.. only:: html
.. note::
:class: sphx-glr-download-link-note
Click :ref:`here ` 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_0_22_0.py:
========================================
Release Highlights for scikit-learn 0.22
========================================
.. currentmodule:: sklearn
We are pleased to announce the release of scikit-learn 0.22, which comes
with many bug fixes and new features! We detail below a few of the major
features of this release. For an exhaustive list of all the changes, please
refer to the :ref:`release notes `.
To install the latest version (with pip)::
pip install --upgrade scikit-learn
or with conda::
conda install scikit-learn
New plotting API
----------------
A new plotting API is available for creating visualizations. This new API
allows for quickly adjusting the visuals of a plot without involving any
recomputation. It is also possible to add different plots to the same
figure. The following example illustrates :class:`~metrics.plot_roc_curve`,
but other plots utilities are supported like
:class:`~inspection.plot_partial_dependence`,
:class:`~metrics.plot_precision_recall_curve`, and
:class:`~metrics.plot_confusion_matrix`. Read more about this new API in the
:ref:`User Guide `.
.. code-block:: default
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.metrics import plot_roc_curve
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import make_classification
import matplotlib.pyplot as plt
X, y = make_classification(random_state=0)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
svc = SVC(random_state=42)
svc.fit(X_train, y_train)
rfc = RandomForestClassifier(random_state=42)
rfc.fit(X_train, y_train)
svc_disp = plot_roc_curve(svc, X_test, y_test)
rfc_disp = plot_roc_curve(rfc, X_test, y_test, ax=svc_disp.ax_)
rfc_disp.figure_.suptitle("ROC curve comparison")
plt.show()
.. image:: /auto_examples/release_highlights/images/sphx_glr_plot_release_highlights_0_22_0_001.png
:alt: ROC curve comparison
:class: sphx-glr-single-img
Stacking Classifier and Regressor
---------------------------------
:class:`~ensemble.StackingClassifier` and
:class:`~ensemble.StackingRegressor`
allow you to have a stack of estimators with a final classifier or
a regressor.
Stacked generalization consists in stacking the output of individual
estimators and use a classifier to compute the final prediction. Stacking
allows to use the strength of each individual estimator by using their output
as input of a final estimator.
Base estimators are fitted on the full ``X`` while
the final estimator is trained using cross-validated predictions of the
base estimators using ``cross_val_predict``.
Read more in the :ref:`User Guide `.
.. code-block:: default
from sklearn.datasets import load_iris
from sklearn.svm import LinearSVC
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import make_pipeline
from sklearn.ensemble import StackingClassifier
from sklearn.model_selection import train_test_split
X, y = load_iris(return_X_y=True)
estimators = [
('rf', RandomForestClassifier(n_estimators=10, random_state=42)),
('svr', make_pipeline(StandardScaler(),
LinearSVC(random_state=42)))
]
clf = StackingClassifier(
estimators=estimators, final_estimator=LogisticRegression()
)
X_train, X_test, y_train, y_test = train_test_split(
X, y, stratify=y, random_state=42
)
clf.fit(X_train, y_train).score(X_test, y_test)
.. rst-class:: sphx-glr-script-out
Out:
.. code-block:: none
0.9473684210526315
Permutation-based feature importance
------------------------------------
The :func:`inspection.permutation_importance` can be used to get an
estimate of the importance of each feature, for any fitted estimator:
.. code-block:: default
from sklearn.ensemble import RandomForestClassifier
from sklearn.inspection import permutation_importance
X, y = make_classification(random_state=0, n_features=5, n_informative=3)
rf = RandomForestClassifier(random_state=0).fit(X, y)
result = permutation_importance(rf, X, y, n_repeats=10, random_state=0,
n_jobs=-1)
fig, ax = plt.subplots()
sorted_idx = result.importances_mean.argsort()
ax.boxplot(result.importances[sorted_idx].T,
vert=False, labels=range(X.shape[1]))
ax.set_title("Permutation Importance of each feature")
ax.set_ylabel("Features")
fig.tight_layout()
plt.show()
.. image:: /auto_examples/release_highlights/images/sphx_glr_plot_release_highlights_0_22_0_002.png
:alt: Permutation Importance of each feature
:class: sphx-glr-single-img
Native support for missing values for gradient boosting
-------------------------------------------------------
The :class:`ensemble.HistGradientBoostingClassifier`
and :class:`ensemble.HistGradientBoostingRegressor` now have native
support for missing values (NaNs). This means that there is no need for
imputing data when training or predicting.
