Fixed sklearn import and added test skeleton.

balanced_accuracy.py

@@ -15,11 +15,9 @@
 
 import evaluate
 import datasets
-from sklearn.base import accuracy_score
 from sklearn.metrics import balanced_accuracy_score
 
 
-
 _DESCRIPTION = """
 Balanced Accuracy is the average of recall obtained on each class. It can be computed with:
 Balanced Accuracy = (TPR + TNR) / N
@@ -29,38 +27,6 @@ TNR: True negative rate
 N: Number of classes
 """
 
-
-_KWARGS_DESCRIPTION = """
-Args:
-    predictions (`list` of `int`): Predicted labels.
-    references (`list` of `int`): Ground truth labels.
-    normalize (`boolean`): If set to False, returns the number of correctly classified samples. Otherwise, returns the fraction of correctly classified samples. Defaults to True.
-    sample_weight (`list` of `float`): Sample weights Defaults to None.
-
-Returns:
-    accuracy (`float` or `int`): Accuracy score. Minimum possible value is 0. Maximum possible value is 1.0, or the number of examples input, if `normalize` is set to `True`.. A higher score means higher accuracy.
-
-Examples:
-
-    Example 1-A simple example
-        >>> accuracy_metric = evaluate.load("accuracy")
-        >>> results = accuracy_metric.compute(references=[0, 1, 2, 0, 1, 2], predictions=[0, 1, 1, 2, 1, 0])
-        >>> print(results)
-        {'accuracy': 0.5}
-
-    Example 2-The same as Example 1, except with `normalize` set to `False`.
-        >>> accuracy_metric = evaluate.load("accuracy")
-        >>> results = accuracy_metric.compute(references=[0, 1, 2, 0, 1, 2], predictions=[0, 1, 1, 2, 1, 0], normalize=False)
-        >>> print(results)
-        {'accuracy': 3.0}
-
-    Example 3-The same as Example 1, except with `sample_weight` set.
-        >>> accuracy_metric = evaluate.load("accuracy")
-        >>> results = accuracy_metric.compute(references=[0, 1, 2, 0, 1, 2], predictions=[0, 1, 1, 2, 1, 0], sample_weight=[0.5, 2, 0.7, 0.5, 9, 0.4])
-        >>> print(results)
-        {'accuracy': 0.8778625954198473}
-"""
-
 _KWARGS_DESCRIPTION = """
 Args:
     predictions (`list` of `int`): Predicted labels.

pytest.ini

@@ -0,0 +1,3 @@
+[pytest]
+testpaths = ./
+python_files = test_*.py

test_balanced_accuracy.py

@@ -0,0 +1,60 @@
+test_cases = [
+    {
+        "predictions": [0, 1, 0, 1, 0, 1],
+        "references":  [0, 1, 0, 1, 0, 1],
+        "sample_weight": None,
+        "adjusted": False,
+        "result": {"balanced_accuracy": 0}
+    },
+    {
+        "predictions": [0, 0, 1, 1, 1, 1],
+        "references":  [0, 0, 0, 0, 1, 1],
+        "sample_weight": None,
+        "adjusted": False,
+        "result": {"balanced_accuracy": 0}
+    },
+    {
+        "predictions": [0, 1, 1, 0, 1, 2],
+        "references":  [0, 1, 2, 0, 1, 2],
+        "sample_weight": None,
+        "adjusted": False,
+        "result": {"balanced_accuracy": 0}
+    },
+    {
+        "predictions": [0, 0, 1, 2, 1, 2],
+        "references":  [0, 0, 0, 0, 1, 2],
+        "sample_weight": None,
+        "adjusted": False,
+        "result": {"balanced_accuracy": 0}
+    },
+    {
+        "predictions": [0, 1, 1, 0, 0, 1],
+        "references":  [0, 1, 0, 1, 0, 1],
+        "sample_weight": [0.5, 0.7, 0.8, 0.9, 1.0, 0.6],
+        "adjusted": False,
+        "result": {"balanced_accuracy": 0}
+    },
+    {
+        "predictions": [0, 1, 1, 0, 0, 1],
+        "references":  [0, 1, 0, 1, 0, 1],
+        "sample_weight": None,
+        "adjusted": True,
+        "result": {"balanced_accuracy": 0}
+    },
+]
+
+import pytest
+from evaluate import load
+from sklearn.metrics import balanced_accuracy_score
+
+@pytest.mark.parametrize("test_case", test_cases)
+def test_balanced_accuracy(test_case):
+    metric = load("hyperml/balanced_accuracy")
+    result = metric.compute(
+        predictions=test_case["predictions"],
+        references=test_case["references"],
+        sample_weight=test_case["sample_weight"],
+        adjusted=test_case["adjusted"]
+    )
+    assert result["balanced_accuracy"] == balanced_accuracy_score(y_pred=test_case["predictions"], y_true=test_case["references"], sample_weight=test_case["sample_weight"], adjusted=test_case["adjusted"])
+    assert result == test_case["result"]

tests.py

@@ -1,17 +0,0 @@
-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}
-    }
-]