List of Prepared Data FilesHere you can find examples of already prepared input data files. You can read them, but you can also download them (click with right mouse and select SAVE .. AS) and then use them as your input data files. Every data file is prepared in four forms with different delimiters.
Small artificial training set with only 5 examples
delimiter is: ... space ... comma ... semicolon . or . TAB
Meningoencephalitis diagnosis data set is a real training set with 140 examples. It has been prepared for JSAI KDD Challenge 2001 (Matsue City, Japan, May 22, 2001). The database was donated by Dr.Shusaku Tsumoto and is here included with kind permission of Dr. Takashi Washio. Here is also a copy of the original data set . You can transform this data set using description of necessary and suggested steps for its transformation into the DMS form. For those who want to learn about the problem in depth here is a link to the detailed domain description. It is a nice example of a typical data mining application in a medical domain.
Prepared data set using different delimiters: ... space ... comma ... semicolon . or . TAB
are available here as well.
Pittsburgh bridges data set (donated by Y.Reich to the UCI Machine Learning Repository ) is a set with 108 examples. The data set and its description can be downloaded from the Repository .
Prepared data set with delimiter: ... space ... comma ... semicolon . or . TAB
Banking crises data set Prepared for the FOC project is a set with 147 examples of real banking crises and 287 selected non-crisis periods. The data set has 945 attributes representing 105 World Bank indicators in the period of 3 years before onset of crises. List of 105 indicators with their short names used in the data file. List of examples defined by the ISO 3166-1 alpha-3 country code and the year of the event. The first 147 examples are crises cases.
Prepared data set with delimiter: ... TAB
© 2001 LIS - Rudjer Boskovic Institute
Last modified: September 09 2015 14:17:42.