Merge branch 'scikit-learn:main' into submodulev2

Author: adam2392

SECURITY.md

@@ -4,8 +4,8 @@
 
 | Version   | Supported          |
 | --------- | ------------------ |
-| 1.2.2     | :white_check_mark: |
-| < 1.2.2   | :x:                |
+| 1.3.0     | :white_check_mark: |
+| < 1.3.0   | :x:                |
 
 ## Reporting a Vulnerability
 

doc/conf.py

@@ -66,7 +66,8 @@
 ]
 
 # Specify how to identify the prompt when copying code snippets
-copybutton_prompt_text = ">>> "
+copybutton_prompt_text = r">>> |\.\.\. "
+copybutton_prompt_is_regexp = True
 
 try:
     import jupyterlite_sphinx  # noqa: F401

doc/developers/contributing.rst

@@ -920,7 +920,7 @@ Building the documentation requires installing some additional packages:
 
     pip install sphinx sphinx-gallery numpydoc matplotlib Pillow pandas \
                 scikit-image packaging seaborn sphinx-prompt \
-                sphinxext-opengraph plotly pooch
+                sphinxext-opengraph sphinx-copybutton plotly pooch
 
 To build the documentation, you need to be in the ``doc`` folder:
 

doc/templates/index.html

@@ -169,6 +169,8 @@ <h4 class="sk-landing-call-header">News</h4>
         <li><strong>On-going development:</strong>
         <a href="https://scikit-learn.org/dev/whats_new.html"><strong>What's new</strong> (Changelog)</a>
         </li>
+        <li><strong>June 2023.</strong> scikit-learn 1.3.0 is available for download (<a href="whats_new/v1.3.html#version-1-3-0">Changelog</a>).
+        </li>
         <li><strong>March 2023.</strong> scikit-learn 1.2.2 is available for download (<a href="whats_new/v1.2.html#version-1-2-2">Changelog</a>).
         </li>
         <li><strong>January 2023.</strong> scikit-learn 1.2.1 is available for download (<a href="whats_new/v1.2.html#version-1-2-1">Changelog</a>).

doc/themes/scikit-learn-modern/static/css/theme.css

@@ -1019,13 +1019,12 @@ div.sphx-glr-thumbcontainer {
   padding: 0;
 }
 
-
 @media screen and (min-width: 1540px) {
-  .sphx-glr-download-link-note {
-    position: absolute;
+  div.sphx-glr-download-link-note.admonition.note {
     position: absolute;
     left: 98%;
     width: 20ex;
+    margin-top: calc(max(5.75rem, 1vh));
   }
 }
 

doc/whats_new/v1.3.rst

@@ -7,7 +7,10 @@
 Version 1.3.0
 =============
 
-**In Development**
+**June 2023**
+
+For a short description of the main highlights of the release, please refer to
+:ref:`sphx_glr_auto_examples_release_highlights_plot_release_highlights_1_3_0.py`.
 
 .. include:: changelog_legend.inc
 
@@ -770,4 +773,40 @@ Code and Documentation Contributors
 Thanks to everyone who has contributed to the maintenance and improvement of
 the project since version 1.2, including:
 
