.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/release_highlights/plot_release_highlights_1_3_0.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_release_highlights_plot_release_highlights_1_3_0.py>`
        to download the full example code. or to run this example in your browser via Binder

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

.. _sphx_glr_auto_examples_release_highlights_plot_release_highlights_1_3_0.py:


=======================================
scikit-learn 1.3 版本发布亮点
=======================================

.. currentmodule:: sklearn

我们很高兴地宣布发布 scikit-learn 1.3！此次更新包含了许多错误修复和改进，以及一些新的关键功能。以下是本次发布的一些主要功能。 **有关所有更改的详尽列表** ，请参阅 :ref:`发布说明 <release_notes_1_3>` 。

要安装最新版本（使用 pip）::

    pip install --upgrade scikit-learn

或使用 conda::

    conda install -c conda-forge scikit-learn

.. GENERATED FROM PYTHON SOURCE LINES 22-27

元数据路由
----------------
我们正在引入一种新的方式来路由诸如 ``sample_weight`` 之类的元数据，这将影响到诸如:class:`pipeline.Pipeline` 和:class:`model_selection.GridSearchCV` 等元估计器的元数据路由方式。虽然此功能的基础设施已经包含在本次发布中，但工作仍在进行中，并非所有元估计器都支持此新功能。您可以在:ref:`元数据路由用户指南<metadata_routing>` 中阅读更多关于此功能的信息。请注意，此功能仍在开发中，并未在大多数元估计器中实现。

第三方开发者已经可以开始将其整合到他们的元估计器中。更多详情，请参见：:ref:`元数据路由开发者指南<sphx_glr_auto_examples_miscellaneous_plot_metadata_routing.py>` 。

.. GENERATED FROM PYTHON SOURCE LINES 29-34

HDBSCAN：基于密度的层次聚类
----------------------------------------------
最初托管在 scikit-learn-contrib 仓库中，:class:`cluster.HDBSCAN` 已被纳入 scikit-learn。它缺少原始实现中的一些功能，这些功能将在未来的版本中添加。
通过同时对多个 epsilon 值执行修改版的 :class:`cluster.DBSCAN` ，:class:`cluster.HDBSCAN` 可以找到不同密度的聚类，使其比 :class:`cluster.DBSCAN` 更加稳健，参数选择更加灵活。
更多详情请参见 :ref:`用户指南 <hdbscan>` 。

.. GENERATED FROM PYTHON SOURCE LINES 34-49

.. code-block:: Python


    import numpy as np
    from sklearn.cluster import HDBSCAN
    from sklearn.datasets import load_digits
    from sklearn.metrics import v_measure_score

    X, true_labels = load_digits(return_X_y=True)
    print(f"number of digits: {len(np.unique(true_labels))}")

    hdbscan = HDBSCAN(min_cluster_size=15).fit(X)
    non_noisy_labels = hdbscan.labels_[hdbscan.labels_ != -1]
    print(f"number of clusters found: {len(np.unique(non_noisy_labels))}")

    print(v_measure_score(true_labels[hdbscan.labels_ != -1], non_noisy_labels))





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

 .. code-block:: none

    number of digits: 10
    number of clusters found: 10
    0.9751818034688537




.. GENERATED FROM PYTHON SOURCE LINES 50-54

目标编码器：一种新的类别编码策略
-----------------------------------------------
非常适合具有高基数的类别特征，:class:`preprocessing.TargetEncoder` 基于属于该类别的观测值的平均目标值的缩减估计对类别进行编码。
更多详情请参见 :ref:`用户指南 <target_encoder>` 。

.. GENERATED FROM PYTHON SOURCE LINES 54-66

.. code-block:: Python


    import numpy as np
    from sklearn.preprocessing import TargetEncoder

    X = np.array([["cat"] * 30 + ["dog"] * 20 + ["snake"] * 38], dtype=object).T
    y = [90.3] * 30 + [20.4] * 20 + [21.2] * 38

    enc = TargetEncoder(random_state=0)
    X_trans = enc.fit_transform(X, y)

    enc.encodings_





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

 .. code-block:: none


    [array([90.3, 20.4, 21.2])]



.. GENERATED FROM PYTHON SOURCE LINES 67-71

决策树中的缺失值支持
----------------------------------------
类 :class:`tree.DecisionTreeClassifier` 和 :class:`tree.DecisionTreeRegressor` 现在支持缺失值。对于非缺失数据的每个潜在阈值，分割器将评估将所有缺失值分配到左节点或右节点的分割情况。
请参阅 :ref:`用户指南 <tree_missing_value_support>` 了解更多详细信息，或参阅 :ref:`sphx_glr_auto_examples_ensemble_plot_hgbt_regression.py` 了解 :class:`~ensemble.HistGradientBoostingRegressor` 中此功能的用例示例。

