Penn Machine Learning Benchmark (PMLB)

Penn Machine Learning Benchmark (PMLB) 是由宾夕法尼亚大学医学信息研究所创建的一个大型机器学习评估和比较基准数据集，包含165个真实世界、模拟和玩具基准数据集，主要用于监督分类方法的评估。数据集来源于多个流行的机器学习基准套件，如KEEL和UCI机器学习库，并经过标准化处理，以简化数据获取和预处理。PMLB旨在通过提供一个易于访问和使用的资源，帮助机器学习实践者和数据科学家识别不同机器学习方法的优缺点。数据集涵盖了广泛的领域，如生物医学研究、信号处理和图像分类等，旨在解决机器学习方法在不同领域应用中的性能评估和比较问题。

Penn Machine Learning Benchmark (PMLB) is a large-scale machine learning evaluation and comparison benchmark dataset developed by the Institute for Medical Informatics at the University of Pennsylvania. It comprises 165 real-world, simulated, and toy benchmark datasets, primarily intended for the evaluation of supervised classification methods. The datasets are sourced from multiple popular machine learning benchmark suites such as KEEL and the UCI Machine Learning Repository, and have undergone standardization to simplify data acquisition and preprocessing. PMLB aims to help machine learning practitioners and data scientists identify the strengths and weaknesses of various machine learning methods by providing an easily accessible and user-friendly resource. Covering a wide range of domains including biomedical research, signal processing, image classification and more, this benchmark is designed to address the challenges of performance evaluation and comparison for machine learning methods across diverse application fields.