DataSets repository

In this page you can find and download the datasets from dataset repository. Please, if you use any of them, cite us using the following reference:

Dataset repository citation:

                Jose M. Cadenas, M. Carmen Garrido, Raquel Martinez.
                NIP - An Imperfection Processor to Data Mining datasets.
                Int. Journal of Computational Intelligence Systems 6 (supp. 1), 3-17, 2013

Datasets with imperfect values

Below you can find all the Classification datasets available. For each dataset, it is shown its name, attributes (the table details the number of Real/Nominal attributes in the data), number of instances and classes (number of possible values of the output variable).

In addition, the table shows if the corresponding dataset has missing values, interval values, fuzzy values and/or noise (the table shows the percentage of low quality values).

The table allows to download each dataset (inside a ZIP file). Additionally, it is possible to obtain the dataset already partitioned, by means of a 10-folds / 5-folds cross validation procedure. Finally, we provide a file to give additional information about each dataset and its attributes.

Data sets Data sets with missing-fuzzy values             Used in paper: "Extending information processing in a Fuzzy Random Forest ensemble."             doi:  10.1007/s00500-011-0777-1 Data sets with interval-fuzzy values             Used in paper: "Feature subset selection Filter-Wrapper based on low quality data"             doi:  10.1016/j.eswa.2013.05.051 Data sets with missing values, fuzzy values and fuzzy-subset values             Used in paper: "A similarity-based instance selection method on imprecise data and Soft Computing"

                                                                                Go to "DataSets and Results repository"