fix default vals for functional forms

Author: rittik9

src/torchmetrics/functional/classification/hamming.py

@@ -163,7 +163,7 @@ def multiclass_hamming_distance(
     preds: Tensor,
     target: Tensor,
     num_classes: int,
-    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "macro",
+    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "micro",
     top_k: int = 1,
     multidim_average: Literal["global", "samplewise"] = "global",
     ignore_index: Optional[int] = None,
@@ -231,7 +231,7 @@ def multiclass_hamming_distance(
         >>> target = tensor([2, 1, 0, 0])
         >>> preds = tensor([2, 1, 0, 1])
         >>> multiclass_hamming_distance(preds, target, num_classes=3)
-        tensor(0.1667)
+        tensor(0.2500)
         >>> multiclass_hamming_distance(preds, target, num_classes=3, average=None)
         tensor([0.5000, 0.0000, 0.0000])
 
@@ -243,7 +243,7 @@ def multiclass_hamming_distance(
         ...                 [0.71, 0.09, 0.20],
         ...                 [0.05, 0.82, 0.13]])
         >>> multiclass_hamming_distance(preds, target, num_classes=3)
-        tensor(0.1667)
+        tensor(0.2500)
         >>> multiclass_hamming_distance(preds, target, num_classes=3, average=None)
         tensor([0.5000, 0.0000, 0.0000])
 
@@ -252,7 +252,7 @@ def multiclass_hamming_distance(
         >>> target = tensor([[[0, 1], [2, 1], [0, 2]], [[1, 1], [2, 0], [1, 2]]])
         >>> preds = tensor([[[0, 2], [2, 0], [0, 1]], [[2, 2], [2, 1], [1, 0]]])
         >>> multiclass_hamming_distance(preds, target, num_classes=3, multidim_average='samplewise')
-        tensor([0.5000, 0.7222])
+        tensor([0.5000, 0.6667])
         >>> multiclass_hamming_distance(preds, target, num_classes=3, multidim_average='samplewise', average=None)
         tensor([[0.0000, 1.0000, 0.5000],
                 [1.0000, 0.6667, 0.5000]])
@@ -273,7 +273,7 @@ def multilabel_hamming_distance(
     target: Tensor,
     num_labels: int,
     threshold: float = 0.5,
-    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "macro",
+    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "micro",
     multidim_average: Literal["global", "samplewise"] = "global",
     ignore_index: Optional[int] = None,
     validate_args: bool = True,

src/torchmetrics/functional/classification/negative_predictive_value.py

@@ -139,7 +139,7 @@ def multiclass_negative_predictive_value(
     preds: Tensor,
     target: Tensor,
     num_classes: int,
-    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "macro",
+    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "micro",
     top_k: int = 1,
     multidim_average: Literal["global", "samplewise"] = "global",
     ignore_index: Optional[int] = None,
@@ -208,7 +208,7 @@ def multiclass_negative_predictive_value(
         >>> target = tensor([2, 1, 0, 0])
         >>> preds = tensor([2, 1, 0, 1])
         >>> multiclass_negative_predictive_value(preds, target, num_classes=3)
-        tensor(0.8889)
+        tensor(0.8750)
         >>> multiclass_negative_predictive_value(preds, target, num_classes=3, average=None)
         tensor([0.6667, 1.0000, 1.0000])
 
@@ -220,7 +220,7 @@ def multiclass_negative_predictive_value(
         ...                 [0.71, 0.09, 0.20],
         ...                 [0.05, 0.82, 0.13]])
         >>> multiclass_negative_predictive_value(preds, target, num_classes=3)
-        tensor(0.8889)
+        tensor(0.8750)
         >>> multiclass_negative_predictive_value(preds, target, num_classes=3, average=None)
         tensor([0.6667, 1.0000, 1.0000])
 
