# Source code for ignite.contrib.metrics.roc_auc

from typing import Any, Callable, Tuple, Union

import torch

from ignite.metrics import EpochMetric

def roc_auc_compute_fn(y_preds: torch.Tensor, y_targets: torch.Tensor) -> float:
from sklearn.metrics import roc_auc_score

y_true = y_targets.cpu().numpy()
y_pred = y_preds.cpu().numpy()
return roc_auc_score(y_true, y_pred)

def roc_auc_curve_compute_fn(y_preds: torch.Tensor, y_targets: torch.Tensor) -> Tuple[Any, Any, Any]:
from sklearn.metrics import roc_curve

y_true = y_targets.numpy()
y_pred = y_preds.numpy()
return roc_curve(y_true, y_pred)

[docs]class ROC_AUC(EpochMetric):
"""Computes Area Under the Receiver Operating Characteristic Curve (ROC AUC)
accumulating predictions and the ground-truth during an epoch and applying
sklearn.metrics.roc_auc_score <https://scikit-learn.org/stable/modules/generated/
sklearn.metrics.roc_auc_score.html#sklearn.metrics.roc_auc_score>_ .

Args:
output_transform: a callable that is used to transform the
:class:~ignite.engine.engine.Engine's process_function's output into the
form expected by the metric. This can be useful if, for example, you have a multi-output model and
you want to compute the metric with respect to one of the outputs.
check_compute_fn: Default False. If True, roc_curve
<https://scikit-learn.org/stable/modules/generated/sklearn.metrics.roc_auc_score.html#
sklearn.metrics.roc_auc_score>_ is run on the first batch of data to ensure there are
no issues. User will be warned in case there are any issues computing the function.
device: optional device specification for internal storage.

ROC_AUC expects y to be comprised of 0's and 1's. y_pred must either be probability estimates or confidence
values. To apply an activation to y_pred, use output_transform as shown below:

.. code-block:: python

def activated_output_transform(output):
y_pred, y = output
y_pred = torch.sigmoid(y_pred)
return y_pred, y

roc_auc = ROC_AUC(activated_output_transform)

"""

def __init__(
self,
output_transform: Callable = lambda x: x,
check_compute_fn: bool = False,
device: Union[str, torch.device] = torch.device("cpu"),
):

try:
from sklearn.metrics import roc_auc_score  # noqa: F401
except ImportError:
raise RuntimeError("This contrib module requires sklearn to be installed.")

super(ROC_AUC, self).__init__(
roc_auc_compute_fn, output_transform=output_transform, check_compute_fn=check_compute_fn, device=device,
)

[docs]class RocCurve(EpochMetric):
by accumulating predictions and the ground-truth during an epoch and applying
sklearn.metrics.roc_curve <https://scikit-learn.org/stable/modules/generated/
sklearn.metrics.roc_curve.html#sklearn.metrics.roc_curve>_ .

Args:
output_transform: a callable that is used to transform the
:class:~ignite.engine.engine.Engine's process_function's output into the
form expected by the metric. This can be useful if, for example, you have a multi-output model and
you want to compute the metric with respect to one of the outputs.
check_compute_fn: Default False. If True, sklearn.metrics.roc_curve
<https://scikit-learn.org/stable/modules/generated/sklearn.metrics.roc_curve.html#
sklearn.metrics.roc_curve>_ is run on the first batch of data to ensure there are
no issues. User will be warned in case there are any issues computing the function.

RocCurve expects y to be comprised of 0's and 1's. y_pred must either be probability estimates or confidence
values. To apply an activation to y_pred, use output_transform as shown below:

.. code-block:: python

def activated_output_transform(output):
y_pred, y = output
y_pred = torch.sigmoid(y_pred)
return y_pred, y

roc_auc = RocCurve(activated_output_transform)

"""

def __init__(self, output_transform: Callable = lambda x: x, check_compute_fn: bool = False) -> None:

try:
from sklearn.metrics import roc_curve  # noqa: F401
except ImportError:
raise RuntimeError("This contrib module requires sklearn to be installed.")

super(RocCurve, self).__init__(
roc_auc_curve_compute_fn, output_transform=output_transform, check_compute_fn=check_compute_fn
)