.. GENERATED FROM PYTHON SOURCE LINES 71-81

.. code-block:: Python


    import numpy as np
    from sklearn.tree import DecisionTreeClassifier

    X = np.array([0, 1, 6, np.nan]).reshape(-1, 1)
    y = [0, 0, 1, 1]

    tree = DecisionTreeClassifier(random_state=0).fit(X, y)
    tree.predict(X)





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

 .. code-block:: none


    array([0, 0, 1, 1])



.. GENERATED FROM PYTHON SOURCE LINES 82-85

新显示 :class:`~model_selection.ValidationCurveDisplay` 
------------------------------------------------------------
:class:`model_selection.ValidationCurveDisplay` 现在可以用于绘制 :func:`model_selection.validation_curve` 的结果。

.. GENERATED FROM PYTHON SOURCE LINES 85-102

.. code-block:: Python


    from sklearn.datasets import make_classification
    from sklearn.linear_model import LogisticRegression
    from sklearn.model_selection import ValidationCurveDisplay

    X, y = make_classification(1000, 10, random_state=0)

    _ = ValidationCurveDisplay.from_estimator(
        LogisticRegression(),
        X,
        y,
        param_name="C",
        param_range=np.geomspace(1e-5, 1e3, num=9),
        score_type="both",
        score_name="Accuracy",
    )




.. image-sg:: /auto_examples/release_highlights/images/sphx_glr_plot_release_highlights_1_3_0_001.png
   :alt: plot release highlights 1 3 0
   :srcset: /auto_examples/release_highlights/images/sphx_glr_plot_release_highlights_1_3_0_001.png
   :class: sphx-glr-single-img





.. GENERATED FROM PYTHON SOURCE LINES 103-106

梯度提升的伽马损失
------------------
类 :class:`ensemble.HistGradientBoostingRegressor` 支持通过 `loss="gamma"` 使用伽马偏差损失函数。该损失函数对于建模具有右偏分布的严格正目标非常有用。

.. GENERATED FROM PYTHON SOURCE LINES 106-119

.. code-block:: Python

    import numpy as np
    from sklearn.model_selection import cross_val_score
    from sklearn.datasets import make_low_rank_matrix
    from sklearn.ensemble import HistGradientBoostingRegressor

    n_samples, n_features = 500, 10
    rng = np.random.RandomState(0)
    X = make_low_rank_matrix(n_samples, n_features, random_state=rng)
    coef = rng.uniform(low=-10, high=20, size=n_features)
    y = rng.gamma(shape=2, scale=np.exp(X @ coef) / 2)
    gbdt = HistGradientBoostingRegressor(loss="gamma")
    cross_val_score(gbdt, X, y).mean()





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

 .. code-block:: none


    np.float64(0.4685851328722167)



.. GENERATED FROM PYTHON SOURCE LINES 120-124

将不常见类别分组到 :class:`~preprocessing.OrdinalEncoder` 
--------------------------------------------------------------
与 :class:`preprocessing.OneHotEncoder` 类似，:class:`preprocessing.OrdinalEncoder` 类现在支持将不常见类别聚合到每个特征的单一输出中。启用不常见类别聚合的参数是 `min_frequency` 和 `max_categories` 。
有关更多详细信息，请参阅 :ref:`用户指南 <encoder_infrequent_categories>` 。

.. GENERATED FROM PYTHON SOURCE LINES 124-133

.. code-block:: Python


    from sklearn.preprocessing import OrdinalEncoder
    import numpy as np

    X = np.array(
        [["dog"] * 5 + ["cat"] * 20 + ["rabbit"] * 10 + ["snake"] * 3], dtype=object
    ).T
    enc = OrdinalEncoder(min_frequency=6).fit(X)
    enc.infrequent_categories_




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

 .. code-block:: none


    [array(['dog', 'snake'], dtype=object)]




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

   **Total running time of the script:** (0 minutes 2.112 seconds)


.. _sphx_glr_download_auto_examples_release_highlights_plot_release_highlights_1_3_0.py:

.. only:: html

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

    .. container:: binder-badge

      .. image:: images/binder_badge_logo.svg
        :target: https://mybinder.org/v2/gh/scikit-learn/scikit-learn/main?urlpath=lab/tree/notebooks/auto_examples/release_highlights/plot_release_highlights_1_3_0.ipynb
        :alt: Launch binder
        :width: 150 px

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

      :download:`Download Jupyter notebook: plot_release_highlights_1_3_0.ipynb <plot_release_highlights_1_3_0.ipynb>`

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

      :download:`Download Python source code: plot_release_highlights_1_3_0.py <plot_release_highlights_1_3_0.py>`

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

      :download:`Download zipped: plot_release_highlights_1_3_0.zip <plot_release_highlights_1_3_0.zip>`


.. include:: plot_release_highlights_1_3_0.recommendations


.. only:: html

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

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