-TODO: update at the time of the release.
+2357juan, Abhishek Singh Kushwah, Adam Handke, Adam Kania, Adam Li, adienes,
+Admir Demiraj, adoublet, Adrin Jalali, A.H.Mansouri, Ahmedbgh, Ala-Na, Alex
+Buzenet, AlexL, Ali H. El-Kassas, amay, András Simon, André Pedersen, Andrew
+Wang, Ankur Singh, annegnx, Ansam Zedan, Anthony22-dev, Artur Hermano, Arturo
+Amor, as-90, ashah002, Ashish Dutt, Ashwin Mathur, AymericBasset, Azaria
+Gebremichael, Barata Tripramudya Onggo, Benedek Harsanyi, Benjamin Bossan,
+Bharat Raghunathan, Binesh Bannerjee, Boris Feld, Brendan Lu, Brevin Kunde,
+cache-missing, Camille Troillard, Carla J, carlo, Carlo Lemos, c-git, Changyao
+Chen, Chiara Marmo, Christian Lorentzen, Christian Veenhuis, Christine P. Chai,
+crispinlogan, Da-Lan, DanGonite57, Dave Berenbaum, davidblnc, david-cortes,
+Dayne, Dea María Léon, Denis, Dimitri Papadopoulos Orfanos, Dimitris
+Litsidis, Dmitry Nesterov, Dominic Fox, Dominik Prodinger, Edern, Ekaterina
+Butyugina, Elabonga Atuo, Emir, farhan khan, Felipe Siola, futurewarning, Gael
+Varoquaux, genvalen, Gleb Levitski, Guillaume Lemaitre, gunesbayir, Haesun
+Park, hujiahong726, i-aki-y, Ian Thompson, Ido M, Ily, Irene, Jack McIvor,
+jakirkham, James Dean, JanFidor, Jarrod Millman, JB Mountford, Jérémie du
+Boisberranger, Jessicakk0711, Jiawei Zhang, Joey Ortiz, JohnathanPi, John
+Pangas, Joshua Choo Yun Keat, Joshua Hedlund, JuliaSchoepp, Julien Jerphanion,
+jygerardy, ka00ri, Kaushik Amar Das, Kento Nozawa, Kian Eliasi, Kilian Kluge,
+Lene Preuss, Linus, Logan Thomas, Loic Esteve, Louis Fouquet, Lucy Liu, Madhura
+Jayaratne, Marc Torrellas Socastro, Maren Westermann, Mario Kostelac, Mark
+Harfouche, Marko Toplak, Marvin Krawutschke, Masanori Kanazu, mathurinm, Matt
+Haberland, Max Halford, maximeSaur, Maxwell Liu, m. bou, mdarii, Meekail Zain,
+Mikhail Iljin, murezzda, Nawazish Alam, Nicola Fanelli, Nightwalkx, Nikolay
+Petrov, Nishu Choudhary, NNLNR, npache, Olivier Grisel, Omar Salman, ouss1508,
+PAB, Pandata, partev, Peter Piontek, Phil, pnucci, Pooja M, Pooja Subramaniam,
+precondition, Quentin Barthélemy, Rafal Wojdyla, Raghuveer Bhat, Rahil Parikh,
+Ralf Gommers, ram vikram singh, Rushil Desai, Sadra Barikbin, SANJAI_3, Sashka
+Warner, Scott Gigante, Scott Gustafson, searchforpassion, Seoeun
+Hong, Shady el Gewily, Shiva chauhan, Shogo Hida, Shreesha Kumar Bhat, sonnivs,
+Sortofamudkip, Stanislav (Stanley) Modrak, Stefanie Senger, Steven Van
+Vaerenbergh, Tabea Kossen, Théophile Baranger, Thijs van Weezel, Thomas A
+Caswell, Thomas Germer, Thomas J. Fan, Tim Head, Tim P, Tom Dupré la Tour,
+tomiock, tspeng, Valentin Laurent, Veghit, VIGNESH D, Vijeth Moudgalya, Vinayak
+Mehta, Vincent M, Vincent-violet, Vyom Pathak, William M, windiana42, Xiao
+Yuan, Yao Xiao, Yaroslav Halchenko, Yotam Avidar-Constantini, Yuchen Zhou,
+Yusuf Raji, zeeshan lone

examples/applications/plot_topics_extraction_with_nmf_lda.py

@@ -46,14 +46,13 @@ def plot_top_words(model, feature_names, n_top_words, title):
     fig, axes = plt.subplots(2, 5, figsize=(30, 15), sharex=True)
     axes = axes.flatten()
     for topic_idx, topic in enumerate(model.components_):
-        top_features_ind = topic.argsort()[: -n_top_words - 1 : -1]
-        top_features = [feature_names[i] for i in top_features_ind]
+        top_features_ind = topic.argsort()[-n_top_words:]
+        top_features = feature_names[top_features_ind]
         weights = topic[top_features_ind]
 
         ax = axes[topic_idx]
         ax.barh(top_features, weights, height=0.7)
         ax.set_title(f"Topic {topic_idx +1}", fontdict={"fontsize": 30})
-        ax.invert_yaxis()
         ax.tick_params(axis="both", which="major", labelsize=20)
         for i in "top right left".split():
             ax.spines[i].set_visible(False)

