Classification Datasets from KEEL

该数据集汇总了所有维度在10到90之间且没有缺失值的分类数据集。此外，所有度量属性都已等频分为5个区间。数据集规模大约为35个，平均包含约52,000行和30列的数据。该数据集的任务是进行高维数据中的依赖关系发现。This dataset compiles all categorical datasets with dimensionality ranging from 10 to 90 and no missing values. All metric attributes within these datasets have been discretized into 5 equal-frequency bins. The compiled dataset includes approximately 35 such datasets, with each averaging around 52,000 rows and 30 columns. The target task of this dataset is dependency discovery in high-dimensional data.