.. code-block:: default
from sklearn.experimental import enable_hist_gradient_boosting # noqa
from sklearn.ensemble import HistGradientBoostingClassifier
import numpy as np
X = np.array([0, 1, 2, np.nan]).reshape(-1, 1)
y = [0, 0, 1, 1]
gbdt = HistGradientBoostingClassifier(min_samples_leaf=1).fit(X, y)
print(gbdt.predict(X))
.. rst-class:: sphx-glr-script-out
Out:
.. code-block:: none
[0 0 1 1]
Precomputed sparse nearest neighbors graph
------------------------------------------
Most estimators based on nearest neighbors graphs now accept precomputed
sparse graphs as input, to reuse the same graph for multiple estimator fits.
To use this feature in a pipeline, one can use the `memory` parameter, along
with one of the two new transformers,
:class:`neighbors.KNeighborsTransformer` and
:class:`neighbors.RadiusNeighborsTransformer`. The precomputation
can also be performed by custom estimators to use alternative
implementations, such as approximate nearest neighbors methods.
See more details in the :ref:`User Guide `.
.. code-block:: default
from tempfile import TemporaryDirectory
from sklearn.neighbors import KNeighborsTransformer
from sklearn.manifold import Isomap
from sklearn.pipeline import make_pipeline
X, y = make_classification(random_state=0)
with TemporaryDirectory(prefix="sklearn_cache_") as tmpdir:
estimator = make_pipeline(
KNeighborsTransformer(n_neighbors=10, mode='distance'),
Isomap(n_neighbors=10, metric='precomputed'),
memory=tmpdir)
estimator.fit(X)
# We can decrease the number of neighbors and the graph will not be
# recomputed.
estimator.set_params(isomap__n_neighbors=5)
estimator.fit(X)
KNN Based Imputation
------------------------------------
We now support imputation for completing missing values using k-Nearest
Neighbors.
Each sample's missing values are imputed using the mean value from
``n_neighbors`` nearest neighbors found in the training set. Two samples are
close if the features that neither is missing are close.
By default, a euclidean distance metric
that supports missing values,
:func:`~metrics.nan_euclidean_distances`, is used to find the nearest
neighbors.
Read more in the :ref:`User Guide `.
.. code-block:: default
import numpy as np
from sklearn.impute import KNNImputer
X = [[1, 2, np.nan], [3, 4, 3], [np.nan, 6, 5], [8, 8, 7]]
imputer = KNNImputer(n_neighbors=2)
print(imputer.fit_transform(X))
.. rst-class:: sphx-glr-script-out
Out:
.. code-block:: none
[[1. 2. 4. ]
[3. 4. 3. ]
[5.5 6. 5. ]
[8. 8. 7. ]]
Tree pruning
------------
It is now possible to prune most tree-based estimators once the trees are
built. The pruning is based on minimal cost-complexity. Read more in the
:ref:`User Guide ` for details.