examples/release_highlights/plot_release_highlights_1_3_0.py

@@ -0,0 +1,156 @@
+# flake8: noqa
+"""
+=======================================
+Release Highlights for scikit-learn 1.3
+=======================================
+
+.. currentmodule:: sklearn
+
+We are pleased to announce the release of scikit-learn 1.3! Many bug fixes
+and improvements were added, as well as some new key 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 <changes_1_3>`.
+
+To install the latest version (with pip)::
+
+    pip install --upgrade scikit-learn
+
+or with conda::
+
+    conda install -c conda-forge scikit-learn
+
+"""
+
+# %%
+# Metadata Routing
+# ----------------
+# We are in the process of introducing a new way to route metadata such as
+# ``sample_weight`` throughout the codebase, which would affect how
+# meta-estimators such as :class:`pipeline.Pipeline` and
+# :class:`model_selection.GridSearchCV` route metadata. While the
+# infrastructure for this feature is already included in this release, the work
+# is ongoing and not all meta-estimators support this new feature. You can read
+# more about this feature in the :ref:`Metadata Routing User Guide
+# <metadata_routing>`. Note that this feature is still under development and
+# not implemented for most meta-estimators.
+#
+# Third party developers can already start incorporating this into their
+# meta-estimators. For more details, see
+# :ref:`metadata routing developer guide
+# <sphx_glr_auto_examples_miscellaneous_plot_metadata_routing.py>`.
+
+# %%
+# HDBSCAN: hierarchical density-based clustering
+# ----------------------------------------------
+# Originally hosted in the scikit-learn-contrib repository, :class:`cluster.HDBSCAN`
+# has been adpoted into scikit-learn. It's missing a few features from the original
+# implementation which will be added in future releases.
+# By performing a modified version of :class:`cluster.DBSCAN` over multiple epsilon
+# values simultaneously, :class:`cluster.HDBSCAN` finds clusters of varying densities
+# making it more robust to parameter selection than :class:`cluster.DBSCAN`.
+# More details in the :ref:`User Guide <hdbscan>`.
+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))
+
+# %%
+# TargetEncoder: a new category encoding strategy
+# -----------------------------------------------
+# Well suited for categorical features with high cardinality,
+# :class:`preprocessing.TargetEncoder` encodes the categories based on a shrunk
+# estimate of the average target values for observations belonging to that category.
+# More details in the :ref:`User Guide <target_encoder>`.
+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_
+
+# %%
+# Missing values support in decision trees
+# ----------------------------------------
+# The classes :class:`tree.DecisionTreeClassifier` and
+# :class:`tree.DecisionTreeRegressor` now support missing values. For each potential
+# threshold on the non-missing data, the splitter will evaluate the split with all the
+# missing values going to the left node or the right node.
+# More details in the :ref:`User Guide <tree_missing_value_support>`.
+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)
+
+# %%
+# New display `model_selection.ValidationCurveDisplay`
+# ----------------------------------------------------
+# :class:`model_selection.ValidationCurveDisplay` is now available to plot results
+# from :func:`model_selection.validation_curve`.
+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",
+)
+
+# %%
+# Gamma loss for gradient boosting
+# --------------------------------
+# The class :class:`ensemble.HistGradientBoostingRegressor` supports the
+# Gamma deviance loss function via `loss="gamma"`. This loss function is useful for
+# modeling strictly positive targets with a right-skewed distribution.
+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()
+
+# %%
+# Grouping infrequent categories in :class:`preprocessing.OrdinalEncoder`
+# -----------------------------------------------------------------------
+# Similarly to :class:`preprocessing.OneHotEncoder`, the class
+# :class:`preprocessing.OrdinalEncoder` now supports aggregating infrequent categories
+# into a single output for each feature. The parameters to enable the gathering of
+# infrequent categories are `min_frequency` and `max_categories`.
+# See the :ref:`User Guide <encoder_infrequent_categories>` for more details.
+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_

sklearn/covariance/_empirical_covariance.py

@@ -23,6 +23,13 @@
 from ..utils.extmath import fast_logdet
 
 
+@validate_params(
+    {
+        "emp_cov": [np.ndarray],
+        "precision": [np.ndarray],
+    },
+    prefer_skip_nested_validation=True,
+)
 def log_likelihood(emp_cov, precision):
     """Compute the sample mean of the log_likelihood under a covariance model.
 

sklearn/datasets/_twenty_newsgroups.py

@@ -209,7 +209,7 @@ def fetch_20newsgroups(
         make the assumption that the samples are independent and identically
         distributed (i.i.d.), such as stochastic gradient descent.
 
-    random_state : int, RandomState instance or None, default=None
+    random_state : int, RandomState instance or None, default=42
         Determines random number generation for dataset shuffling. Pass an int
         for reproducible output across multiple function calls.
         See :term:`Glossary <random_state>`.