@@ -229,7 +229,7 @@ def multiclass_negative_predictive_value(
         >>> target = tensor([[[0, 1], [2, 1], [0, 2]], [[1, 1], [2, 0], [1, 2]]])
         >>> preds = tensor([[[0, 2], [2, 0], [0, 1]], [[2, 2], [2, 1], [1, 0]]])
         >>> multiclass_negative_predictive_value(preds, target, num_classes=3, multidim_average='samplewise')
-        tensor([0.7833, 0.6556])
+        tensor([0.7500, 0.6667])
         >>> multiclass_negative_predictive_value(
         ...     preds, target, num_classes=3, multidim_average='samplewise', average=None
         ... )
@@ -254,7 +254,7 @@ def multilabel_negative_predictive_value(
     target: Tensor,
     num_labels: int,
     threshold: float = 0.5,
-    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "macro",
+    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "micro",
     multidim_average: Literal["global", "samplewise"] = "global",
     ignore_index: Optional[int] = None,
     validate_args: bool = True,
@@ -320,7 +320,7 @@ def multilabel_negative_predictive_value(
         >>> target = tensor([[0, 1, 0], [1, 0, 1]])
         >>> preds = tensor([[0, 0, 1], [1, 0, 1]])
         >>> multilabel_negative_predictive_value(preds, target, num_labels=3)
-        tensor(0.5000)
+        tensor(0.6667)
         >>> multilabel_negative_predictive_value(preds, target, num_labels=3, average=None)
         tensor([1.0000, 0.5000, 0.0000])
 
@@ -329,7 +329,7 @@ def multilabel_negative_predictive_value(
         >>> target = tensor([[0, 1, 0], [1, 0, 1]])
         >>> preds = tensor([[0.11, 0.22, 0.84], [0.73, 0.33, 0.92]])
         >>> multilabel_negative_predictive_value(preds, target, num_labels=3)
-        tensor(0.5000)
+        tensor(0.6667)
         >>> multilabel_negative_predictive_value(preds, target, num_labels=3, average=None)
         tensor([1.0000, 0.5000, 0.0000])
 
@@ -339,7 +339,7 @@ def multilabel_negative_predictive_value(
         >>> preds = tensor([[[0.59, 0.91], [0.91, 0.99], [0.63, 0.04]],
         ...                 [[0.38, 0.04], [0.86, 0.780], [0.45, 0.37]]])
         >>> multilabel_negative_predictive_value(preds, target, num_labels=3, multidim_average='samplewise')
-        tensor([0.0000, 0.1667])
+        tensor([0.0000, 0.2500])
         >>> multilabel_negative_predictive_value(
         ...     preds, target, num_labels=3, multidim_average='samplewise', average=None
         ... )

src/torchmetrics/functional/classification/precision_recall.py

@@ -141,7 +141,7 @@ def multiclass_precision(
     preds: Tensor,
     target: Tensor,
     num_classes: int,
-    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "macro",
+    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "micro",
     top_k: int = 1,
     multidim_average: Literal["global", "samplewise"] = "global",
     ignore_index: Optional[int] = None,
@@ -209,7 +209,7 @@ def multiclass_precision(
         >>> target = tensor([2, 1, 0, 0])
         >>> preds = tensor([2, 1, 0, 1])
         >>> multiclass_precision(preds, target, num_classes=3)
-        tensor(0.8333)
+        tensor(0.7500)
         >>> multiclass_precision(preds, target, num_classes=3, average=None)
         tensor([1.0000, 0.5000, 1.0000])
 
@@ -221,7 +221,7 @@ def multiclass_precision(
         ...                 [0.71, 0.09, 0.20],
         ...                 [0.05, 0.82, 0.13]])
         >>> multiclass_precision(preds, target, num_classes=3)
-        tensor(0.8333)
+        tensor(0.7500)
         >>> multiclass_precision(preds, target, num_classes=3, average=None)
         tensor([1.0000, 0.5000, 1.0000])
 
@@ -230,7 +230,7 @@ def multiclass_precision(
         >>> target = tensor([[[0, 1], [2, 1], [0, 2]], [[1, 1], [2, 0], [1, 2]]])
         >>> preds = tensor([[[0, 2], [2, 0], [0, 1]], [[2, 2], [2, 1], [1, 0]]])
         >>> multiclass_precision(preds, target, num_classes=3, multidim_average='samplewise')
-        tensor([0.3889, 0.2778])
+        tensor([0.5000, 0.3333])
         >>> multiclass_precision(preds, target, num_classes=3, multidim_average='samplewise', average=None)
         tensor([[0.6667, 0.0000, 0.5000],
                 [0.0000, 0.5000, 0.3333]])
@@ -261,7 +261,7 @@ def multilabel_precision(
     target: Tensor,
     num_labels: int,
     threshold: float = 0.5,
-    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "macro",
+    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "micro",
     multidim_average: Literal["global", "samplewise"] = "global",
     ignore_index: Optional[int] = None,
     validate_args: bool = True,
@@ -326,7 +326,7 @@ def multilabel_precision(
         >>> target = tensor([[0, 1, 0], [1, 0, 1]])
         >>> preds = tensor([[0, 0, 1], [1, 0, 1]])
         >>> multilabel_precision(preds, target, num_labels=3)
-        tensor(0.5000)
+        tensor(0.6667)
         >>> multilabel_precision(preds, target, num_labels=3, average=None)
         tensor([1.0000, 0.0000, 0.5000])
 
