tf.metrics.auc(
labels,
predictions,
weights=None,
num_thresholds=200,
metrics_collections=None,
updates_collections=None,
curve='ROC',
name=None,
summation_method='trapezoidal'
)
Defined in tensorflow/python/ops/metrics_impl.py
.
Computes the approximate AUC via a Riemann sum.
The auc
function creates four local variables, true_positives
,
true_negatives
, false_positives
and false_negatives
that are used to
compute the AUC. To discretize the AUC curve, a linearly spaced set of
thresholds is used to compute pairs of recall and precision values. The area
under the ROC-curve is therefore computed using the height of the recall
values by the false positive rate, while the area under the PR-curve is the
computed using the height of the precision values by the recall.
This value is ultimately returned as auc
, an idempotent operation that
computes the area under a discretized curve of precision versus recall values
(computed using the aforementioned variables). The num_thresholds
variable
controls the degree of discretization with larger numbers of thresholds more
closely approximating the true AUC. The quality of the approximation may vary
dramatically depending on num_thresholds
.
For best results, predictions
should be distributed approximately uniformly
in the range [0, 1] and not peaked around 0 or 1. The quality of the AUC
approximation may be poor if this is not the case. Setting summation_method
to 'minoring' or 'majoring' can help quantify the error in the approximation
by providing lower or upper bound estimate of the AUC.
For estimation of the metric over a stream of data, the function creates an
update_op
operation that updates these variables and returns the auc
.
If weights
is None
, weights default to 1. Use weights of 0 to mask values.
Args:
labels
: ATensor
whose shape matchespredictions
. Will be cast tobool
.predictions
: A floating pointTensor
of arbitrary shape and whose values are in the range[0, 1]
.weights
: OptionalTensor
whose rank is either 0, or the same rank aslabels
, and must be broadcastable tolabels
(i.e., all dimensions must be either1
, or the same as the correspondinglabels
dimension).num_thresholds
: The number of thresholds to use when discretizing the roc curve.metrics_collections
: An optional list of collections thatauc
should be added to.updates_collections
: An optional list of collections thatupdate_op
should be added to.curve
: Specifies the name of the curve to be computed, 'ROC' [default] or 'PR' for the Precision-Recall-curve.name
: An optional variable_scope name.summation_method
: Specifies the Riemann summation method used (https://en.wikipedia.org/wiki/Riemann_sum): 'trapezoidal' [default] that applies the trapezoidal rule; 'careful_interpolation', a variant of it differing only by a more correct interpolation scheme for PR-AUC - interpolating (true/false) positives but not the ratio that is precision; 'minoring' that applies left summation for increasing intervals and right summation for decreasing intervals; 'majoring' that does the opposite. Note that 'careful_interpolation' is strictly preferred to 'trapezoidal' (to be deprecated soon) as it applies the same method for ROC, and a better one (see Davis & Goadrich 2006 for details) for the PR curve.
Returns:
auc
: A scalarTensor
representing the current area-under-curve.update_op
: An operation that increments thetrue_positives
,true_negatives
,false_positives
andfalse_negatives
variables appropriately and whose value matchesauc
.
Raises:
ValueError
: Ifpredictions
andlabels
have mismatched shapes, or ifweights
is notNone
and its shape doesn't matchpredictions
, or if eithermetrics_collections
orupdates_collections
are not a list or tuple.RuntimeError
: If eager execution is enabled.