Ads by Google
Christian Borgelt's Web Pages

Frequent Item Set Mining and Association Rule Induction for R

Download

fim4r.zip (805 kb) fim4r.tar.gz (743 kb) C sources, version 1.5 (2016.03.23)
fim4r_test.R (1 kb) R test program, included in the sources

Description

FIM4R is an extension module that makes several frequent item set mining (FIM) and association rule induction algorithms available as functions in R and also includes functions for generating a pattern spectrum with the help of surrogate data and FIM analysis, for estimating a pattern spectrum and for pattern set reduction.

This extension module was developed for R 3.1.2 and has been tested up to now only on Ubuntu Linux 15.10. However, there is no reason why it should not work on Microsoft Windows as well, since no Linux-specific functions have been used.

How to use the different functions can be seen in the test program fim4r_test.R made available above (which is also available in the source package). Package documentation is currently a bit sparse, but what is available can be accessed by calling help(fim4r) in R, after loading this extension library with library(fim4r).

Installation

To install this extension library, unpack the sources to a new directory and call R CMD INSTALL fim4r in this directory. Note that you may need root or administrator rights for the installation, as R may want to copy some files to its system directories.

References

More information about frequent item set mining and association rule induction can be found in the following paper:

The use of pattern spectra to evaluate the statistical significance of found frequent item sets is explained in this paper: