ruff formatting + changing gradio app loading

app.py

@@ -1,6 +1,17 @@
+"""Application file."""
+
 import evaluate
-from evaluate.utils import launch_gradio_widget
+import gradio as gr
+
+"""module = evaluate.load("Natooz/ece")
+gradio_app = gr.Interface(
+    module,
+    inputs=gr.component(),
+    outputs=[gr.Image(label="Processed Image"), gr.Label(label="Result", num_top_classes=2)],
+    title=module.name,
+)"""
+gradio_app = gr.load("Natooz/ece", src="spaces")
 
 
-module = evaluate.load("Natooz/ece")
-launch_gradio_widget(module)
+if __name__ == "__main__":
+    gradio_app.launch()

ece.py

@@ -1,27 +1,19 @@
-# 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.
-
-from typing import Dict
+"""ECE metric file."""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
 
-import evaluate
 import datasets
-from torch import Tensor, LongTensor
+import evaluate
+from torch import LongTensor, Tensor
 from torchmetrics.functional.classification.calibration_error import (
     binary_calibration_error,
     multiclass_calibration_error,
 )
 
+if TYPE_CHECKING:
+    from collections.abc import Iterable
 
 _CITATION = """\
 @InProceedings{huggingface:ece,
@@ -41,7 +33,8 @@ https://torchmetrics.readthedocs.io/en/stable/classification/calibration_error.h
 _KWARGS_DESCRIPTION = """
 Calculates how good are predictions given some references, using certain scores
 Args:
-    predictions: list of predictions to score. They must have a shape (N,C,...) if multiclass, or (N,...) if binary.
+    predictions: list of predictions to score. They must have a shape (N,C,...) if
+        multiclass, or (N,...) if binary.
     references: list of reference for each prediction, with a shape (N,...).
 Returns:
     ece: expected calibration error
@@ -65,11 +58,17 @@ Examples:
 @evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
 class ECE(evaluate.Metric):
     """
-    Proxy to the BinaryCalibrationError (ECE) metric of the torchmetrics package:
-    https://torchmetrics.readthedocs.io/en/stable/classification/calibration_error.html
+    Module for the BinaryCalibrationError (ECE) metric of the torchmetrics package.
+
+    https://torchmetrics.readthedocs.io/en/stable/classification/calibration_error.html.
     """
 
-    def _info(self):
+    def _info(self) -> evaluate.MetricInfo:
+        """
+        Return the module info.
+
+        :return: module info.
+        """
         return evaluate.MetricInfo(
             # This is the description that will appear on the modules page.
             module_type="metric",
@@ -94,31 +93,43 @@ class ECE(evaluate.Metric):
             ],
         )
 
-    def _compute(self, predictions=None, references=None, **kwargs) -> Dict[str, float]:
-        """Returns the ece.
-        See the torchmetrics documentation for more information on the arguments to pass.
+    def _compute(
+        self,
+        predictions: Iterable[float] | None = None,
+        references: Iterable[int] | None = None,
+        **kwargs
+    ) -> dict[str, float]:
+        """
+        Return the Expected Calibration Error (ECE).
+
+        See the torchmetrics documentation for more information on the method.
         https://torchmetrics.readthedocs.io/en/stable/classification/calibration_error.html
             predictions: (N,C,...) if multiclass or (N,...) if binary
-            references: (N,...)
+            references: (N,...).
 
-        If "num_classes" is not provided in a multiclasses setting, the number maximum label index will
-        be used as "num_classes".
+        If "num_classes" is not provided in a multiclass setting, the number maximum
+        label index will be used as "num_classes".
         """
         # Convert the input
         predictions = Tensor(predictions)
         references = LongTensor(references)
 
         # Determine number of classes / binary or multiclass
-        error_msg = "Expected to have predictions with shape (N,C,...) for multiclass or (N,...) for binary, " \
-                    f"and references with shape (N,...), but got {predictions.shape} and {references.shape}"
+        error_msg = (
+            "Expected to have predictions with shape (N,C,...) for multiclass or "
+            "(N,...) for binary, and references with shape (N,...), but got "
+            f"{predictions.shape} and {references.shape}"
+        )
         binary = True
         if predictions.dim() == references.dim() + 1:  # multiclass
             binary = False
             if "num_classes" not in kwargs:
                 kwargs["num_classes"] = int(predictions.shape[1])
         elif predictions.dim() == references.dim() and "num_classes" in kwargs:
-            raise ValueError("You gave the num_classes argument, with predictions and references having the"
-                             "same number of dimensions. " + error_msg)
+            raise ValueError(
+                "You gave the num_classes argument, with predictions and references "
+                "having the same number of dimensions. " + error_msg
+            )
         elif predictions.dim() != references.dim():
             raise ValueError("Bad input shape. " + error_msg)
 

tests.py

@@ -1,3 +1,5 @@
+"""Test cases."""
+
 test_cases = [
     {
         "predictions": [0, 0],
@@ -14,4 +16,4 @@ test_cases = [
         "references": [1, 1],
         "result": {"metric_score": 0.5}
     }
-]
+]