"Dataset for Clustering Ensemble"

"This dataset collection, designed for clustering ensemble research and evaluation, aggregates nine publicly available datasets from diverse domains, including biomedicine, education, marketing, and text mining. The datasets vary significantly in size, dimensionality, class balance, and attribute types (categorical, numerical, mixed), providing a comprehensive benchmark for testing the robustness and generalizability of clustering ensemble algorithms. Below is a brief description of the included datasets:Ionosphere (UCI): Radar data for ionospheric structure classification with 351 instances and 34 features.Teaching Assistant Evaluation (TAE) (UCI): Contains 151 instances evaluating teaching assistants with both categorical and numerical features.Heart Failure Clinical Records (Kaggle): Medical dataset of 299 patients used to predict mortality events based on 13 clinical features.Breast Cancer Wisconsin (Diagnostic) (UCI): A well-known dataset with 569 instances and 30 real-valued features for binary classification.Reuters-21578 (Kaggle): A large-scale text corpus widely used in topic modeling and document clustering tasks.Bank Marketing (UCI): Marketing data from a Portuguese bank with 4,521 instances and a mix of categorical and numerical attributes.Yeast (UCI): A biological dataset with 1,484 instances for predicting protein localization sites.Liver Disorders (UCI): Contains 345 instances related to liver enzyme measurements and alcohol consumption.Haberman\u2019s Survival (UCI): A small clinical dataset (306 instances) concerning post-surgery survival of breast cancer patients."