Sync with Inria repo

Author: ArturoAmorQ

.pre-commit-config.yaml

@@ -10,7 +10,7 @@ repos:
       exclude: notebooks
       exclude_types: [svg]
 - repo: https://github.com/psf/black
-  rev: 23.1.0
+  rev: 25.11.0
   hooks:
   -   id: black
 - repo: https://github.com/astral-sh/ruff-pre-commit

environment-dev.yml

@@ -14,4 +14,4 @@ dependencies:
   - packaging
   - pip
   - pip:
-    - jupyter-book >= 0.11
+    - jupyter-book < 2.0

jupyter-book/_config.yml

@@ -47,7 +47,7 @@ html:
     <div>
       <div class="mooc_add">
        <a href="https://www.fun-mooc.fr/en/courses/machine-learning-python-scikit-learn">Join the full MOOC experience</a>
-       <a href="https://certification.probabl.ai/">Get officially certified!</a>
+       <a href="https://probabl.ai/certification?utm_source=inria&utm_medium=mooc&utm_campaign=2026_inria_mooc_referrals">Get officially certified!</a>
       </div>
       Brought to you under a <a href="https://github.com/INRIA/scikit-learn-mooc/blob/main/LICENSE">CC-BY License</a> by
       <a href="https://learninglab.inria.fr">Inria Learning Lab</a>,

notebooks/cross_validation_validation_curve.ipynb

@@ -259,18 +259,18 @@
     "errors made during the data collection process (besides not measuring the\n",
     "unobserved input feature).\n",
     "\n",
-    "One extreme case could happen if there where samples in the dataset with\n",
-    "exactly the same input feature values but different values for the target\n",
-    "variable. That is very unlikely in real life settings, but could the case if\n",
-    "all features are categorical or if the numerical features were discretized\n",
-    "or rounded up naively. In our example, we can imagine two houses having\n",
-    "the exact same features in our dataset, but having different prices because\n",
-    "of the (unmeasured) seller's rush.\n",
-    "\n",
-    "Apart from these extreme case, it's hard to know for sure what should qualify\n",
-    "or not as noise and which kind of \"noise\" as introduced above is dominating.\n",
-    "But in practice, the best ways to make our predictive models robust to noise\n",
-    "are to avoid overfitting models by:\n",
+    "One extreme case could happen if there where samples in the dataset with exactly\n",
+    "the same input feature values but different values for the target variable. That\n",
+    "is very unlikely in real life settings, but could be the case if all features\n",
+    "are categorical or if the numerical features were discretized or rounded up\n",
+    "naively. In our example, we can imagine two houses having the exact same\n",
+    "features in our dataset, but having different prices because of the (unmeasured)\n",
+    "seller's rush.\n",
+    "\n",
+    "Apart from this extreme case, it's hard to know for sure what should qualify or\n",
+    "not as noise and which kind of \"noise\" as introduced above is dominating. But in\n",
+    "practice, the best way to make our predictive models robust to noise is to\n",
+    "avoid overfitting models by:\n",
     "\n",
     "- selecting models that are simple enough or with tuned hyper-parameters as\n",
     "  explained in this module;\n",

notebooks/linear_models_ex_01.ipynb

@@ -43,7 +43,7 @@
     "penguins = pd.read_csv(\"../datasets/penguins_regression.csv\")\n",
     "feature_name = \"Flipper Length (mm)\"\n",
     "target_name = \"Body Mass (g)\"\n",
-    "data, target = penguins[[feature_name]], penguins[target_name]"
+    "data, target = penguins[[feature_name]], penguins[[target_name]]"
    ]
   },
   {

notebooks/linear_models_sol_01.ipynb

@@ -43,7 +43,7 @@
     "penguins = pd.read_csv(\"../datasets/penguins_regression.csv\")\n",
     "feature_name = \"Flipper Length (mm)\"\n",
     "target_name = \"Body Mass (g)\"\n",
-    "data, target = penguins[[feature_name]], penguins[target_name]"
+    "data, target = penguins[[feature_name]], penguins[[target_name]]"
    ]
   },
   {
@@ -153,7 +153,7 @@
     "def goodness_fit_measure(true_values, predictions):\n",
     "    # we compute the error between the true values and the predictions of our\n",
     "    # model\n",
-    "    errors = np.ravel(true_values) - np.ravel(predictions)\n",
+    "    errors = true_values - predictions\n",
     "    # We have several possible strategies to reduce all errors to a single value.\n",
     "    # Computing the mean error (sum divided by the number of element) might seem\n",
     "    # like a good solution. However, we have negative errors that will misleadingly\n",

python_scripts/cross_validation_validation_curve.py

@@ -202,16 +202,16 @@
 #
 # One extreme case could happen if there where samples in the dataset with
 # exactly the same input feature values but different values for the target
-# variable. That is very unlikely in real life settings, but could the case if
-# all features are categorical or if the numerical features were discretized
-# or rounded up naively. In our example, we can imagine two houses having
-# the exact same features in our dataset, but having different prices because
-# of the (unmeasured) seller's rush.
+# variable. That is very unlikely in real life settings, but could be the case
+# if all features are categorical or if the numerical features were discretized
+# or rounded up naively. In our example, we can imagine two houses having the
+# exact same features in our dataset, but having different prices because of the
+# (unmeasured) seller's rush.
 #
-# Apart from these extreme case, it's hard to know for sure what should qualify
+# Apart from this extreme case, it's hard to know for sure what should qualify
 # or not as noise and which kind of "noise" as introduced above is dominating.
-# But in practice, the best ways to make our predictive models robust to noise
-# are to avoid overfitting models by:
+# But in practice, the best way to make our predictive models robust to noise
+# is to avoid overfitting models by:
 #
 # - selecting models that are simple enough or with tuned hyper-parameters as
 #   explained in this module;

python_scripts/datasets_ames_housing.py

@@ -169,7 +169,6 @@
 from sklearn.impute import SimpleImputer
 from sklearn.pipeline import make_pipeline
 
-
 numerical_features = [
     "LotFrontage",
     "LotArea",

python_scripts/ensemble_bagging.py

@@ -356,7 +356,6 @@ def bootstrap_sample(data, target, seed=0):
 from sklearn.preprocessing import MinMaxScaler
 from sklearn.pipeline import make_pipeline
 
-
 polynomial_regressor = make_pipeline(
     MinMaxScaler(),
     PolynomialFeatures(degree=4, include_bias=False),

python_scripts/feature_selection_introduction.py

@@ -57,7 +57,6 @@
 from sklearn.feature_selection import f_classif
 from sklearn.pipeline import make_pipeline
 
-
 model_with_selection = make_pipeline(
     SelectKBest(score_func=f_classif, k=2),
     RandomForestClassifier(n_jobs=2),