%%-*- text -*-
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% This is a PROMISE Software Engineering Repository data set made publicly
% available in order to encourage repeatable, verifiable, refutable, and/or
% improvable predictive models of software engineering.
%
% If you publish material based on PROMISE data sets then, please
% follow the acknowledgment guidelines posted on the PROMISE repository
% web page http://promise.site.uottawa.ca/SERepository .
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

% 1. Title/Topic: reuse/predicting successful reuse

@relation reuse

% 2. Sources:
% 
%        M. Morisio and M. Ezran, and C. Tully,
%        Success and failure factors in software reuse,
%        IEEE Transactions on Software Engineering, volume 28, 
%        4, 2002, pages 340--357
% 
%    -- Donor: Tim Menzies (tim@barmag.net)
% 
%    -- Date:  December 2 2004

% 3. Past usage:
% 
%     1. M. Morisio and M. Ezran, and C. Tully,
%        Success and failure factors in software reuse,
%        IEEE Transactions on Software Engineering, volume 28, 
%        4, 2002, pages 340--357
%        -- Results:
%           -- Data mining was used to confirm that results of
%              an analysis of surverys of software managers 
%	      regarding factors that predict for successful reuse.
%
%     2. More Success and Failure Factors in Software Reuse,
%        "T. Menzies and J.S. Di Stefano", IEEE Transactions on Software
%        Engineering, 2003, May (http://menzies.us/pdf/02sereuse.pdf)
%        -- Results:
%           -- Raised doubts about some of the Morisio and Ezran
%              conclusions.

%4. Relevaant information
%   This data set represents an interesting SE problem: how to make
%   sense of software development when very little data (only 23 instances)
%   is availabe for generalization


