init

.gitignore

@@ -0,0 +1,164 @@
+### Python template
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+

.python-version

@@ -0,0 +1 @@
+3.13

main.py

@@ -0,0 +1,6 @@
+import evaluate
+from evaluate.utils import launch_gradio_widget
+
+
+module = evaluate.load("Aye10032/top5_error_rate")
+launch_gradio_widget(module)

pyproject.toml

@@ -0,0 +1,9 @@
+[project]
+name = "top5-error-rate"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.13"
+dependencies = [
+    "evaluate[template]>=0.4.3",
+]

top5_error_rate.py

@@ -0,0 +1,79 @@
+from typing import Dict, Any
+
+import datasets
+import evaluate
+import numpy as np
+from evaluate.utils.file_utils import add_start_docstrings
+
+_DESCRIPTION = """
+The "top-5 error" is the percentage of times that the target label does not appear among the 5 highest-probability predictions. It can be computed with:
+Top-5 Error Rate = 1 - Top-5 Accuracy
+or equivalently:
+Top-5 Error Rate = (Number of incorrect top-5 predictions) / (Total number of cases processed)
+ Where:
+- Top-5 Accuracy: The proportion of cases where the true label is among the model's top 5 predicted classes.
+- Incorrect top-5 prediction: The true label is not in the top 5 predicted classes (ranked by probability).
+"""
+
+
+_KWARGS_DESCRIPTION = """
+Args:
+    predictions (`list` of `int`): Predicted labels.
+    references (`list` of `int`): Ground truth labels.
+Returns:
+    accuracy (`float` or `int`): Accuracy score. Minimum possible value is 0. Maximum possible value is 1.0, or the number of examples input.
+Examples:
+    >>> accuracy_metric = evaluate.load("accuracy")
+    >>> results = accuracy_metric.compute(references=[0, 1, 2, 0, 1, 2], predictions=[0, 1, 1, 2, 1, 0])
+    >>> print(results)
+    {'accuracy': 0.5}
+"""
+
+
+_CITATION = """
+"""
+
+
+@add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
+class Top5ErrorRate(evaluate.Metric):
+    def _info(self):
+        return evaluate.MetricInfo(
+            description=_DESCRIPTION,
+            citation=_CITATION,
+            inputs_description=_KWARGS_DESCRIPTION,
+            features=datasets.Features(
+                {
+                    "predictions": datasets.Sequence(datasets.Value("int32")),
+                    "references": datasets.Sequence(datasets.Value("int32")),
+                }
+            ),
+            reference_urls=[],
+        )
+
+    def _compute(
+        self,
+        *,
+        predictions: list[list[float]] = None,
+        references: list[float] = None,
+        **kwargs,
+    ) -> Dict[str, Any]:
+        # 确保输入是numpy数组
+        predictions = np.array(predictions)
+        references = np.array(references)
+
+        # 获取每个样本的top-5预测类别
+        top5_pred = np.argsort(predictions, axis=1)[:, -5:]
+
+        # 计算top-5错误率
+        correct = 0
+        total = len(references)
+
+        for i in range(total):
+            if references[i] in top5_pred[i]:
+                correct += 1
+
+        error_rate = 1.0 - (correct / total)
+
+        return {
+            "top5_error_rate": float(error_rate)
+        }