first commit

app.py

@@ -1,6 +1,5 @@
 import evaluate
 from evaluate.utils import launch_gradio_widget
 
-
 module = evaluate.load("symanto/clustering_evaluator")
-launch_gradio_widget(module)
+launch_gradio_widget(module)

clustering_evaluator.py

@@ -1,95 +1,95 @@
-# 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 evaluate
+from sklearn.metrics import (
+    adjusted_mutual_info_score,
+    adjusted_rand_score,
+    calinski_harabasz_score,
+    completeness_score,
+    davies_bouldin_score,
+    fowlkes_mallows_score,
+    homogeneity_score,
+    silhouette_score,
+)
+from sklearn.metrics.cluster import contingency_matrix, pair_confusion_matrix
 
-
-# TODO: Add BibTeX citation
-_CITATION = """\
-@InProceedings{huggingface:module,
-title = {A great new module},
-authors={huggingface, Inc.},
-year={2020}
+_CITATION = """
+@article{scikit-learn,
+  title={Scikit-learn: Machine Learning in {P}ython},
+  author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V.
+         and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P.
+         and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and
+         Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.},
+  journal={Journal of Machine Learning Research},
+  volume={12},
+  pages={2825--2830},
+  year={2011}
 }
 """
 
-# 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.
+This evaluator computes multiple clustering metrics to assess the quality of a clustering.
 """
 
 
-# TODO: Add description of the arguments of the module here
 _KWARGS_DESCRIPTION = """
-Calculates how good are predictions given some references, using certain scores
+Computes the quality of clustering results.
 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.
+    samples' vector representations
+    y: computed cluster labels
 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}
+    silhouete_score (float): cohesiveness and separation between clusters
+    davies_bouldin_score (float): average similarity measure of each cluster with its most similar cluster
+    calinski_harabasz_score (float): ratio of the sum of between-cluster dispersion and of within-cluster dispersion 
 """
 
-# 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 Clusteringevaluator(evaluate.Metric):
-    """TODO: Short description of my evaluation module."""
 
+@evaluate.utils.file_utils.add_start_docstrings(
+    _DESCRIPTION, _KWARGS_DESCRIPTION
+)
+class ClusteringEvaluator(evaluate.Metric):
     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('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"]
+            features=datasets.Features(
+                {
+                    "samples": datasets.Sequence(datasets.Value("float32")),
+                    "predictions": 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
-        pass
+    def _compute(self, samples, predictions, truth_labels=None):
+        unsupervised_metrics = [
+            silhouette_score,
+            davies_bouldin_score,
+            calinski_harabasz_score,
+        ]
+        supervised_metrics = [
+            adjusted_rand_score,
+            adjusted_mutual_info_score,
+            homogeneity_score,
+            completeness_score,
+            fowlkes_mallows_score,
+            contingency_matrix,
+            pair_confusion_matrix,
+        ]
+        results = {}
+
+        # Compute unsupervised metrics always
+        for fn in unsupervised_metrics:
+            results[fn.__name__] = float(fn(samples, predictions))
 
-    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,
-        }
+        # Compute supervised metrics if reference labels are passed
+        if truth_labels is not None:
+            for fn in supervised_metrics:
+                score = fn(truth_labels, predictions)
+                try:
+                    score = float(score)
+                except (AttributeError, TypeError):
+                    pass
+                results[fn.__name__] = score
+        return results

requirements.txt

@@ -1 +1,4 @@
-git+https://github.com/huggingface/evaluate@main
+evaluate
+datasets
+scikit-learn
+gradio

tests.py

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