add module default template

README.md

@@ -1,12 +1,50 @@
 ---
-title: Place Gen Evaluate
-emoji: 😻
-colorFrom: green
-colorTo: indigo
+title: Place_gen_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 Place_gen_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/place_gen_evaluate")
+launch_gradio_widget(module)

place_gen_evaluate.py

@@ -0,0 +1,127 @@
+# 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 numpy as np
+import ast
+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 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}
+"""
+
+
+@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
+class Place_gen_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({
+                'generations': datasets.Value('int64'),
+                'golds': datasets.Sequence(datasets.Value('int64')),
+            }),
+        )
+
+    def _download_and_prepare(self, dl_manager):
+        """Optional: download external resources useful to compute the scores"""
+        # TODO: Download external resources if needed
+        self.bleu = evaluate.load('bleu')
+        self.bert_score = evaluate.load('bertscore')
+
+    def _compute(self, generations, golds):
+    '''Calculate Accuracy and BLEU-1 scores between model generations and golden answers.
+       We expect a set of generated answers and want to find it among a set of gold answers.'''
+        assert len(generations) == len(golds)
+        assert isinstance(golds, list)
+    
+        predictions, references = [], []
+        precisions, recalls, means_pre_rec = [], [], []
+    
+        for gen, gold in zip(generations, golds):
+            gen = gen.strip().lower()
+            #each gold must be a list of str
+            for i in range(len(gold)):
+                gold[i] = gold[i].lower().strip()
+    
+            try:
+                f_ans = ast.literal_eval(gen)
+            except:
+                subs = ['[', ']', '(', ')', ' ']
+                pattern = r'(' + '|'.join(map(re.escape, subs)) + r')'
+                f_ans = re.sub(pattern, "", gen).split(',')
+                
+            f_ans = list(set([a.lower().strip() for a in f_ans])) #get rid of duples values
+            f_gold = list(set(gold))
+    
+            precision, recall = calculate_pre_rec(f_ans, f_gold, Levenshtein.distance)
+    
+            precisions.append(precision)
+            recalls.append(recall)
+            means_pre_rec.append((precision+recall)/2)
+    
+            predictions.append(gen)
+            references.append(gold)
+    
+        metrics = {f"bert_score_{k}":np.mean(v).item() for k,v in bert_score.compute(predictions=predictions, references=references, lang="en").items() if k in ['recall', 'precision', 'f1']}
+        metrics.update({ 
+            'bleu-1': bleu.compute(predictions=predictions, references=references, max_order=1)['bleu'],
+            'macro-precision': np.mean(precisions).item(),
+            'macro-rappel': np.mean(recalls).item(),
+            'macro-mean': np.mean(means_pre_rec).item(),
+            'median absolute error': median(means_pre_rec)
+        })
+    
+        return metrics

requirements.txt

@@ -0,0 +1,7 @@
+git+https://github.com/huggingface/evaluate@main
+transformers
+torch
+datasets
+numpy
+bert_score
+levenshtein

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}
+    }
+]