% 5. Number of instances: 24

% 6. Number of attributes: 29
%
%   Here are the "high-level control variables" i.e. key high-level 
%   management decisions about a reuse program.
%
%Attribute 	 		Value		#	Notes 
%------------------------------  --------------  ------  -----------------------------------
%Project id	 		1 .. infinity		 
%------------------------------  --------------  ------  -----------------------------------
%Top management  ommitment 	yes 		20	top management reuse committed  
%				 no 		 4	 
%------------------------------  --------------  ------  -----------------------------------
%Key reuse roles introduced  	yes 		19	 >=1 reuse role
%     	 			 no 		 4	 no reuse roles were introduced
%------------------------------  --------------  ------  -----------------------------------
%Reuse process introduced   	yes 		15	 >=1 reuse process was introduced
%    	 			 no 		 8	 no reuse process was introduced
%------------------------------  --------------  ------  -----------------------------------
%Nonreuse process modified 	yes 		16	 >=1 nonreuse  processes  modified
% 	 			 no 		 7	 no nonreuse   processes  modified
%------------------------------  --------------  ------  -----------------------------------
%Human factors 	 	        yes 	        16	 human factors  handled; e.g. via awareness, 
%                                                         training, and motivation programs
% 	 			 no	         8 	  
%------------------------------  --------------  ------  -----------------------------------
%Repository 	                yes 	        23	 assets in repository tool
% 	                         no 	         0 
%
%   Note that all 23 projects seen in this data set used a repository;
%   i.e. this data set could never be used to refute claims that a
%   repository is useless. Nevertheless, like Morisio et.al., we
%   believe that reuse products have to be kept in some sort of
%   repository to enable reuse.
%
%   Here are the "state variables"; i.e.  attributes over which a
%   company has no control.
%
%Attribute 	                Value	        #	Notes
%------------------------------  --------------  ------  -----------------------------------
%Project id	 		1 .. infinity  
%------------------------------  --------------  ------  -----------------------------------
%Software staff	                L		 6	 >201 people on the project.
% 				M		 9  	 51 .. 200 people on the project.
% 				S  		 9	 1 .. 50 people on the project.
%------------------------------  --------------  ------  -----------------------------------
%Overall Staff	 		X		10	 >501 people.
% 				L		 7   	 201 .. 500 people.
% 				M		 5   	 51 .. 200 people.
% 				S		 2   	 1 .. 50 people.
%------------------------------  --------------  ------  -----------------------------------
%Production Type	 		product-family 	20	 projects related; evolve over time
% 				isolated 	 4	 projects have little in common
%------------------------------  --------------  ------  -----------------------------------
%Software and product  	 	product 	17	 software is embedded in a product
% 				alone 		 4	 software is standalone product
%       				process		 2 	 software  embedded in a process
%------------------------------  --------------  ------  -----------------------------------
%SP maturity  	 		high 		 6	 CMM level 3 or higher
%      	 			medium		13 	 ISO 9001 certification or CMM level 2
% 	 			low		 5 	 not high or medium
%------------------------------  --------------  ------  -----------------------------------
%Application domain  	 	TLC 		 7	 telecommunications
% 	 			FMS		 4 	 flight management systems
% 	 			ATC 		 1	 air traffic control
% 	 			TS 		 1	 train simulation
% 	 			TTC 		 7	 train traffic control
% 	 			Bank 		 1	 bank
% 	 			Book-keeping 	 1	 book-keeping
% 	 			Measurement 	 1	 management, control of measurements
% 	 			Space 		 1	 aerospace applications
% 	 			Manufacturing 	 3	 manufacturing
% 	 			SE-Tools 	 2	 software tools
%------------------------------  --------------  ------  -----------------------------------
%Type of software	 	Embedded-RT 	 6	 embedded, real-time
%	 			Non-Embedded-RT  2	 non-embedded, real-time
% 	 			Technical 	12	 non-embedded, non-real-time, small DBMS, 
%							 important control part
% 	 			Business 	 4	 non-embedded, non-real-time, important 
%							 DBMS, limited control part
%------------------------------  --------------  ------  -----------------------------------
%Size of  baseline 	 	L		 8 	 100 ... 500 KLOC; >100$ person months
% 	 			M 		13	  10 ... 100 KLOC; 10 .. 100$ person months
% 	 			S 		 2	 <10 KLOC; <10 person months
%------------------------------  --------------  ------  -----------------------------------
%Development approach 	 	OO 		15	 object oriented
% 	 			proc 		 8	 procedural
%------------------------------  --------------  ------  -----------------------------------
%Staff experience  	 	high 		 7	 >5 years average
% 	 			medium 		15	 2 .. 4 years average
% 	 			low 		 1	 <=1 year average
%
%   Here are the "low-level conrol variables"; i.e. specific approaches
%   to the implementation of reuse.
%
%Attribute 	                Value	        #	Notes
%------------------------------  --------------  ------  -----------------------------------
%Project id	                1 .. infinity
%------------------------------  --------------  ------  -----------------------------------
%Reuse approach 	 		loose 		12 	 assets loosely coupled 
% 	 			tight 		11	 assets  coupled, used in groups
%------------------------------  --------------  ------  -----------------------------------
%Domain Analysis 	 	yes 		 9	 domain analysis was performed
% 	 			no 		14	
%------------------------------  --------------  ------  -----------------------------------
%Origin 	 			ex-novo 	 4	 assets are developed from scratch
% 	 			reeng 		15	 assets via reengineering old work
% 	 			as-is 		 4	 old products used  without change
%------------------------------  --------------  ------  -----------------------------------
%Independent team 	 	yes 		 2	 independent team makes assets
% 	 			no 		21	 development projects makes  assets
%------------------------------  --------------  ------  -----------------------------------
%When assets built 	 	before 		 7	 well before  they are reused
% 	 			just-in-time 	16	 just before they are reused
%------------------------------  --------------  ------  -----------------------------------
%Qualification 	 		yes 		14	 assets undergo a qualification process
% 	 			no 		 9	 no defined qualification process
%------------------------------  --------------  ------  -----------------------------------
%Configuration management 	yes 		16	 configuration management used 
% 	 			no 		 7	  
%------------------------------  --------------  ------  -----------------------------------
%Rewards policy 	 		yes 		 3	 a rewards policy for  reuse in place
% 	 			no 		21	 no rewards policy in place
%------------------------------  --------------  ------  -----------------------------------
%# of assets 	 		1 to 20  	 5	 number of assets in the repository
%             	 		21 to 50 	 3	 
%             	 		51 to 100	 8	 
%             	 		100+     	 7	
%------------------------------  --------------  ------  -----------------------------------
%Work-products 	 		C  	                 code
% 	 			D	 		 design
% 	 			R	 		 requirements
%
%   Note that in the last entry, "work products", the number of values
%   is counted differently to the above. Specifically, C=10; D+C=4;
%   R+D+C=9

