Upload 3 files

app.py

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

multiclass_sensitivity_weighted.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
+
+
+# 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 multiclass_sensitivity_weighted(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('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"]
+        )
+
+    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):
+        from collections import defaultdict
+        """Returns the scores"""
+        # TODO: Compute the different scores of the module
+        # Count true positives, false negatives, and true instance counts for each class
+        tp_counts = defaultdict(int)
+        fn_counts = defaultdict(int)
+        true_counts = defaultdict(int)
+
+        for true_label, pred_label in zip(references, predictions):
+            true_counts[true_label] += 1
+            if true_label == pred_label:
+                tp_counts[true_label] += 1
+            else:
+                fn_counts[true_label] += 1
+
+        # Calculate class-wise sensitivity
+        class_sensitivities = {}
+        total_weight = sum(true_counts.values())
+        weighted_sum = 0.0
+
+        for class_label in set(references):
+            tp = tp_counts[class_label]
+            fn = fn_counts[class_label]
+            true_instances = true_counts[class_label]
+
+            sensitivity = tp / (tp + fn) if (tp + fn) > 0 else 0
+            class_sensitivities[class_label] = sensitivity
+            weighted_sum += sensitivity * true_instances
+
+        weighted_avg_sensitivity = weighted_sum / total_weight if total_weight > 0 else 0
+        return {
+            "weighted_sensitivity": weighted_avg_sensitivity,
+        }

requirements.txt

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