MNT Adjust code after NEP 51 numpy scalar formatting changes (#27042)

lesteve · jeremiedbb · commit 37e821bcef1b · 2023-09-20T14:40:31.000+02:00
diff --git a/sklearn/dummy.py b/sklearn/dummy.py
@@ -227,7 +227,7 @@ def fit(self, X, y, sample_weight=None):
                         "The constant target value must be present in "
                         "the training data. You provided constant={}. "
                         "Possible values are: {}.".format(
-                            self.constant, list(self.classes_[k])
+                            self.constant, self.classes_[k].tolist()
                         )
                     )
                     raise ValueError(err_msg)
diff --git a/sklearn/impute/tests/test_impute.py b/sklearn/impute/tests/test_impute.py
@@ -259,7 +259,7 @@ def test_imputation_median_special_cases():
 @pytest.mark.parametrize("dtype", [None, object, str])
 def test_imputation_mean_median_error_invalid_type(strategy, dtype):
     X = np.array([["a", "b", 3], [4, "e", 6], ["g", "h", 9]], dtype=dtype)
-    msg = "non-numeric data:\ncould not convert string to float: '"
+    msg = "non-numeric data:\ncould not convert string to float:"
     with pytest.raises(ValueError, match=msg):
         imputer = SimpleImputer(strategy=strategy)
         imputer.fit_transform(X)
@@ -272,7 +272,7 @@ def test_imputation_mean_median_error_invalid_type_list_pandas(strategy, type):
     if type == "dataframe":
         pd = pytest.importorskip("pandas")
         X = pd.DataFrame(X)
-    msg = "non-numeric data:\ncould not convert string to float: '"
+    msg = "non-numeric data:\ncould not convert string to float:"
     with pytest.raises(ValueError, match=msg):
         imputer = SimpleImputer(strategy=strategy)
         imputer.fit_transform(X)
diff --git a/sklearn/preprocessing/_encoders.py b/sklearn/preprocessing/_encoders.py
@@ -774,8 +774,8 @@ def _map_drop_idx_to_infrequent(self, feature_idx, drop_idx):
         if infrequent_indices is not None and drop_idx in infrequent_indices:
             categories = self.categories_[feature_idx]
             raise ValueError(
-                f"Unable to drop category {categories[drop_idx]!r} from feature"
-                f" {feature_idx} because it is infrequent"
+                f"Unable to drop category {categories[drop_idx].item()!r} from"
+                f" feature {feature_idx} because it is infrequent"
             )
         return default_to_infrequent[drop_idx]
 
diff --git a/sklearn/utils/class_weight.py b/sklearn/utils/class_weight.py
@@ -68,8 +68,10 @@ def compute_class_weight(class_weight, *, classes, y):
 
         n_weighted_classes = len(classes) - len(unweighted_classes)
         if unweighted_classes and n_weighted_classes != len(class_weight):
+            unweighted_classes_user_friendly_str = np.array(unweighted_classes).tolist()
             raise ValueError(
-                f"The classes, {unweighted_classes}, are not in class_weight"
+                f"The classes, {unweighted_classes_user_friendly_str}, are not in"
+                " class_weight"
             )
 
     return weight
diff --git a/sklearn/utils/validation.py b/sklearn/utils/validation.py
@@ -2243,7 +2243,7 @@ def _check_pos_label_consistency(pos_label, y_true):
             or np.array_equal(classes, [1])
         )
     ):
-        classes_repr = ", ".join(repr(c) for c in classes)
+        classes_repr = ", ".join([repr(c) for c in classes.tolist()])
         raise ValueError(
             f"y_true takes value in {{{classes_repr}}} and pos_label is not "
             "specified: either make y_true take value in {0, 1} or "

Original file line number	Diff line number	Diff line change
`@@ -227,7 +227,7 @@ def fit(self, X, y, sample_weight=None):`
`227`	`227`	`"The constant target value must be present in "`
`228`	`228`	`"the training data. You provided constant={}. "`
`229`	`229`	`"Possible values are: {}.".format(`
`230`		`- self.constant, list(self.classes_[k])`
	`230`	`+ self.constant, self.classes_[k].tolist()`
`231`	`231`	`)`
`232`	`232`	`)`
`233`	`233`	`raise ValueError(err_msg)`
Original file line number	Diff line number	Diff line change
`@@ -2243,7 +2243,7 @@ def _check_pos_label_consistency(pos_label, y_true):`
`2243`	`2243`	`or np.array_equal(classes, [1])`
`2244`	`2244`	`)`
`2245`	`2245`	`):`
`2246`		`- classes_repr = ", ".join(repr(c) for c in classes)`
	`2246`	`+ classes_repr = ", ".join([repr(c) for c in classes.tolist()])`
`2247`	`2247`	`raise ValueError(`
`2248`	`2248`	`f"y_true takes value in {{{classes_repr}}} and pos_label is not "`
`2249`	`2249`	`"specified: either make y_true take value in {0, 1} or "`