@attribute 'Project ID' {A,B,D,E,F,G,H,I,J,K,L,M,N,O,P,Q,R,S,T,U,V,W,X,Y}
@attribute 'Software Staff' {L,M,S}
@attribute 'Overall Staff' {L,X,M,S}
@attribute 'Type of Software Production' {product-family,isolated}
@attribute 'Software and Product' {product,alone,process,NA}
@attribute 'SP maturity' {high,middle,low}
@attribute 'Application Domain' {TLC,SE-Tools,Bank,Engine_Controller,FMS,ATC,TS,Space,Manufacturing,Measurement,Finance,Book-Keeping}
@attribute 'Type of Software' {Technical,Business,Embedded-RT,Non-Embedded-RT}
@attribute 'Size of Baseline' {L,M,S,not_available}
@attribute 'Development Approach' {OO,proc,not_available}
@attribute 'Staff Experience' {high,middle,low,not_available}
@attribute 'Top Management Commitment' {yes,no}
@attribute 'Key Reuse Roles Introduced' {yes,no,NA}
@attribute 'Reuse Processes Introduced' {yes,no,NA}
@attribute 'Non-Reuse Processes Modified' {yes,no,NA}
@attribute Repository {yes,NA}
@attribute 'Human Factors' {yes,no}
@attribute 'Reuse Approach' {tight,loose,NA}
@attribute 'Work Products' {D+C,C,R+D+C,NA}
@attribute 'Domain Analysis' {yes,no,NA}
@attribute Origin {ex-novo,as-is,reeng,NA}
@attribute 'Independent Team' {yes,no,NA}
@attribute 'When Assests Developed' {before,justintime,NA}
@attribute Qualification {yes,no,NA}
@attribute 'Configuration Management' {yes,no,NA}
@attribute 'Rewards Policy' {no,yes}
@attribute '# assests' {51_to_100,21_to_50,100+,1_to_20,NA}
@attribute 'Success or Failure' {success,failure}
 
