Matthews Correlation Coefficient¶
Module Interface¶
MatthewsCorrCoef¶
- class torchmetrics.MatthewsCorrCoef(task: Optional[Literal['binary', 'multiclass', 'multilabel']] = None, threshold: float = 0.5, num_classes: Optional[int] = None, num_labels: Optional[int] = None, ignore_index: Optional[int] = None, validate_args: bool = True, **kwargs: Any)[source]
Calculates Matthews correlation coefficient . This metric measures the general correlation or quality of a classification.
This function is a simple wrapper to get the task specific versions of this metric, which is done by setting the
task
argument to either'binary'
,'multiclass'
ormultilabel
. See the documentation ofBinaryMatthewsCorrCoef
,MulticlassMatthewsCorrCoef
andMultilabelMatthewsCorrCoef
for the specific details of each argument influence and examples.- Legacy Example:
>>> target = torch.tensor([1, 1, 0, 0]) >>> preds = torch.tensor([0, 1, 0, 0]) >>> matthews_corrcoef = MatthewsCorrCoef(task='binary') >>> matthews_corrcoef(preds, target) tensor(0.5774)
BinaryMatthewsCorrCoef¶
- class torchmetrics.classification.BinaryMatthewsCorrCoef(threshold=0.5, ignore_index=None, validate_args=True, **kwargs)[source]
Calculates Matthews correlation coefficient for binary tasks. This metric measures the general correlation or quality of a classification.
As input to
forward
andupdate
the metric accepts the following input:preds
(Tensor
): A int tensor or float tensor of shape(N, ...)
. If preds is a floating point tensor with values outside [0,1] range we consider the input to be logits and will auto apply sigmoid per element. Addtionally, we convert to int tensor with thresholding using the value inthreshold
.target
(Tensor
): An int tensor of shape(N, ...)
Note
Additional dimension
...
will be flattened into the batch dimension.As output to
forward
andcompute
the metric returns the following output:bmcc
(Tensor
): A tensor containing the Binary Matthews Correlation Coefficient.
- Parameters
threshold¶ (
float
) – Threshold for transforming probability to binary (0,1) predictionsignore_index¶ (
Optional
[int
]) – Specifies a target value that is ignored and does not contribute to the metric calculationvalidate_args¶ (
bool
) – bool indicating if input arguments and tensors should be validated for correctness. Set toFalse
for faster computations.kwargs¶ (
Any
) – Additional keyword arguments, see Advanced metric settings for more info.
- Example (preds is int tensor):
>>> from torchmetrics.classification import BinaryMatthewsCorrCoef >>> target = torch.tensor([1, 1, 0, 0]) >>> preds = torch.tensor([0, 1, 0, 0]) >>> metric = BinaryMatthewsCorrCoef() >>> metric(preds, target) tensor(0.5774)
- Example (preds is float tensor):
>>> from torchmetrics.classification import BinaryMatthewsCorrCoef >>> target = torch.tensor([1, 1, 0, 0]) >>> preds = torch.tensor([0.35, 0.85, 0.48, 0.01]) >>> metric = BinaryMatthewsCorrCoef() >>> metric(preds, target) tensor(0.5774)
Initializes internal Module state, shared by both nn.Module and ScriptModule.
MulticlassMatthewsCorrCoef¶
- class torchmetrics.classification.MulticlassMatthewsCorrCoef(num_classes, ignore_index=None, validate_args=True, **kwargs)[source]
Calculates Matthews correlation coefficient for multiclass tasks. This metric measures the general correlation or quality of a classification.
As input to
forward
andupdate
the metric accepts the following input:preds
(Tensor
): A int tensor of shape(N, ...)
or float tensor of shape(N, C, ..)
. If preds is a floating point we applytorch.argmax
along theC
dimension to automatically convert probabilities/logits into an int tensor.target
(Tensor
): An int tensor of shape(N, ...)
Note
Additional dimension
...
will be flattened into the batch dimension.As output to
forward
andcompute
the metric returns the following output:mcmcc
(Tensor
): A tensor containing the Multi-class Matthews Correlation Coefficient.
- Parameters
num_classes¶ (
int
) – Integer specifing the number of classesignore_index¶ (
Optional
[int
]) – Specifies a target value that is ignored and does not contribute to the metric calculationvalidate_args¶ (
bool
) – bool indicating if input arguments and tensors should be validated for correctness. Set toFalse
for faster computations.kwargs¶ (
Any
) – Additional keyword arguments, see Advanced metric settings for more info.
