FIX GridSearchCV regression in 1.5 with parameter grid with heterogeneous parameter values (scikit-learn#29078)

lesteve · web-flow · commit 1bd9c1df19f5 · 2024-05-23T16:47:12.000+02:00
diff --git a/doc/whats_new/v1.5.rst b/doc/whats_new/v1.5.rst
@@ -13,6 +13,24 @@ For a short description of the main highlights of the release, please refer to
 
 .. include:: changelog_legend.inc
 
+.. _changes_1_5_1:
+
+Version 1.5.1
+=============
+
+**TODO**
+
+Changelog
+---------
+
+:mod:`sklearn.model_selection`
+..............................
+
+- |Fix| Fix a regression in :class:`model_selection.GridSearchCV` for parameter
+  grids that have heterogeneous parameter values.
+  :pr:`29078` by :user:`Loïc Estève <lesteve>`
+
+
 .. _changes_1_5:
 
 Version 1.5.0
@@ -550,29 +568,29 @@ Changelog
 Thanks to everyone who has contributed to the maintenance and improvement of
 the project since version 1.4, including:
 
-101AlexMartin, Abdulaziz Aloqeely, Adam J. Stewart, Adam Li, Adarsh Wase, Adrin 
-Jalali, Advik Sinha, Akash Srivastava, Akihiro Kuno, Alan Guedes, Alexis 
-IMBERT, Ana Paula Gomes, Anderson Nelson, Andrei Dzis, Arnaud Capitaine, Arturo 
-Amor, Aswathavicky, Bharat Raghunathan, Brendan Lu, Bruno, Cemlyn, Christian 
-Lorentzen, Christian Veenhuis, Cindy Liang, Claudio Salvatore Arcidiacono, 
-Connor Boyle, Conrad Stevens, crispinlogan, davidleon123, DerWeh, Dipan Banik, 
-Duarte São José, DUONG, Eddie Bergman, Edoardo Abati, Egehan Gunduz, Emad 
-Izadifar, Erich Schubert, Filip Karlo Došilović, Franck Charras, Gael 
-Varoquaux, Gönül Aycı, Guillaume Lemaitre, Gyeongjae Choi, Harmanan Kohli, 
-Hong Xiang Yue, Ian Faust, itsaphel, Ivan Wiryadi, Jack Bowyer, Javier Marin 
-Tur, Jérémie du Boisberranger, Jérôme Dockès, Jiawei Zhang, Joel Nothman, 
-Johanna Bayer, John Cant, John Hopfensperger, jpcars, jpienaar-tuks, Julian 
-Libiseller-Egger, Julien Jerphanion, KanchiMoe, Kaushik Amar Das, keyber, 
-Koustav Ghosh, kraktus, Krsto Proroković, ldwy4, LeoGrin, lihaitao, Linus 
-Sommer, Loic Esteve, Lucy Liu, Lukas Geiger, manasimj, Manuel Labbé, Manuel 
-Morales, Marco Edward Gorelli, Maren Westermann, Marija Vlajic, Mark Elliot, 
-Mateusz Sokół, Mavs, Michael Higgins, Michael Mayer, miguelcsilva, Miki 
-Watanabe, Mohammed Hamdy, myenugula, Nathan Goldbaum, Naziya Mahimkar, Neto, 
-Olivier Grisel, Omar Salman, Patrick Wang, Pierre de Fréminville, Priyash 
-Shah, Puneeth K, Rahil Parikh, raisadz, Raj Pulapakura, Ralf Gommers, Ralph 
-Urlus, Randolf Scholz, Reshama Shaikh, Richard Barnes, Rodrigo Romero, Saad 
-Mahmood, Salim Dohri, Sandip Dutta, SarahRemus, scikit-learn-bot, Shaharyar 
-Choudhry, Shubham, sperret6, Stefanie Senger, Suha Siddiqui, Thanh Lam DANG, 
-thebabush, Thomas J. Fan, Thomas Lazarus, Thomas Li, Tialo, Tim Head, Tuhin 
-Sharma, VarunChaduvula, Vineet Joshi, virchan, Waël Boukhobza, Weyb, Will 
+101AlexMartin, Abdulaziz Aloqeely, Adam J. Stewart, Adam Li, Adarsh Wase, Adrin
+Jalali, Advik Sinha, Akash Srivastava, Akihiro Kuno, Alan Guedes, Alexis
+IMBERT, Ana Paula Gomes, Anderson Nelson, Andrei Dzis, Arnaud Capitaine, Arturo
+Amor, Aswathavicky, Bharat Raghunathan, Brendan Lu, Bruno, Cemlyn, Christian
+Lorentzen, Christian Veenhuis, Cindy Liang, Claudio Salvatore Arcidiacono,
+Connor Boyle, Conrad Stevens, crispinlogan, davidleon123, DerWeh, Dipan Banik,
+Duarte São José, DUONG, Eddie Bergman, Edoardo Abati, Egehan Gunduz, Emad
+Izadifar, Erich Schubert, Filip Karlo Došilović, Franck Charras, Gael
+Varoquaux, Gönül Aycı, Guillaume Lemaitre, Gyeongjae Choi, Harmanan Kohli,
+Hong Xiang Yue, Ian Faust, itsaphel, Ivan Wiryadi, Jack Bowyer, Javier Marin
+Tur, Jérémie du Boisberranger, Jérôme Dockès, Jiawei Zhang, Joel Nothman,
+Johanna Bayer, John Cant, John Hopfensperger, jpcars, jpienaar-tuks, Julian
+Libiseller-Egger, Julien Jerphanion, KanchiMoe, Kaushik Amar Das, keyber,
+Koustav Ghosh, kraktus, Krsto Proroković, ldwy4, LeoGrin, lihaitao, Linus
+Sommer, Loic Esteve, Lucy Liu, Lukas Geiger, manasimj, Manuel Labbé, Manuel
+Morales, Marco Edward Gorelli, Maren Westermann, Marija Vlajic, Mark Elliot,
+Mateusz Sokół, Mavs, Michael Higgins, Michael Mayer, miguelcsilva, Miki
+Watanabe, Mohammed Hamdy, myenugula, Nathan Goldbaum, Naziya Mahimkar, Neto,
+Olivier Grisel, Omar Salman, Patrick Wang, Pierre de Fréminville, Priyash
+Shah, Puneeth K, Rahil Parikh, raisadz, Raj Pulapakura, Ralf Gommers, Ralph
+Urlus, Randolf Scholz, Reshama Shaikh, Richard Barnes, Rodrigo Romero, Saad
+Mahmood, Salim Dohri, Sandip Dutta, SarahRemus, scikit-learn-bot, Shaharyar
+Choudhry, Shubham, sperret6, Stefanie Senger, Suha Siddiqui, Thanh Lam DANG,
+thebabush, Thomas J. Fan, Thomas Lazarus, Thomas Li, Tialo, Tim Head, Tuhin
+Sharma, VarunChaduvula, Vineet Joshi, virchan, Waël Boukhobza, Weyb, Will
 Dean, Xavier Beltran, Xiao Yuan, Xuefeng Xu, Yao Xiao
diff --git a/sklearn/model_selection/_search.py b/sklearn/model_selection/_search.py
@@ -1090,7 +1090,7 @@ def _store(key_name, array, weights=None, splits=False, rank=False):
             param_list = list(param_result.values())
             try:
                 arr_dtype = np.result_type(*param_list)
-            except TypeError:
+            except (TypeError, ValueError):
                 arr_dtype = object
             if len(param_list) == n_candidates and arr_dtype != object:
                 # Exclude `object` else the numpy constructor might infer a list of
diff --git a/sklearn/model_selection/tests/test_search.py b/sklearn/model_selection/tests/test_search.py
@@ -2641,3 +2641,48 @@ def test_score_rejects_params_with_no_routing_enabled(SearchCV, param_search):
 
