modified: average_precision.py

average_precision.py

@@ -11,30 +11,50 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""TODO: Add a description here."""
+"""Average Precision"""
 
 import evaluate
 import datasets
+from sklearn.metrics import average_precision_score
 
 
 # TODO: Add BibTeX citation
 _CITATION = """\
 @InProceedings{huggingface:module,
 title = {A great new module},
-authors={huggingface, Inc.},
-year={2020}
+authors={chanelcolgate, Inc.},
+year={2023}
 }
 """
 
 # TODO: Add description of the module here
 _DESCRIPTION = """\
-This new module is designed to solve this great ML task and is crafted with a lot of care.
+    Average Precision
 """
 
 
 # TODO: Add description of the arguments of the module here
 _KWARGS_DESCRIPTION = """
-Calculates how good are predictions given some references, using certain scores
+Note: To be consistent with the `evaluate` input conventions the scikit-learn inputs are renamed:
+- `y_true`: `references`
+- `y_pred`: `prediction_scores`
+
+Scikit-learn docstring:
+Average precision score.
+
+Compute average precision (AP) from prediction scores.
+AP summarizes a precision-recall curve as the weighted mean of precisions
+achieved at each threshold, with the increase in recall from the previous
+threshold used as the weight:
+.. math::
+    \\text{AP} = \\sum_n (R_n - R_{n-1}) P_n
+where :math:`P_n` and :math:`R_n` are the precision and recall at the nth
+threshold [1]_. This implementation is not interpolated and is different
+from computing the area under the precision-recall curve with the
+trapezoidal rule, which uses linear interpolation and can be too optimistic.
+Note: this implementation is restricted to the binary classification task or
+multilabel classification task.
+Read more in the :ref:`User Guide <precision_recall_f_measure_metrics`.
 Args:
     predictions: list of predictions to score. Each predictions
         should be a string with tokens separated by spaces.
@@ -57,7 +77,9 @@ Examples:
 BAD_WORDS_URL = "http://url/to/external/resource/bad_words.txt"
 
 
-@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
+@evaluate.utils.file_utils.add_start_docstrings(
+    _DESCRIPTION, _KWARGS_DESCRIPTION
+)
 class AveragePrecision(evaluate.Metric):
     """TODO: Short description of my evaluation module."""
 
@@ -70,15 +92,17 @@ 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(
+                {
+                    "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):
@@ -89,7 +113,9 @@ class AveragePrecision(evaluate.Metric):
     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)
+        accuracy = sum(i == j for i, j in zip(predictions, references)) / len(
+            predictions
+        )
         return {
             "accuracy": accuracy,
-        }
+        }

requirements.txt

@@ -1 +1,2 @@
-git+https://github.com/huggingface/evaluate@main
+git+https://github.com/huggingface/evaluate@main
+scikit-learn