- Example (pred is integer tensor):
>>> from torchmetrics.classification import MulticlassMatthewsCorrCoef >>> target = torch.tensor([2, 1, 0, 0]) >>> preds = torch.tensor([2, 1, 0, 1]) >>> metric = MulticlassMatthewsCorrCoef(num_classes=3) >>> metric(preds, target) tensor(0.7000)
- Example (pred is float tensor):
>>> from torchmetrics.classification import MulticlassMatthewsCorrCoef >>> target = torch.tensor([2, 1, 0, 0]) >>> preds = torch.tensor([ ... [0.16, 0.26, 0.58], ... [0.22, 0.61, 0.17], ... [0.71, 0.09, 0.20], ... [0.05, 0.82, 0.13], ... ]) >>> metric = MulticlassMatthewsCorrCoef(num_classes=3) >>> metric(preds, target) tensor(0.7000)
Initializes internal Module state, shared by both nn.Module and ScriptModule.
MultilabelMatthewsCorrCoef¶
- class torchmetrics.classification.MultilabelMatthewsCorrCoef(num_labels, threshold=0.5, ignore_index=None, validate_args=True, **kwargs)[source]
Calculates Matthews correlation coefficient for multilabel tasks. This metric measures the general correlation or quality of a classification.
As input to
forward
andupdate
the metric accepts the following input:preds
(Tensor
): An int or float tensor of shape(N, C, ...)
. If preds is a floating point tensor with values outside [0,1] range we consider the input to be logits and will auto apply sigmoid per element. Addtionally, we convert to int tensor with thresholding using the value inthreshold
.target
(Tensor
): An int tensor of shape(N, C, ...)
Note
Additional dimension
...
will be flattened into the batch dimension.As output to
forward
andcompute
the metric returns the following output:mlmcc
(Tensor
): A tensor containing the Multi-label Matthews Correlation Coefficient.
- Parameters
num_classes¶ – Integer specifing the number of labels
threshold¶ (
float
) – Threshold for transforming probability to binary (0,1) predictionsignore_index¶ (
Optional
[int
]) – Specifies a target value that is ignored and does not contribute to the metric calculationvalidate_args¶ (
bool
) – bool indicating if input arguments and tensors should be validated for correctness. Set toFalse
for faster computations.kwargs¶ (
Any
) – Additional keyword arguments, see Advanced metric settings for more info.
- Example (preds is int tensor):
>>> from torchmetrics.classification import MultilabelMatthewsCorrCoef >>> target = torch.tensor([[0, 1, 0], [1, 0, 1]]) >>> preds = torch.tensor([[0, 0, 1], [1, 0, 1]]) >>> metric = MultilabelMatthewsCorrCoef(num_labels=3) >>> metric(preds, target) tensor(0.3333)
- Example (preds is float tensor):
>>> from torchmetrics.classification import MultilabelMatthewsCorrCoef >>> target = torch.tensor([[0, 1, 0], [1, 0, 1]]) >>> preds = torch.tensor([[0.11, 0.22, 0.84], [0.73, 0.33, 0.92]]) >>> metric = MultilabelMatthewsCorrCoef(num_labels=3) >>> metric(preds, target) tensor(0.3333)
Initializes internal Module state, shared by both nn.Module and ScriptModule.
Functional Interface¶
matthews_corrcoef¶
- torchmetrics.functional.matthews_corrcoef(preds, target, task=None, threshold=0.5, num_classes=None, num_labels=None, ignore_index=None, validate_args=True)[source]
Calculates Matthews correlation coefficient . This metric measures the general correlation or quality of a classification.
This function is a simple wrapper to get the task specific versions of this metric, which is done by setting the
task
argument to either'binary'
,'multiclass'
ormultilabel
. See the documentation ofbinary_matthews_corrcoef()
,multiclass_matthews_corrcoef()
andmultilabel_matthews_corrcoef()
for the specific details of each argument influence and examples.- Legacy Example:
>>> target = torch.tensor([1, 1, 0, 0]) >>> preds = torch.tensor([0, 1, 0, 0]) >>> matthews_corrcoef(preds, target, task="multiclass", num_classes=2) tensor(0.5774)
- Return type
binary_matthews_corrcoef¶
- torchmetrics.functional.classification.binary_matthews_corrcoef(preds, target, threshold=0.5, ignore_index=None, validate_args=True)[source]
Calculates Matthews correlation coefficient for binary tasks. This metric measures the general correlation or quality of a classification.
Accepts the following input tensors:
preds
(int or float tensor):(N, ...)
. If preds is a floating point tensor with values outside [0,1] range we consider the input to be logits and will auto apply sigmoid per element. Addtionally, we convert to int tensor with thresholding using the value inthreshold
.target
(int tensor):(N, ...)