@@ -335,7 +335,7 @@ def multilabel_precision(
         >>> target = tensor([[0, 1, 0], [1, 0, 1]])
         >>> preds = tensor([[0.11, 0.22, 0.84], [0.73, 0.33, 0.92]])
         >>> multilabel_precision(preds, target, num_labels=3)
-        tensor(0.5000)
+        tensor(0.6667)
         >>> multilabel_precision(preds, target, num_labels=3, average=None)
         tensor([1.0000, 0.0000, 0.5000])
 
@@ -345,7 +345,7 @@ def multilabel_precision(
         >>> preds = tensor([[[0.59, 0.91], [0.91, 0.99], [0.63, 0.04]],
         ...                 [[0.38, 0.04], [0.86, 0.780], [0.45, 0.37]]])
         >>> multilabel_precision(preds, target, num_labels=3, multidim_average='samplewise')
-        tensor([0.3333, 0.0000])
+        tensor([0.4000, 0.0000])
         >>> multilabel_precision(preds, target, num_labels=3, multidim_average='samplewise', average=None)
         tensor([[0.5000, 0.5000, 0.0000],
                 [0.0000, 0.0000, 0.0000]])
@@ -451,7 +451,7 @@ def multiclass_recall(
     preds: Tensor,
     target: Tensor,
     num_classes: int,
-    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "macro",
+    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "micro",
     top_k: int = 1,
     multidim_average: Literal["global", "samplewise"] = "global",
     ignore_index: Optional[int] = None,
@@ -519,7 +519,7 @@ def multiclass_recall(
         >>> target = tensor([2, 1, 0, 0])
         >>> preds = tensor([2, 1, 0, 1])
         >>> multiclass_recall(preds, target, num_classes=3)
-        tensor(0.8333)
+        tensor(0.7500)
         >>> multiclass_recall(preds, target, num_classes=3, average=None)
         tensor([0.5000, 1.0000, 1.0000])
 
@@ -531,7 +531,7 @@ def multiclass_recall(
         ...                 [0.71, 0.09, 0.20],
         ...                 [0.05, 0.82, 0.13]])
         >>> multiclass_recall(preds, target, num_classes=3)
-        tensor(0.8333)
+        tensor(0.7500)
         >>> multiclass_recall(preds, target, num_classes=3, average=None)
         tensor([0.5000, 1.0000, 1.0000])
 
@@ -540,7 +540,7 @@ def multiclass_recall(
         >>> target = tensor([[[0, 1], [2, 1], [0, 2]], [[1, 1], [2, 0], [1, 2]]])
         >>> preds = tensor([[[0, 2], [2, 0], [0, 1]], [[2, 2], [2, 1], [1, 0]]])
         >>> multiclass_recall(preds, target, num_classes=3, multidim_average='samplewise')
-        tensor([0.5000, 0.2778])
+        tensor([0.5000, 0.3333])
         >>> multiclass_recall(preds, target, num_classes=3, multidim_average='samplewise', average=None)
         tensor([[1.0000, 0.0000, 0.5000],
                 [0.0000, 0.3333, 0.5000]])
@@ -571,7 +571,7 @@ def multilabel_recall(
     target: Tensor,
     num_labels: int,
     threshold: float = 0.5,
-    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "macro",
+    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "micro",
     multidim_average: Literal["global", "samplewise"] = "global",
     ignore_index: Optional[int] = None,
     validate_args: bool = True,

src/torchmetrics/functional/classification/specificity.py

@@ -132,7 +132,7 @@ def multiclass_specificity(
     preds: Tensor,
     target: Tensor,
     num_classes: int,
-    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "macro",
+    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "micro",
     top_k: int = 1,
     multidim_average: Literal["global", "samplewise"] = "global",
     ignore_index: Optional[int] = None,
@@ -198,7 +198,7 @@ def multiclass_specificity(
         >>> target = tensor([2, 1, 0, 0])
         >>> preds = tensor([2, 1, 0, 1])
         >>> multiclass_specificity(preds, target, num_classes=3)
-        tensor(0.8889)
+        tensor(0.8750)
         >>> multiclass_specificity(preds, target, num_classes=3, average=None)
         tensor([1.0000, 0.6667, 1.0000])
 
