add metric default template

README.md

@@ -1,12 +1,23 @@
 ---
-title: Test
-emoji: 📚
-colorFrom: red
-colorTo: gray
+title: test
+datasets:
+-  
+tags:
+- metric
 sdk: gradio
-sdk_version: 2.9.4
+sdk_version: 2.8.13
 app_file: app.py
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference
+# Metric card
+
+## Description
+
+## How to use
+
+## Examples 
+
+## References 
+
+## Limitations and bias

app.py

@@ -0,0 +1,6 @@
+from test import test
+from evaluate.utils import launch_gradio_widget
+
+
+metric = test()
+launch_gradio_widget(metric)

requirements.txt

@@ -0,0 +1,3 @@
+# TODO: fix github to release
+git+https://github.com/huggingface/evaluate.git@metrics-template
+datasets~=2.0

test.py

@@ -0,0 +1,94 @@
+# Copyright 2020 The HuggingFace Datasets Authors and the current dataset script contributor.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# 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."""
+
+import evaluate
+import datasets
+
+
+# TODO: Add BibTeX citation
+_CITATION = """\
+@InProceedings{huggingface:metric,
+title = {A great new metric},
+authors={huggingface, Inc.},
+year={2020}
+}
+"""
+
+# TODO: Add description of the metric here
+_DESCRIPTION = """\
+This new metric is designed to solve this great NLP task and is crafted with a lot of care.
+"""
+
+
+# TODO: Add description of the arguments of the metric 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_metric = evaluate.load_metric("my_new_metric")
+    >>> results = my_new_metric.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 test(evaluate.Metric):
+    """TODO: Short description of my metric."""
+
+    def _info(self):
+        # TODO: Specifies the evaluate.MetricInfo object
+        return evaluate.MetricInfo(
+            # This is the description that will appear on the metrics page.
+            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 metric for documentation
+            homepage="http://metric.homepage",
+            # Additional links to the codebase or references
+            codebase_urls=["http://github.com/path/to/codebase/of/new_metric"],
+            reference_urls=["http://path.to.reference.url/new_metric"]
+        )
+
+    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 metric
+        accuracy = sum(i == j for i, j in zip(predictions, references)) / len(predictions)
+        return {
+            "accuracy": accuracy,
+        }

tests.py

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