam_space = HyperparameterSpace(fixed_hyperparams, evolvable_hyperparams)








.. GENERATED FROM PYTHON SOURCE LINES 37-40

The GeneticSearch class is used to optimize the hyperparameters of a machine learning model.
Configure genetic algorithm parameters for reproducible results.
Note: Values reduced for faster documentation builds. For production, use larger values.

.. GENERATED FROM PYTHON SOURCE LINES 40-58

.. code-block:: default

    genetic_params = {
        'generations': 10,
        'population_size': 20,
        'n_elites': 2,
        'cxpb': 0.5,
        'mutpb': 0.8,
        'seed': 42
    }

    cv = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)
    opt = GeneticSearch(
        estimator_class=DecisionTreeClassifier,
        hyperparam_space=hyperparam_space,
        cv=cv,
        scoring='accuracy',
        **genetic_params
    )








.. GENERATED FROM PYTHON SOURCE LINES 59-60

To optimize the classifier we need to call the fit method.

.. GENERATED FROM PYTHON SOURCE LINES 60-64

.. code-block:: default

    opt.fit(X, y)
    clf = opt.best_estimator_









.. GENERATED FROM PYTHON SOURCE LINES 65-66

Following we can generate the plot of the search space

.. GENERATED FROM PYTHON SOURCE LINES 66-74

.. code-block:: default

    population_df = opt.populations_
    param_names = list(opt.get_evolvable_hyperparams().keys())
    param_names.append("fitness")
    df = population_df[param_names]
    g_search_space = plotly_search_space(df, param_names)
    g_search_space.update_layout(autosize=True, width=None, height=600)
    plotly.io.show(g_search_space, config={'responsive': True})




.. raw:: html
    :file: images/sphx_glr_plot_search_space_001.html





.. GENERATED FROM PYTHON SOURCE LINES 75-76

At the end of the evolution the graph is saved as an html at the path:

.. GENERATED FROM PYTHON SOURCE LINES 76-80

.. code-block:: default

    print(opt._optimizer_service.optimizer.tracker.graphics_path)
    print(os.listdir(opt._optimizer_service.optimizer.tracker.graphics_path))






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

 .. code-block:: none

    None
    ['plot_evolution.py', 'plot_mlp_neural_network.py', 'plot_hist_gradient_boosting.py', 'regression_example.py', 'plot_lightgbm_classifier.py', 'plot_xgboost_example.py', 'plot_catboost_example.py', 'plot_search_space.py', 'plot_xgboost_hyperparam_opt_comparison.py', 'plot_logistic_regression.py', 'plot_lightgbm_regressor.py', 'plot_quickstart.py', 'plot_linear_models.py', 'plot_adaboost.py', 'README.rst']




.. GENERATED FROM PYTHON SOURCE LINES 81-82

The data to generate the graph is available at the path:

.. GENERATED FROM PYTHON SOURCE LINES 82-86

.. code-block:: default

    print(opt._optimizer_service.optimizer.tracker.results_path)
    print(os.listdir(opt._optimizer_service.optimizer.tracker.results_path))

    del opt




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

 .. code-block:: none

    None
    ['plot_evolution.py', 'plot_mlp_neural_network.py', 'plot_hist_gradient_boosting.py', 'regression_example.py', 'plot_lightgbm_classifier.py', 'plot_xgboost_example.py', 'plot_catboost_example.py', 'plot_search_space.py', 'plot_xgboost_hyperparam_opt_comparison.py', 'plot_logistic_regression.py', 'plot_lightgbm_regressor.py', 'plot_quickstart.py', 'plot_linear_models.py', 'plot_adaboost.py', 'README.rst']





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

   **Total running time of the script:** (0 minutes 2.078 seconds)


.. _sphx_glr_download_auto_examples_plot_search_space.py:

.. only:: html

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




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

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

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

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


.. only:: html

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

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