Additional resources for the CRAN package readMLData
This folder contains files, which are needed for the use of some benchmark
machine learning data from
UCI Machine Learning Repository using
within The R Project for Statistical Computing.
In order to use the data, perform the following steps.
- Install CRAN packages XML
(version 0.9-6) into R.
- Unpack UCI_ML_DataDescription-0-9.tar.gz
at any directory in your computer.
- Update the paths in test_script.R and
download_script.R to the actual
placement of UCI_ML_DataDescription and UCI_ML_DataFolders in your computer.
- Use an appropriate modification of the script
to download selected data sets from
UCI Machine Learning Repository.
Note that the script uses "wget" command line tool, which should be available
or replaced by another command. Some of the data sets require further steps to
be used. Follow the instructions in UCI_ML_DataFolders/README, which describe
also these additional steps.
- Run test_script.R. The output should contain for
each included data set
- its identification for local reference,
- its full name as it appears in
View All UCI Datasets,
- its dimension,
- the result of a check of the types of columns in the data set.
Wget for Windows