Update classification_report.py

README.md

@@ -1,15 +1,16 @@
 ---
 title: classification_report
-datasets:
--  
 tags:
 - evaluate
 - metric
-description: "TODO: add a description here"
+description: >-
+  a classification report is a simple tool to compute multiple metrics such as:
+  accuracy precision/recall/f1-score by class. mean/weighted average.
 sdk: gradio
 sdk_version: 3.0.2
 app_file: app.py
 pinned: false
+license: apache-2.0
 ---
 
 # Metric Card for classification_report

classification_report.py

@@ -1,4 +1,4 @@
-# Copyright 2020 The HuggingFace Datasets Authors and the current dataset script contributor.
+# Copyright 2020 The HuggingFace Evaluate Authors.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -11,85 +11,40 @@
 # 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."""
+""" classification_report metric. """
+from typing import Optional
 
+import sklearn
 import evaluate
 import datasets
 
 
-# TODO: Add BibTeX citation
-_CITATION = """\
-@InProceedings{huggingface:module,
-title = {A great new module},
-authors={huggingface, Inc.},
-year={2020}
-}
-"""
-
-# 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.
-"""
-
-
-# TODO: Add description of the arguments of the module here
-_KWARGS_DESCRIPTION = """
-Calculates how good are predictions given some references, using certain scores
-Args:
-    predictions: list of predictions to score. Each predictions
-        should be a string with tokens separated by spaces.
-    references: list of reference for each prediction. Each
-        reference should be a string with tokens separated by spaces.
-Returns:
-    accuracy: description of the first score,
-    another_score: description of the second score,
-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}
-"""
-
-# 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)
-class classification_report(evaluate.Metric):
-    """TODO: Short description of my evaluation module."""
-
-    def _info(self):
-        # TODO: Specifies the evaluate.EvaluationModuleInfo object
+class ClassificationReportModule(evaluate.Metric):
+    """
+    Local metric used for classification task based on sklearn classiication_report().
+    a classification report is a simple tool to compute multiple metrics such as:
+        - accuracy
+        - precision/recall/f1-score by class.
+        - mean/weighted average.
+    """
+    def _info(self) -> evaluate.MetricInfo:
         return evaluate.MetricInfo(
-            # This is the description that will appear on the modules page.
-            module_type="metric",
-            description=_DESCRIPTION,
-            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'),
-            }),
-            # 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"]
+            description="Metric based on sklearn classification_report() method.",
+            citation="",
+            inputs_description="",
+            features=datasets.Features(
+                {
+                    "predictions": datasets.Sequence(datasets.Value("int32")),
+                    "references": datasets.Sequence(datasets.Value("int32")),
+                }
+                if self.config_name == "multilabel"
+                else {
+                    "predictions": datasets.Value("int32"),
+                    "references": datasets.Value("int32"),
+                }
+            ),
+            reference_urls=[""],
         )
 
-    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)
-        return {
-            "accuracy": accuracy,
-        }
+    def _compute(self, *, predictions=None, references=None, **kwargs) -> Optional[dict]:
+        return sklearn.metrics.classification_report(references, predictions)