Create false_positive_rate.py

false_positive_rate.py

@@ -0,0 +1,58 @@
+import datasets
+from sklearn.metrics import confusion_matrix
+import evaluate
+
+_DESCRIPTION = """
+FPR is the proportion of negative cases incorrectly identified as positive cases in the data (i.e. the probability that false alerts will be raised). It is defined as:
+FPR = FP / (FP + TN)
+ Where:
+TN: True negative
+FP: False positive
+"""
+
+
+_KWARGS_DESCRIPTION = """
+Args:
+    predictions (`list` of `int`): Predicted labels.
+    references (`list` of `int`): Ground truth (correct) target values.
+    normalize (`boolean`): Normalizes confusion matrix over the true (rows), predicted (columns) conditions or all the population. If None, confusion matrix will not be normalized.
+    sample_weight (`list` of `float`): Sample weights. Defaults to None.
+Returns:
+    false positive rate (`float` or `int`): FPR score. Minimum possible value is 0. Maximum possible value is 1.0.
+"""
+
+_CITATION = """
+@misc{ enwiki:1178431122,
+    author = "{Wikipedia contributors}",
+    title = "False positives and false negatives --- {Wikipedia}{,} The Free Encyclopedia",
+    year = "2023",
+    url = "https://en.wikipedia.org/w/index.php?title=False_positives_and_false_negatives&oldid=1178431122",
+    note = "[Online; accessed 17-November-2023]"
+}
+"""
+
+@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
+class FPR(evaluate.Metric):
+    def _info(self):
+        return evaluate.MetricInfo(
+            description=_DESCRIPTION,
+            citation=_CITATION,
+            inputs_description=_KWARGS_DESCRIPTION,
+            features=datasets.Features(
+                {
+                    "predictions": datasets.Sequence(datasets.Value("int32")),
+                    "references": datasets.Sequence(datasets.Value("int32")),
+                }
+                if self.config_name == "multilabel"
+                else {
+                    "predictions": datasets.Value("int32"),
+                    "references": datasets.Value("int32"),
+                }
+            ),
+            reference_urls=["https://scikit-learn.org/stable/modules/generated/sklearn.metrics.confusion_matrix.html"],
+        )
+
+    def _compute(self, predictions, references, normalize=None, sample_weight=None):
+        tn, fp, fn, tp = confusion_matrix(references, predictions, normalize=normalize, sample_weight=sample_weight).ravel()
+        fpr = fp / (fp + tn)
+        return {"false_positive_rate": fpr}