\begin{thebibliography}{10}

\bibitem{awkbook}
Brian W.~Kernighan Alfred V.~Aho and Peter~J. Weinberger.
\newblock {\em The AWK Programming Language}.
\newblock Addison-Wesley, 1988.

\bibitem{me05c}
Zhihao Chen, Tim Menzies, Dan Port, and Barry Boehm.
\newblock Finding the right data for software cost modeling.
\newblock {\em IEEE Software}, Nov 2005.

\bibitem{Eisenstein04}
Jacob Eisenstein and Randall Davis.
\newblock Visual and linguistic information in gesture classification.
\newblock In {\em ICMI}, pages 113--120, 2004.
\newblock Avaliable from
  \url{http://iccle.googlecode.com/svn/trunk/share/pdf/eisenstein04.pdf}.

\bibitem{ferri09}
César Ferri, José Hernández-Orallo, and R.~Modroiu.
\newblock An experimental comparison of performance measures for
  classification.
\newblock {\em Pattern Recognition Letters}, 30(1):27--38, 2009.

\bibitem{Freund99thealternating}
Yoav Freund and Llew Mason.
\newblock The alternating decision tree learning algorithm.
\newblock In {\em In Machine Learning: Proceedings of the Sixteenth
  International Conference}, pages 124--133. Morgan Kaufmann, 1999.

\bibitem{gay09}
Greg Gay, Tim Menzies, and Bojan Cukic.
\newblock How to build repeatable experiments.
\newblock In {\em PROMISE '09: Proceedings of the 5th International Conference
  on Predictor Models in Software Engineering}, pages 1--9, New York, NY, USA,
  2009. ACM.

\bibitem{genic04}
Chetan Gupta and Robert Grossman.
\newblock Genic: A single pass generalized incremental algorithm for
  clustering.
\newblock In {\em In SIAM Int. Conf. on Data Mining}. SIAM, 2004.

\bibitem{kitch07}
B.~A. Kitchenham, E.~Mendes, and G.~H. Travassos.
\newblock Cross- vs. within-company cost estimation studies: A systematic
  review.
\newblock {\em IEEE Transactions on Software Engineering}, pages 316--329, May
  2007.

\bibitem{lessmann08}
S.~Lessmann, B.~Baesens, C.~Mues, and S.~Pietsch.
\newblock Benchmarking classification models for software defect prediction: A
  proposed framework and novel findings.
\newblock {\em IEEE Transactions on Software Engineering}, May 2008.
\newblock Available from
  \url{http://iccle.googlecode.com/svn/trunk/share/pdf/lessmann08.pdf}.

\bibitem{gawkai}
R.~Loui.
\newblock Gawk for ai.
\newblock {\em Class Lecture}.
\newblock Available from \url{http://menzies.us/cs591o/?lecture=gawk}.

\bibitem{matheny09}
A.~Matheny.
\newblock Scaling up text mining, 2009.
\newblock Masters thesis, Lane Department of Computer Science and Electrical
  Engineering, West Virginia University.

\bibitem{canopies00}
Andrew McCallum, Kamal Nigam, and Lyle~H. Ungar.
\newblock Efficient clustering of high-dimensional data sets with application
  to reference matching.
\newblock In {\em KDD '00: Proceedings of the sixth ACM SIGKDD international
  conference on Knowledge discovery and data mining}, pages 169--178, New York,
  NY, USA, 2000. ACM.

\bibitem{me00v}
T.~Menzies.
\newblock Evaluation issues for visual programming languages, 2002.
\newblock Available from \url{http://menzies.us/pdf/00vp.pdf}.

\bibitem{me05d}
T.~Menzies, D.~Port, Z.~Chen, J.~Hihn, and S.~Stukes.
\newblock Specialization and extrapolation of induced domain models: Case
  studies in software effort estimation.
\newblock 2005.
\newblock IEEE ASE, 2005, Available from
  \url{http://menzies.us/pdf/05learncost.pdf}.

\bibitem{me07i}
T.~Menzies, B.~Turhan, A.~Bener, and J.~Distefano.
\newblock Cross- vs within-company defect prediction studies.
\newblock 2007.
\newblock Available from \url{http://menzies.us/pdf/07ccwc.pdf}.

\bibitem{me06d}
Tim Menzies, Zhihao Chen, Jairus Hihn, and Karen Lum.
\newblock Selecting best practices for effort estimation.
\newblock {\em IEEE Transactions on Software Engineering}, November 2006.
\newblock Available from \url{http://menzies.us/pdf/06coseekmo.pdf}.

\bibitem{me07b}
Tim Menzies, Jeremy Greenwald, and Art Frank.
\newblock Data mining static code attributes to learn defect predictors.
\newblock {\em IEEE Transactions on Software Engineering}, January 2007.
\newblock Available from \url{http://menzies.us/pdf/06learnPredict.pdf}.

\bibitem{mie06}
I.~Mierswa, M.~Wurst, and R.~Klinkenberg.
\newblock Yale: Rapid prototyping for complex data mining tasks.
\newblock In {\em KDD'06}, 1996.

\bibitem{orrego04}
A.S. Orrego.
\newblock Sawtooth: Learning from huge amounts of data, 2004.

\bibitem{ramey94}
Chet Ramey.
\newblock Bash, the bourne-again shell.
\newblock 1994.
\newblock Available from \url{http://tiswww.case.edu/php/chet/bash/rose94.pdf}.

\bibitem{ramos03}
Juan Ramos.
\newblock Using tf-idf to determine word relevance in document queries.
\newblock In {\em Proceedings of the First Instructional Conference on Machine
  Learning}, 2003.
\newblock Available from
  \url{http://www.cs.rutgers.edu/~mlittman/courses/ml03/iCML03/papers/ramos.pd%
f}.

\bibitem{ritthoff01}
O.~Ritthoff, R.~Klinkenberg, S.~Fischer, I.~Mierswa, and S.~Felske.
\newblock Yale: Yet another learning environment.
\newblock In {\em LLWA 01 - Tagungsband der GI-Workshop-Woche, Dortmund,
  Germany}, pages 84--92, October 2001.
\newblock Available from
  \url{http://ls2-www.cs.uni-dortmund.de/~fischer/publications/YaleLLWA01.pdf}.

\bibitem{turhan08}
Burak Turhan, Tim Menzies, Ayse~B. Bener, and Justin~Di Stefano.
\newblock On the relative value of cross-company and within-company data for
  defect prediction.
\newblock {\em Empirical Software Engineering}, 2009.
\newblock Available from \url{http://menzies.us/pdf/08ccwc.pdf}.

\end{thebibliography}