@@ -210,7 +210,7 @@ def multiclass_specificity(
         ...                 [0.71, 0.09, 0.20],
         ...                 [0.05, 0.82, 0.13]])
         >>> multiclass_specificity(preds, target, num_classes=3)
-        tensor(0.8889)
+        tensor(0.8750)
         >>> multiclass_specificity(preds, target, num_classes=3, average=None)
         tensor([1.0000, 0.6667, 1.0000])
 
@@ -219,7 +219,7 @@ def multiclass_specificity(
         >>> target = tensor([[[0, 1], [2, 1], [0, 2]], [[1, 1], [2, 0], [1, 2]]])
         >>> preds = tensor([[[0, 2], [2, 0], [0, 1]], [[2, 2], [2, 1], [1, 0]]])
         >>> multiclass_specificity(preds, target, num_classes=3, multidim_average='samplewise')
-        tensor([0.7500, 0.6556])
+        tensor([0.7500, 0.6667])
         >>> multiclass_specificity(preds, target, num_classes=3, multidim_average='samplewise', average=None)
         tensor([[0.7500, 0.7500, 0.7500],
                 [0.8000, 0.6667, 0.5000]])
@@ -240,7 +240,7 @@ def multilabel_specificity(
     target: Tensor,
     num_labels: int,
     threshold: float = 0.5,
-    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "macro",
+    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "micro",
     multidim_average: Literal["global", "samplewise"] = "global",
     ignore_index: Optional[int] = None,
     validate_args: bool = True,

src/torchmetrics/functional/classification/stat_scores.py

@@ -220,7 +220,7 @@ def binary_stat_scores(
 def _multiclass_stat_scores_arg_validation(
     num_classes: int,
     top_k: int = 1,
-    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "macro",
+    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "micro",
     multidim_average: Literal["global", "samplewise"] = "global",
     ignore_index: Optional[int] = None,
     zero_division: float = 0,
@@ -369,7 +369,7 @@ def _multiclass_stat_scores_update(
     target: Tensor,
     num_classes: int,
     top_k: int = 1,
-    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "macro",
+    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "micro",
     multidim_average: Literal["global", "samplewise"] = "global",
     ignore_index: Optional[int] = None,
 ) -> tuple[Tensor, Tensor, Tensor, Tensor]:
@@ -450,7 +450,7 @@ def _multiclass_stat_scores_compute(
     fp: Tensor,
     tn: Tensor,
     fn: Tensor,
-    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "macro",
+    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "micro",
     multidim_average: Literal["global", "samplewise"] = "global",
 ) -> Tensor:
     """Stack statistics and compute support also.
@@ -478,7 +478,7 @@ def multiclass_stat_scores(
     preds: Tensor,
     target: Tensor,
     num_classes: int,
-    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "macro",
+    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "micro",
     top_k: int = 1,
     multidim_average: Literal["global", "samplewise"] = "global",
     ignore_index: Optional[int] = None,
@@ -591,7 +591,7 @@ def multiclass_stat_scores(
 def _multilabel_stat_scores_arg_validation(
     num_labels: int,
     threshold: float = 0.5,
-    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "macro",
+    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "micro",
     multidim_average: Literal["global", "samplewise"] = "global",
     ignore_index: Optional[int] = None,
     zero_division: float = 0,
@@ -715,7 +715,7 @@ def _multilabel_stat_scores_compute(
     fp: Tensor,
     tn: Tensor,
     fn: Tensor,
-    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "macro",
+    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "micro",
     multidim_average: Literal["global", "samplewise"] = "global",
 ) -> Tensor:
     """Stack statistics and compute support also.
@@ -742,7 +742,7 @@ def multilabel_stat_scores(
     target: Tensor,
     num_labels: int,
     threshold: float = 0.5,
-    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "macro",
+    average: Optional[Literal["micro", "macro", "weighted", "none"]] = "micro",
     multidim_average: Literal["global", "samplewise"] = "global",
     ignore_index: Optional[int] = None,
     validate_args: bool = True,