Additional dimension
...
will be flattened into the batch dimension.- Parameters
threshold¶ (
float
) – Threshold for transforming probability to binary (0,1) predictionsignore_index¶ (
Optional
[int
]) – Specifies a target value that is ignored and does not contribute to the metric calculationvalidate_args¶ (
bool
) – bool indicating if input arguments and tensors should be validated for correctness. Set toFalse
for faster computations.kwargs¶ – Additional keyword arguments, see Advanced metric settings for more info.
- Example (preds is int tensor):
>>> from torchmetrics.functional.classification import binary_matthews_corrcoef >>> target = torch.tensor([1, 1, 0, 0]) >>> preds = torch.tensor([0, 1, 0, 0]) >>> binary_matthews_corrcoef(preds, target) tensor(0.5774)
- Example (preds is float tensor):
>>> from torchmetrics.functional.classification import binary_matthews_corrcoef >>> target = torch.tensor([1, 1, 0, 0]) >>> preds = torch.tensor([0.35, 0.85, 0.48, 0.01]) >>> binary_matthews_corrcoef(preds, target) tensor(0.5774)
- Return type
multiclass_matthews_corrcoef¶
- torchmetrics.functional.classification.multiclass_matthews_corrcoef(preds, target, num_classes, ignore_index=None, validate_args=True)[source]
Calculates Matthews correlation coefficient for multiclass tasks. This metric measures the general correlation or quality of a classification.
Accepts the following input tensors:
preds
:(N, ...)
(int tensor) or(N, C, ..)
(float tensor). If preds is a floating point we applytorch.argmax
along theC
dimension to automatically convert probabilities/logits into an int tensor.target
(int tensor):(N, ...)
Additional dimension
...
will be flattened into the batch dimension.- Parameters
num_classes¶ (
int
) – Integer specifing the number of classesignore_index¶ (
Optional
[int
]) – Specifies a target value that is ignored and does not contribute to the metric calculationvalidate_args¶ (
bool
) – bool indicating if input arguments and tensors should be validated for correctness. Set toFalse
for faster computations.kwargs¶ – Additional keyword arguments, see Advanced metric settings for more info.
- Example (pred is integer tensor):
>>> from torchmetrics.functional.classification import multiclass_matthews_corrcoef >>> target = torch.tensor([2, 1, 0, 0]) >>> preds = torch.tensor([2, 1, 0, 1]) >>> multiclass_matthews_corrcoef(preds, target, num_classes=3) tensor(0.7000)
- Example (pred is float tensor):
>>> from torchmetrics.functional.classification import multiclass_matthews_corrcoef >>> target = torch.tensor([2, 1, 0, 0]) >>> preds = torch.tensor([ ... [0.16, 0.26, 0.58], ... [0.22, 0.61, 0.17], ... [0.71, 0.09, 0.20], ... [0.05, 0.82, 0.13], ... ]) >>> multiclass_matthews_corrcoef(preds, target, num_classes=3) tensor(0.7000)
- Return type
multilabel_matthews_corrcoef¶
- torchmetrics.functional.classification.multilabel_matthews_corrcoef(preds, target, num_labels, threshold=0.5, ignore_index=None, validate_args=True)[source]
Calculates Matthews correlation coefficient for multilabel tasks. This metric measures the general correlation or quality of a classification.
Accepts the following input tensors:
preds
(int or float tensor):(N, C, ...)
. If preds is a floating point tensor with values outside [0,1] range we consider the input to be logits and will auto apply sigmoid per element. Addtionally, we convert to int tensor with thresholding using the value inthreshold
.target
(int tensor):(N, C, ...)
Additional dimension
...
will be flattened into the batch dimension.- Parameters
num_classes¶ – Integer specifing the number of labels
threshold¶ (
float
) – Threshold for transforming probability to binary (0,1) predictionsignore_index¶ (
Optional
[int
]) – Specifies a target value that is ignored and does not contribute to the metric calculationvalidate_args¶ (
bool
) – bool indicating if input arguments and tensors should be validated for correctness. Set toFalse
for faster computations.kwargs¶ – Additional keyword arguments, see Advanced metric settings for more info.
- Example (preds is int tensor):
>>> from torchmetrics.functional.classification import multilabel_matthews_corrcoef >>> target = torch.tensor([[0, 1, 0], [1, 0, 1]]) >>> preds = torch.tensor([[0, 0, 1], [1, 0, 1]]) >>> multilabel_matthews_corrcoef(preds, target, num_labels=3) tensor(0.3333)
- Example (preds is float tensor):
>>> from torchmetrics.functional.classification import multilabel_matthews_corrcoef >>> target = torch.tensor([[0, 1, 0], [1, 0, 1]]) >>> preds = torch.tensor([[0.11, 0.22, 0.84], [0.73, 0.33, 0.92]]) >>> multilabel_matthews_corrcoef(preds, target, num_labels=3) tensor(0.3333)
- Return type