THE LUCS-KDD DECISION TREE CLASSIFIER SOFTWARE

The decision tree software comprises seven source files. These are provided from this WWW page together with three application classes. The source files are as follows:

2.1. Compiling

The decision tree software has been implemented in Java using the Java2 SDK (Software Development Kit) Version 1.5.0, which should therefore make it highly portable. The code does not require any special packages and thus can be compiled using the standard Java compiler:

javac *.java

2.2. Documentation

The code can be documented using Java Doc. First create a directory Documentation in which to place the resulting HTML pages and then type:

javadoc -d Documentation/ *.java

This will produce a hierarchy of WWW pages contained in the Document directory.

When compiled the software can be invoked in the normal manner using the Java interpreter:

java APPLICATION_CLASS_FILE_NAME

If you are planning to process a very large data set it is a good idea to grab some extra memory. For example:

java -Xms600m -Xmx600m APPLICATION_CLASS_FILE_NAME

The input to the software, in all cases is a (space separated) binary valued data set R. The set R comprises a set of N records such that each record (r), in turn, comprises a set of attributes. Thus:

R  = {r | r = subset A}

Where A is the set of available attributes. The value D is then defined as:

D = |A|

We then say that a particular data set has D columns and N rows. A small example data sets might be as follows:

1 2 3 6
1 4 5 7
1 3 4 6
1 2 6
1 2 3 4 5 7

where, in this case, A = {1, 2, 3, 4, 5, 6, 7}. Note that attribute numbers are ordered sequentially commencing with the number 1 (the value 0 has a special meaning). The input file is included using a -F flag.

The program assumes that the last attribute in each row is the class for that record (exactly one class per record). The software does not calculate how many classes there are, the user has to inform the software using the -N flag.

If required (the DecTreeRandom_2file_App and DecTreeInfoGain_2file_App applications) the name of a seperate test file can be included using a -T flag.

Some output is always generated such as: (i) the input parameters and start settings and (ii) "mile stones" during processing. Additional output statements can be included in application classes. The available additional output options are as follows:

1. outputDataArray(): Outputs the training set.
2. outputTestDataArray(): Outputs the test set.
3. outputDataArraySize(): Outputs the size of the input data (number of records and columns, number of elements and overall density).
4. outputDuration(double time1, double time2): The elapsed time, in seconds between time1 and time2. Typically used to measure processing time:

   double time1 = (double) System.currentTimeMillis();
   
   // Program statements
   
   < INSTANCE_NAME > .outputDuration(time1,
   				(double) System.currentTimeMillis());
   

5. outputNumClasses(): Outputs number of classes.
6. outputNumRules(): The number of discovered ARs.
7. outputDecTree(): Output a textual representation of the generated decision tree.
8. outputRulesWithDefault: Lists the generated classifier.

Below are some example test runs using number ten data sets taken from the UCI machine learning repository (Blake and Merz, 1998) and discretised using the LUCS-KDD DN software (Coenen 2003). The datasets may be obtained from:

The decision tree algorithms described here have been use successfully used by the LUCS-KDD research group to contrast and compare a variety of classification algorithms and techniques. The software is available for free, however the author would appreciate appropriate acknowledgement. The following reference format for referring to the decision tree implementation available from this www site is suggested:

1. Coenen, F. (2007), The LUCS-KDD Decision Tree Classifier Software, http://www.csc.liv.ac.uk/~frans/KDD/Software/DecisionTrees/decisionTree.html, Department of Computer Science, The University of Liverpool, UK.

Should you discover any "bugs" or other problems within the software (or this documentation), do not hesitate to contact the author.

1. Blake, C.L. & Merz, C.J. (1998). UCI Repository of machine learning databases http://www.ics.uci.edu/~mlearn/MLRepository.html, Irvine, CA: University of California, Department of Information and Computer Science.
2. Coenen, F. (2003). LUCS-KDD DN Software, http://www.csc.liv.ac.uk/~frans/KDD/Software/LUCS_KDD_DN/, Department of Computer Science, The University of Liverpool, UK.

3. Mitchell, T.M. (1997). Machine Learning. McGraw-Hill.
4. Quinlan, J. R. (1998). C4.5: Programs for Machine Learning.. Morgan Kaufmann Publishers.