MAINT Parameter validation for metrics.cluster._supervised (scikit-learn#26258)

Co-authored-by: Jérémie du Boisberranger <34657725+jeremiedbb@users.noreply.github.com>

Author: hujiahong726

sklearn/metrics/cluster/_supervised.py

@@ -476,7 +476,7 @@ def homogeneity_completeness_v_measure(labels_true, labels_pred, *, beta=1.0):
 
     Parameters
     ----------
-    labels_true : int array, shape = [n_samples]
+    labels_true : array-like of shape (n_samples,)
         Ground truth class labels to be used as a reference.
 
     labels_pred : array-like of shape (n_samples,)
@@ -532,6 +532,12 @@ def homogeneity_completeness_v_measure(labels_true, labels_pred, *, beta=1.0):
     return homogeneity, completeness, v_measure_score
 
 
+@validate_params(
+    {
+        "labels_true": ["array-like"],
+        "labels_pred": ["array-like"],
+    }
+)
 def homogeneity_score(labels_true, labels_pred):
     """Homogeneity metric of a cluster labeling given a ground truth.
 
@@ -550,7 +556,7 @@ def homogeneity_score(labels_true, labels_pred):
 
     Parameters
     ----------
-    labels_true : int array, shape = [n_samples]
+    labels_true : array-like of shape (n_samples,)
         Ground truth class labels to be used as a reference.
 
     labels_pred : array-like of shape (n_samples,)
@@ -601,6 +607,12 @@ def homogeneity_score(labels_true, labels_pred):
     return homogeneity_completeness_v_measure(labels_true, labels_pred)[0]
 
 
+@validate_params(
+    {
+        "labels_true": ["array-like"],
+        "labels_pred": ["array-like"],
+    }
+)
 def completeness_score(labels_true, labels_pred):
     """Compute completeness metric of a cluster labeling given a ground truth.
 
@@ -619,7 +631,7 @@ def completeness_score(labels_true, labels_pred):
 
     Parameters
     ----------
-    labels_true : int array, shape = [n_samples]
+    labels_true : array-like of shape (n_samples,)
         Ground truth class labels to be used as a reference.
 
     labels_pred : array-like of shape (n_samples,)
@@ -670,6 +682,13 @@ def completeness_score(labels_true, labels_pred):
     return homogeneity_completeness_v_measure(labels_true, labels_pred)[1]
 
 
+@validate_params(
+    {
+        "labels_true": ["array-like"],
+        "labels_pred": ["array-like"],
+        "beta": [Interval(Real, 0, None, closed="left")],
+    }
+)
 def v_measure_score(labels_true, labels_pred, *, beta=1.0):
     """V-measure cluster labeling given a ground truth.
 
@@ -694,7 +713,7 @@ def v_measure_score(labels_true, labels_pred, *, beta=1.0):
 
     Parameters
     ----------
-    labels_true : int array, shape = [n_samples]
+    labels_true : array-like of shape (n_samples,)
         Ground truth class labels to be used as a reference.
 
     labels_pred : array-like of shape (n_samples,)

sklearn/tests/test_public_functions.py

@@ -180,6 +180,7 @@ def _check_function_param_validation(
     "sklearn.metrics.balanced_accuracy_score",
     "sklearn.metrics.brier_score_loss",
     "sklearn.metrics.calinski_harabasz_score",
+    "sklearn.metrics.completeness_score",
     "sklearn.metrics.class_likelihood_ratios",
     "sklearn.metrics.classification_report",
     "sklearn.metrics.cluster.adjusted_mutual_info_score",
@@ -205,6 +206,7 @@ def _check_function_param_validation(
     "sklearn.metrics.get_scorer",
     "sklearn.metrics.hamming_loss",
     "sklearn.metrics.hinge_loss",
+    "sklearn.metrics.homogeneity_score",
     "sklearn.metrics.jaccard_score",
     "sklearn.metrics.label_ranking_average_precision_score",
     "sklearn.metrics.label_ranking_loss",
@@ -248,6 +250,7 @@ def _check_function_param_validation(
     "sklearn.metrics.roc_auc_score",
     "sklearn.metrics.roc_curve",
     "sklearn.metrics.top_k_accuracy_score",
+    "sklearn.metrics.v_measure_score",
     "sklearn.metrics.zero_one_loss",
     "sklearn.model_selection.cross_validate",
     "sklearn.model_selection.permutation_test_score",