# $Id: shuttle.R,v 1.2 2007/09/21 13:35:44 kaip Exp $

#
# Copyright (c) 2007 Kai Puolamaki <Kai.Puolamaki@iki.fi>
#
# Permission to use, copy, modify, and distribute this software for any
# purpose with or without fee is hereby granted, provided that the above
# copyright notice and this permission notice appear in all copies.
#
# THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
# WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
# MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
# ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
# ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
# OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
#
#
# T-61.3050 Machine Learning: Basic Principles
# Example for the lecture of 25 September 2007
#

# The required shuttle data is in the MASS library
library(MASS)
help(shuttle)
## shuttle                 package:MASS                 R Documentation
##
## Space Shuttle Autolander Problem
##
## Description:
##
##      The 'shuttle' data frame has 256 rows and 7 columns. The first six
##      columns are categorical variables giving example conditions; the
##      seventh is the decision. The first 253 rows are the training set,
##      the last 3 the test conditions.
##
## Usage:
##
##      shuttle
##
## Format:
##
##      This data frame contains the following columns:
##
##      'stability' Stable positioning or not ('stab / xstab')
##
##      'error' Size of error ('MM / SS / LX / XL')
##
##      'sign' Sign of error, positive or negative ('pp / nn')
##
##      'wind' Wind sign ('head / tail')
##
##      'magn' Wind strength ('Light / Medium / Strong / Out of Range')
##
##      'vis' Visibility ('yes / no')
##
##      'use' Use the autolander or not
##
## Source:
##
##      D. Michie (1989) Problems of computer-aided concept formation. In
##      _Applications of Expert Systems 2_, ed. J. R. Quinlan, Turing
##      Institute Press / Addison-Wesley, pp. 310-333.
##
## References:
##
##      Venables, W. N. and Ripley, B. D. (2002) _Modern Applied
##      Statistics with S._ Fourth edition.  Springer.


##############################################################################
##############################################################################
# Let's construct a network using Bene at http://b-course.hiit.fi/bene
# Reference: Silander T, Myllymaki P (2006) A Simple Optimal Approach
# for Finding the Globally Optimal Bayesian Network Structure. In Proc
# 22nd Annual Conference on Uncertainty in Artificial Intelligence
# (UAI'06).
#
# We must transform each column such that the factors are from 0 to n:


numerize <- function(D) {
  res <- D
  for(col in colnames(D)) res[,col] <- as.integer(D[,col])-1
  res
}

shuttleN <- numerize(shuttle)
for(row in rownames(shuttleN)) {
  for(col in colnames(shuttleN)) cat(sprintf("%d ",shuttleN[row,col]))
  cat("\n")
}

# Write table for those with no access to R:
# write.table(shuttle,file="shuttle.txt")
write.table(shuttleN,file="shuttleN.txt",col.names=FALSE,row.names=FALSE)

for(i in 1:length(colnames(D3))) cat(sprintf("%d %s\n",i-1,colnames(D3)[i]))

# Cut-and-paste the numerical output to http://b-course.hiit.fi/bene
# You can then analyze the resulting network.