add module default template

README.md

@@ -1,12 +1,50 @@
 ---
-title: Keywords Evaluate
-emoji: 🔥
-colorFrom: blue
-colorTo: yellow
+title: Keywords_evaluate
+datasets:
+-  GeoBenchmark
+tags:
+- evaluate
+- metric
+description: "TODO: add a description here"
 sdk: gradio
-sdk_version: 6.5.1
+sdk_version: 3.19.1
 app_file: app.py
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Metric Card for Keywords_evaluate
+
+***Module Card Instructions:*** *Fill out the following subsections. Feel free to take a look at existing metric cards if you'd like examples.*
+
+## Metric Description
+*Give a brief overview of this metric, including what task(s) it is usually used for, if any.*
+
+## How to Use
+*Give general statement of how to use the metric*
+
+*Provide simplest possible example for using the metric*
+
+### Inputs
+*List all input arguments in the format below*
+- **input_field** *(type): Definition of input, with explanation if necessary. State any default value(s).*
+
+### Output Values
+
+*Explain what this metric outputs and provide an example of what the metric output looks like. Modules should return a dictionary with one or multiple key-value pairs, e.g. {"bleu" : 6.02}*
+
+*State the range of possible values that the metric's output can take, as well as what in that range is considered good. For example: "This metric can take on any value between 0 and 100, inclusive. Higher scores are better."*
+
+#### Values from Popular Papers
+*Give examples, preferrably with links to leaderboards or publications, to papers that have reported this metric, along with the values they have reported.*
+
+### Examples
+*Give code examples of the metric being used. Try to include examples that clear up any potential ambiguity left from the metric description above. If possible, provide a range of examples that show both typical and atypical results, as well as examples where a variety of input parameters are passed.*
+
+## Limitations and Bias
+*Note any known limitations or biases that the metric has, with links and references if possible.*
+
+## Citation
+*Cite the source where this metric was introduced.*
+
+## Further References
+*Add any useful further references.*

app.py

@@ -0,0 +1,6 @@
+import evaluate
+from evaluate.utils import launch_gradio_widget
+
+
+module = evaluate.load("rfr2003/keywords_evaluate")
+launch_gradio_widget(module)

keywords_evaluate.py

@@ -0,0 +1,122 @@
+# 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
+import re
+
+
+# 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 metric aims to evaluate LM generations where it has to predict one or multiple keywords.
+"""
+
+
+# TODO: Add description of the arguments of the module here
+_KWARGS_DESCRIPTION = """
+Calculates Accuracy between generations and gold answers in a Keyword generation context.
+Args:
+    generations: list of predictions to score. Each predictions
+        should be a string generated by a LM model.
+    golds: list of reference for each prediction. Each
+        reference should be a list of strings only. Each string should be a keyword.
+Returns:
+    accuracy: 1 if the set of keywords generated matches the set of gold ones in case strict is True. If strict is False, only one keyword from the set generated must match at least one gold keyword. 0 otherwise. 
+Examples:
+    Here is an exemple on how to use the metric:
+
+    >>> metric = evaluate.load("rfr2003/keywords_evaluate")
+    >>> results = metric.compute(generations=["yes", "no"], golds=[["yes"], ["yes"]], keywords={'yes', 'no'})
+    >>> print(results)
+    {'accuracy': 0.5}
+"""
+
+
+@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
+class Keywords_evaluate(evaluate.Metric):
+    """TODO: Short description of my evaluation module."""
+
+    def _info(self):
+        # TODO: Specifies the evaluate.EvaluationModuleInfo object
+        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('string'),
+                'references': datasets.Sequence(Value('string')),
+            }),
+        )
+
+    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, generations, golds, keywords={'yes', 'no'}, strict=True):
+        '''Calculate Accuracy scores between model generations and golden answers where the task is to generate the good(s) keyword(s) among a list of them. If strict is True, we expect to find all the expected keywords generated, if not we want only one'''
+        assert len(generations) == len(golds)
+        assert isinstance(golds, list)
+        
+        correct, total = 0, 0
+        
+        if keywords:
+            pattern = r"\b(" + "|".join(map(re.escape, keywords)) + r")\b"
+            
+        else:
+            subs = ['[', ']', '(', ')', ' ']
+            pattern = r'(' + '|'.join(map(re.escape, subs)) + r')'
+            
+        for gen, gold in zip(generations, golds):
+            #each gold must be a list
+            for i in range(len(gold)):
+                gold[i] = str(gold[i]).lower().strip()
+            if keywords:
+                find = re.findall(pattern, gen.strip().lower())
+            else:
+                find = re.sub(pattern, "", gen).split(',')
+                
+            f_gold = set(gold)
+            if strict:
+                f_ans = set(find)
+                if len(f_ans.difference(f_gold)) == 0:
+                    correct += 1
+            else:
+                f_ans = find[0]
+                for i in range(len(gold)):
+                    if f_ans == gold[i]:
+                        correct += 1
+                        f_gold = gold[i]
+    
+            total += 1
+    
+        metrics = {}
+        metrics.update({
+            'accuracy': correct/total,  
+        })
+    
+        return metrics

requirements.txt

@@ -0,0 +1 @@
+git+https://github.com/huggingface/evaluate@main

tests.py

@@ -0,0 +1,23 @@
+test_cases = [
+    {
+        "generations": ["yes", "no"],
+        "golds": [["yes"], ["yes"]],
+        "keywords": {'yes', 'no'}
+        "strict": True,
+        "result": {"accuracy": 1.0}
+    },
+    {
+        "generations": ["[up, left]", "[right]"],
+        "golds": [['up', 'left'], ['right', 'down']],
+        "keywords": {'up', 'left', 'right', 'down'}
+        "strict": True,
+        "result": {"accuracy": 0.5}
+    },
+    {
+        "generations": ["[up, left]", "[right]"],
+        "golds": [['up', 'left'], ['right', 'down']],
+        "keywords": {'up', 'left', 'right', 'down'}
+        "strict": False,
+        "result": {"accuracy": 1.0}
+    }
+]