From 5314915a6ce9ae7a4d6a57af2f22d31afa19e28d Mon Sep 17 00:00:00 2001
From: Sylvain Combettes <48064216+sylvaincom@users.noreply.github.com>
Date: Mon, 13 Jan 2025 00:48:55 +0100
Subject: [PATCH] docs: Use logistic regression instead of SVC on the Iris
 dataset (#1087)

Fix #1018

In quick start example, do not use SVC on the Iris dataset, but rather
logistic regression
---
 README.md                                    | 11 ++++++++---
 examples/getting_started/plot_quick_start.py |  8 +++++---
 2 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/README.md b/README.md
index 674efd131..b0b709672 100644
--- a/README.md
+++ b/README.md
@@ -65,12 +65,17 @@ You can find information on the latest version [here](https://anaconda.org/conda
 2. Evaluate your model using `skore.CrossValidationReporter`:
     ```python
     from sklearn.datasets import load_iris
-    from sklearn.svm import SVC
+    from sklearn.pipeline import Pipeline
+    from sklearn.preprocessing import StandardScaler
+    from sklearn.linear_model import LogisticRegression
 
     X, y = load_iris(return_X_y=True)
-    clf = SVC(kernel="linear", C=1, random_state=0)
+    clf_pipeline = Pipeline([
+        ('scaler', StandardScaler()),
+        ('clf', LogisticRegression())
+    ])
 
-    reporter = skore.CrossValidationReporter(clf, X, y, cv=5)
+    reporter = skore.CrossValidationReporter(clf_pipeline, X, y, cv=5)
 
     # Store the results in the project
     my_project.put("cv_reporter", reporter)
diff --git a/examples/getting_started/plot_quick_start.py b/examples/getting_started/plot_quick_start.py
index 040a738e8..fd7359d2d 100644
--- a/examples/getting_started/plot_quick_start.py
+++ b/examples/getting_started/plot_quick_start.py
@@ -23,12 +23,14 @@
 
 # %%
 from sklearn.datasets import load_iris
-from sklearn.svm import SVC
+from sklearn.pipeline import Pipeline
+from sklearn.preprocessing import StandardScaler
+from sklearn.linear_model import LogisticRegression
 
 X, y = load_iris(return_X_y=True)
-clf = SVC(kernel="linear", C=1, random_state=0)
+clf_pipeline = Pipeline([("scaler", StandardScaler()), ("clf", LogisticRegression())])
 
-reporter = skore.CrossValidationReporter(clf, X, y, cv=5)
+reporter = skore.CrossValidationReporter(clf_pipeline, X, y, cv=5)
 
 # %%
 # Store the results in the skore project: