Add waf metric logic

waf_metric.py

@@ -62,7 +62,6 @@ class WafMetric(evaluate.Metric):
     """TODO: Short description of my evaluation module."""
 
     def _info(self):
-        # TODO: Specifies the evaluate.EvaluationModuleInfo object
         return evaluate.MetricInfo(
             # This is the description that will appear on the modules page.
             module_type="metric",
@@ -70,26 +69,40 @@ class WafMetric(evaluate.Metric):
             citation=_CITATION,
             inputs_description=_KWARGS_DESCRIPTION,
             # This defines the format of each prediction and reference
-            features=datasets.Features({
-                'predictions': datasets.Value('int64'),
-                'references': datasets.Value('int64'),
-            }),
+            features=datasets.Features(
+                {
+                    "predictions": datasets.Value("int64"),
+                    "references": datasets.Value("int64"),
+                }
+            ),
             # Homepage of the module for documentation
             homepage="http://module.homepage",
             # Additional links to the codebase or references
             codebase_urls=["http://github.com/path/to/codebase/of/new_module"],
-            reference_urls=["http://path.to.reference.url/new_module"]
+            reference_urls=["http://path.to.reference.url/new_module"],
         )
 
     def _download_and_prepare(self, dl_manager):
         """Optional: download external resources useful to compute the scores"""
-        # TODO: Download external resources if needed
         pass
 
     def _compute(self, predictions, references):
         """Returns the scores"""
-        # TODO: Compute the different scores of the module
-        accuracy = sum(i == j for i, j in zip(predictions, references)) / len(predictions)
+        white_cnt = 0
+        black_cnt = 0
+        false_white = 0
+        true_black = 0
+        for i, j in zip(predictions, references):
+            if j == 0:
+                white_cnt += 1
+                if i != j:
+                    false_white += 1
+            else:
+                black_cnt += 1
+                if i == j:
+                    true_black += 1
+
         return {
-            "accuracy": accuracy,
-        }
+            "precision": false_white / (white_cnt + 1e-6),
+            "recall": true_black / (black_cnt + 1e-6),
+        }