modified: average_precision.py

average_precision.py

@@ -86,19 +86,24 @@ Args:
 Returns:
     accuracy: description of the first score,
     another_score: description of the second score,
+    average_precision: float
+        Average precision score.
+    See Also
+    roc_auc_score: Compute the area under the ROC curve.
+    precision_recall_curve: Compute precision-recall pairs for different
+        probability thresholds.
 Examples:
     Examples should be written in doctest format, and should illustrate how
     to use the function.
 
-    >>> my_new_module = evaluate.load("my_new_module")
-    >>> results = my_new_module.compute(references=[0, 1], predictions=[0, 1])
-    >>> print(results)
-    {'accuracy': 1.0}
+    >>> import numpy as np
+    >>> from sklearn.metrics import average_precision_score
+    >>> y_true = np.array([0, 0, 1, 1])
+    >>> y_scores = np.array([0.1, 0.4, 0.35, 0.8])
+    >>> average_precision_score(y_true, y_scores)
+    0.8333333333333333
 """
 
-# TODO: Define external resources urls if needed
-BAD_WORDS_URL = "http://url/to/external/resource/bad_words.txt"
-
 
 @evaluate.utils.file_utils.add_start_docstrings(
     _DESCRIPTION, _KWARGS_DESCRIPTION
@@ -115,17 +120,29 @@ class AveragePrecision(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(
+                    {
+                        "references": datasets.Value("int64"),
+                        "prediction_scores": datasets.Value("float"),
+                    }
+                ),
+                datasets.Features(
+                    {
+                        "references": datasets.Sequence(
+                            datasets.Value("int64")
+                        ),
+                        "prediction_scores": datasets.Sequence(
+                            datasets.Value("float")
+                        ),
+                    }
+                ),
+            ],
             # Homepage of the module for documentation
-            homepage="http://module.homepage",
+            homepage="https://scikit-learn.org/stable/modules/generated/sklearn.metrics.average_precision_score.html",
             # 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"],
+            codebase_urls=["https://github.com/scikit-learn/scikit-learn"],
+            reference_urls=["https://scikit-learn.org/stable/index.html"],
         )
 
     def _download_and_prepare(self, dl_manager):
@@ -133,12 +150,22 @@ class AveragePrecision(evaluate.Metric):
         # TODO: Download external resources if needed
         pass
 
-    def _compute(self, predictions, references):
+    def _compute(
+        self,
+        references,
+        prediction_scores,
+        average="macro",
+        pos_label=1,
+        sample_weight=None,
+    ):
         """Returns the scores"""
         # TODO: Compute the different scores of the module
-        accuracy = sum(i == j for i, j in zip(predictions, references)) / len(
-            predictions
-        )
         return {
-            "accuracy": accuracy,
+            "average_precision_score": average_precision_score(
+                y_true=references,
+                y_score=prediction_scores,
+                average=average,
+                pos_label=pos_label,
+                sample_weight=sample_weight,
+            )
         }