test config

app.py

@@ -1,6 +1,5 @@
 import evaluate
 from evaluate.utils import launch_gradio_widget
 
-
 module = evaluate.load("Glazkov/mars")
-launch_gradio_widget(module)
+launch_gradio_widget(module)

mars.py

@@ -13,9 +13,8 @@
 # limitations under the License.
 """TODO: Add a description here."""
 
-import evaluate
 import datasets
-
+import evaluate
 
 # TODO: Add BibTeX citation
 _CITATION = """\
@@ -61,7 +60,7 @@ BAD_WORDS_URL = "http://url/to/external/resource/bad_words.txt"
 class MARS(evaluate.Metric):
     """TODO: Short description of my evaluation module."""
 
-    def _info(self):
+    def _info(self) -> evaluate.MetricInfo:
         # TODO: Specifies the evaluate.EvaluationModuleInfo object
         return evaluate.MetricInfo(
             # This is the description that will appear on the modules page.
@@ -70,15 +69,17 @@ class MARS(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):
@@ -86,10 +87,12 @@ class MARS(evaluate.Metric):
         # TODO: Download external resources if needed
         pass
 
-    def _compute(self, predictions, references):
+    def _compute(self, predictions, references) -> dict[str, float]:
         """Returns the scores"""
         # TODO: Compute the different scores of the module
-        accuracy = sum(i == j for i, j in zip(predictions, references)) / len(predictions)
+        accuracy = sum(i == j for i, j in zip(predictions, references)) / len(
+            predictions
+        )
         return {
             "accuracy": accuracy,
-        }
+        }

tests.py

@@ -1,17 +1,5 @@
 test_cases = [
-    {
-        "predictions": [0, 0],
-        "references": [1, 1],
-        "result": {"metric_score": 0}
-    },
-    {
-        "predictions": [1, 1],
-        "references": [1, 1],
-        "result": {"metric_score": 1}
-    },
-    {
-        "predictions": [1, 0],
-        "references": [1, 1],
-        "result": {"metric_score": 0.5}
-    }
-]
+    {"predictions": [0, 0], "references": [1, 1], "result": {"metric_score": 0}},
+    {"predictions": [1, 1], "references": [1, 1], "result": {"metric_score": 1}},
+    {"predictions": [1, 0], "references": [1, 1], "result": {"metric_score": 0.5}},
+]