Pushing the docs to dev/ for branch: main, commit f315bc9a181a986110738d3e4e561c6c4cc6419e

Author: dirty-cat-ci

dev/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file records the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 514904c5fd7261eb8f2f6d227b4e2e90
+config: deb37e3180b8d4a35b00330119ad70b8
 tags: 645f666f9bcd5a90fca523b33c5a78b7

dev/CHANGES.html

@@ -11,10 +11,10 @@
 <meta property="og:type" content="website" />
 <meta property="og:url" content="https://skrub-data.github.io/stable/CHANGES.html" />
 <meta property="og:site_name" content="skrub" />
-<meta property="og:description" content="Ongoing Development: New features: Changes: Bugfixes: DropCols and SelectCols: attributes were renamed to end with an underscore, in order to follow a scikit-learn convention which is used to deter..." />
+<meta property="og:description" content="Ongoing Development: New features: A new dataset, fetch_california_housing(), has been added to the skrub.datasets module. It allows to get a redundancy copy of the scikit-learn fetch_california_ho..." />
 <meta property="og:image" content="https://skrub-data.github.io/stable/_static/skrub.svg" />
 <meta property="og:image:alt" content="skrub" />
-<meta name="description" content="Ongoing Development: New features: Changes: Bugfixes: DropCols and SelectCols: attributes were renamed to end with an underscore, in order to follow a scikit-learn convention which is used to deter..." />
+<meta name="description" content="Ongoing Development: New features: A new dataset, fetch_california_housing(), has been added to the skrub.datasets module. It allows to get a redundancy copy of the scikit-learn fetch_california_ho..." />
 
     <title>Release history &#8212; skrub</title>
 
@@ -577,6 +577,12 @@
 <h2>Ongoing Development<a class="headerlink" href="#ongoing-development" title="Link to this heading">#</a></h2>
 <section id="new-features">
 <h3>New features<a class="headerlink" href="#new-features" title="Link to this heading">#</a></h3>
+<ul class="simple">
+<li><p>A new dataset, <code class="xref py py-func docutils literal notranslate"><span class="pre">fetch_california_housing()</span></code>, has been added to the
+<code class="xref py py-mod docutils literal notranslate"><span class="pre">skrub.datasets</span></code> module. It allows to get a redundancy copy of the scikit-learn
+<code class="xref py py-func docutils literal notranslate"><span class="pre">fetch_california_housing()</span></code> function.
+<a class="reference external" href="https://github.com/skrub-data/skrub/pull/1830">#1830</a> by <a class="reference external" href="https://github.com/glemaitre">Guillaume Lemaitre</a>.</p></li>
+</ul>
 </section>
 <section id="id1">
 <h3>Changes<a class="headerlink" href="#id1" title="Link to this heading">#</a></h3>
@@ -2059,7 +2065,7 @@ <h3>This Page</h3>
 
   <p class="copyright">
 
-      © Copyright 2018-2023, the dirty_cat developers, 2023-2025, the skrub developers.
+      © Copyright 2018-2023, the dirty_cat developers, 2023-2026, the skrub developers.
       <br/>
 
   </p>

dev/CONTRIBUTING.html

@@ -1096,7 +1096,7 @@ <h3>This Page</h3>
 
   <p class="copyright">
 
-      © Copyright 2018-2023, the dirty_cat developers, 2023-2025, the skrub developers.
+      © Copyright 2018-2023, the dirty_cat developers, 2023-2026, the skrub developers.
       <br/>
 
   </p>

dev/RELEASE_PROCESS.html

@@ -850,7 +850,7 @@ <h3>This Page</h3>
 
   <p class="copyright">
 
-      © Copyright 2018-2023, the dirty_cat developers, 2023-2025, the skrub developers.
+      © Copyright 2018-2023, the dirty_cat developers, 2023-2026, the skrub developers.
       <br/>
 
   </p>

dev/_downloads/079702aaaa2e975f1668cb635070b620/0050_deduplication.zip

@@ -29,8 +29,8 @@
 # ------------------------------------
 #
 # We will fit a regressor containing a few choices on a toy dataset. We
-# try 2 regressors: gradient boosting and random forest. They both have
-# hyperparameters that we want to tune.
+# try 2 regressors: extra trees and ridge. They both have  hyperparameters that
+# we want to tune.
 
 # %%
 from sklearn.ensemble import ExtraTreesRegressor
@@ -56,11 +56,12 @@
 # Load data for the example
 
 # %%
-from sklearn.datasets import fetch_california_housing
 from sklearn.model_selection import KFold
 
 # (We subsample the dataset by half to make the example run faster)
-df = fetch_california_housing(as_frame=True).frame.sample(10_000, random_state=0)
+df = skrub.datasets.fetch_california_housing().california_housing.sample(
+    10_000, random_state=0
+)
 
 # The environment we will use to fit the learners created by our DataOp.
 env = {"data": df}