.. code-block:: default
X, y = make_classification(random_state=0)
rf = RandomForestClassifier(random_state=0, ccp_alpha=0).fit(X, y)
print("Average number of nodes without pruning {:.1f}".format(
np.mean([e.tree_.node_count for e in rf.estimators_])))
rf = RandomForestClassifier(random_state=0, ccp_alpha=0.05).fit(X, y)
print("Average number of nodes with pruning {:.1f}".format(
np.mean([e.tree_.node_count for e in rf.estimators_])))
.. rst-class:: sphx-glr-script-out
Out:
.. code-block:: none
Average number of nodes without pruning 22.3
Average number of nodes with pruning 6.4
Retrieve dataframes from OpenML
-------------------------------
:func:`datasets.fetch_openml` can now return pandas dataframe and thus
properly handle datasets with heterogeneous data:
.. code-block:: default
from sklearn.datasets import fetch_openml
titanic = fetch_openml('titanic', version=1, as_frame=True)
print(titanic.data.head()[['pclass', 'embarked']])
.. rst-class:: sphx-glr-script-out
Out:
.. code-block:: none
pclass embarked
0 1.0 S
1 1.0 S
2 1.0 S
3 1.0 S
4 1.0 S
Checking scikit-learn compatibility of an estimator
---------------------------------------------------
Developers can check the compatibility of their scikit-learn compatible
estimators using :func:`~utils.estimator_checks.check_estimator`. For
instance, the ``check_estimator(LinearSVC)`` passes.
We now provide a ``pytest`` specific decorator which allows ``pytest``
to run all checks independently and report the checks that are failing.
.. code-block:: default
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeRegressor
from sklearn.utils.estimator_checks import parametrize_with_checks
@parametrize_with_checks([LogisticRegression, DecisionTreeRegressor])
def test_sklearn_compatible_estimator(estimator, check):
check(estimator)
.. rst-class:: sphx-glr-script-out
Out:
.. code-block:: none
/home/circleci/project/sklearn/utils/estimator_checks.py:420: FutureWarning: Passing a class is deprecated since version 0.23 and won't be supported in 0.24.Please pass an instance instead.
warnings.warn(msg, FutureWarning)
ROC AUC now supports multiclass classification
----------------------------------------------
The :func:`roc_auc_score` function can also be used in multi-class
classification. Two averaging strategies are currently supported: the
one-vs-one algorithm computes the average of the pairwise ROC AUC scores, and
the one-vs-rest algorithm computes the average of the ROC AUC scores for each
class against all other classes. In both cases, the multiclass ROC AUC scores
are computed from the probability estimates that a sample belongs to a
particular class according to the model. The OvO and OvR algorithms support
weighting uniformly (``average='macro'``) and weighting by the prevalence
(``average='weighted'``).
Read more in the :ref:`User Guide `.
.. code-block:: default
from sklearn.datasets import make_classification
from sklearn.svm import SVC
from sklearn.metrics import roc_auc_score
X, y = make_classification(n_classes=4, n_informative=16)
clf = SVC(decision_function_shape='ovo', probability=True).fit(X, y)
print(roc_auc_score(y, clf.predict_proba(X), multi_class='ovo'))
.. rst-class:: sphx-glr-script-out
Out:
.. code-block:: none
0.9984000000000001
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 0 minutes 1.820 seconds)
.. _sphx_glr_download_auto_examples_release_highlights_plot_release_highlights_0_22_0.py:
.. only :: html
.. container:: sphx-glr-footer
:class: sphx-glr-footer-example
.. container:: binder-badge
.. image:: https://mybinder.org/badge_logo.svg
:target: https://mybinder.org/v2/gh/scikit-learn/scikit-learn/0.23.X?urlpath=lab/tree/notebooks/auto_examples/release_highlights/plot_release_highlights_0_22_0.ipynb
:width: 150 px
.. container:: sphx-glr-download sphx-glr-download-python
:download:`Download Python source code: plot_release_highlights_0_22_0.py `
.. container:: sphx-glr-download sphx-glr-download-jupyter
:download:`Download Jupyter notebook: plot_release_highlights_0_22_0.ipynb `
.. only:: html
.. rst-class:: sphx-glr-signature
`Gallery generated by Sphinx-Gallery `_