view release on metacpan or  search on metacpan

t/02-noisy.t  view on Meta::CPAN

}

# The following data comes from the "C4.5" software package, in the
# "soybean.data" data file.  It is somewhat noisy.  I chose it because
# it was a pretty big data set, and because there are published
# results on it that I can compare to.  Since the data seemed to be in
# order from most-information to least-information or something in the
# C4.5 distribution, I randomized the order of the instances.  Note
# also that I'm treating the '?' value as a normal string value.

# It looks like the original data source is
#     (a) Michalski,R.S. Learning by being told and learning from
#         examples: an experimental comparison of the two methodes of knowledge
#         acquisition in the context of developing an expert system for soybean
#         desease diagnoiss", International Journal of Policy Analysis and
#         Information Systems, 1980, 4(2), 125-161.

# The "C4.5" package is written by J.R. Quinlan and may be downloaded
# and used for free, but it is not supported and may not be
# redistributed.