 # End of Metadata Routing Tests
 # =============================
+
+
+def test_cv_results_dtype_issue_29074():
+    """Non-regression test for https://github.com/scikit-learn/scikit-learn/issues/29074"""
+
+    class MetaEstimator(BaseEstimator, ClassifierMixin):
+        def __init__(
+            self,
+            base_clf,
+            parameter1=None,
+            parameter2=None,
+            parameter3=None,
+            parameter4=None,
+        ):
+            self.base_clf = base_clf
+            self.parameter1 = parameter1
+            self.parameter2 = parameter2
+            self.parameter3 = parameter3
+            self.parameter4 = parameter4
+
+        def fit(self, X, y=None):
+            self.base_clf.fit(X, y)
+            return self
+
+        def score(self, X, y):
+            return self.base_clf.score(X, y)
+
+    # Values of param_grid are such that np.result_type gives slightly
+    # different errors, in particular ValueError and TypeError
+    param_grid = {
+        "parameter1": [None, {"option": "A"}, {"option": "B"}],
+        "parameter2": [None, [1, 2]],
+        "parameter3": [{"a": 1}],
+        "parameter4": ["str1", "str2"],
+    }
+    grid_search = GridSearchCV(
+        estimator=MetaEstimator(LogisticRegression()),
+        param_grid=param_grid,
+        cv=3,
+    )
+
+    X, y = make_blobs(random_state=0)
+    grid_search.fit(X, y)
+    for param in param_grid:
+        assert grid_search.cv_results_[f"param_{param}"].dtype == object
