DrTycoon

该数据集名为DrTycoon，包含了从Seagate ST31000524NS企业级硬盘收集的样本，详细记录了它们的运行状态和SMART属性。数据集中包含了大部分功能正常的硬盘和小部分故障硬盘，因此数据集存在不平衡性。此外，该数据集包含了23,395块硬盘，在2年的时间里以每小时一次的频率记录样本，总计有1,048,573条实际运行硬盘的数据记录。数据规模较大，其任务是预测硬盘的健康状态，以便进行选择性擦除。

The dataset named DrTycoon comprises samples collected from Seagate ST31000524NS enterprise-grade hard disk drives, with detailed records of their operational states and SMART attributes. The dataset primarily consists of functionally healthy hard disks with only a small fraction of faulty ones, resulting in class imbalance. Additionally, it covers 23,395 hard disk drives, with data sampled hourly over a two-year period, yielding a total of 1,048,573 data records from actively running hard disks. Owing to its large data scale, the core task of this dataset is to predict the health status of hard disks for the purpose of selective erasure.