% 8. Missing attributes: 6 

% 9. Class Distribution:
  % success: 15
  % failure: 9

@data

A,L,L,product-family,product,high,TLC,Technical,L,OO,high,yes,yes,yes,yes,yes,yes,tight,D+C,yes,ex-novo,yes,before,yes,yes,no,51_to_100,success
B,L,L,product-family,product,high,TLC,Technical,M,OO,high,yes,yes,yes,yes,yes,yes,tight,D+C,yes,ex-novo,yes,before,yes,yes,no,51_to_100,success
D,L,L,isolated,alone,middle,SE-Tools,Technical,M,OO,middle,yes,yes,no,no,yes,no,loose,C,no,as-is,no,before,no,no,yes,21_to_50,failure
E,L,L,isolated,alone,middle,TLC,Technical,M,OO,middle,yes,yes,no,no,yes,no,loose,C,no,as-is,no,before,no,no,yes,21_to_50,failure
F,L,L,isolated,alone,middle,TLC,Technical,M,OO,middle,yes,yes,no,no,yes,no,loose,C,no,as-is,no,before,no,no,yes,21_to_50,failure
G,L,X,product-family,process,low,Bank,Business,L,OO,middle,yes,yes,yes,yes,yes,yes,loose,C,no,reeng,no,justintime,yes,yes,no,51_to_100,success
H,M,M,product-family,product,high,Engine_Controller,Embedded-RT,L,OO,middle,yes,yes,yes,yes,yes,yes,tight,R+D+C,no,reeng,no,justintime,no,yes,no,51_to_100,success
I,M,X,product-family,product,middle,FMS,Technical,M,OO,high,no,no,no,yes,yes,no,loose,D+C,no,reeng,no,justintime,no,no,no,51_to_100,failure
J,M,X,product-family,product,middle,FMS,Technical,M,OO,middle,no,no,no,yes,yes,no,loose,D+C,no,reeng,no,justintime,no,no,no,51_to_100,failure
K,M,X,product-family,product,middle,ATC,Non-Embedded-RT,L,proc,high,yes,yes,yes,yes,yes,yes,tight,R+D+C,yes,reeng,no,justintime,yes,yes,no,100+,success
L,M,X,product-family,product,high,TS,Technical,M,proc,high,yes,yes,yes,yes,yes,yes,tight,R+D+C,yes,reeng,no,justintime,yes,yes,no,51_to_100,success
M,M,X,product-family,product,high,SE-Tools,Technical,L,proc,middle,yes,yes,yes,yes,yes,yes,tight,R+D+C,yes,reeng,no,justintime,yes,yes,no,100+,success
N,M,X,product-family,product,middle,TLC,Non-Embedded-RT,M,proc,middle,yes,yes,yes,yes,yes,yes,tight,R+D+C,yes,reeng,no,justintime,yes,yes,no,51_to_100,success
O,S,L,product-family,product,middle,Space,Embedded-RT,M,OO,middle,yes,no,no,no,yes,no,loose,R+D+C,no,ex-novo,no,before,yes,yes,no,1_to_20,failure
P,S,M,product-family,product,middle,Manufacturing,Embedded-RT,M,proc,middle,yes,yes,yes,yes,yes,yes,loose,R+D+C,yes,reeng,no,justintime,yes,yes,no,100+,success
Q,S,M,product-family,product,middle,Manufacturing,Technical,M,proc,middle,yes,yes,yes,yes,yes,yes,loose,R+D+C,yes,reeng,no,justintime,yes,yes,no,100+,success
R,S,M,product-family,product,middle,TLC,Embedded-RT,L,proc,high,yes,yes,yes,yes,yes,yes,loose,C,no,reeng,no,justintime,yes,yes,no,1_to_20,success
S,S,S,product-family,product,low,Measurement,Technical,M,OO,middle,yes,yes,yes,yes,yes,yes,tight,C,no,ex-novo,no,justintime,yes,yes,no,100+,success
T,S,X,product-family,product,middle,FMS,Embedded-RT,M,OO,high,no,yes,yes,no,yes,no,loose,C,no,reeng,no,justintime,yes,yes,no,1_to_20,failure
U,S,X,product-family,process,low,Finance,Business,L,OO,low,yes,yes,no,yes,yes,yes,tight,R+D+C,no,reeng,no,justintime,no,yes,no,100+,success
V,S,X,product-family,product,low,TLC,Technical,S,OO,middle,yes,yes,yes,yes,yes,yes,tight,C,no,reeng,no,justintime,yes,yes,no,1_to_20,success
W,M,L,product-family,alone,middle,Manufacturing,Business,L,OO,middle,yes,no,yes,no,yes,yes,tight,C,yes,reeng,no,justintime,no,no,no,1_to_20,success
X,S,S,product-family,NA,low,Book-Keeping,Business,S,proc,middle,yes,NA,NA,NA,NA,no,NA,NA,NA,NA,NA,NA,NA,NA,no,NA,failure
Y,M,M,isolated,product,high,FMS,Embedded-RT,not_available,not_available,not_available,no,yes,no,no,yes,yes,loose,C,no,as-is,no,before,no,no,no,100+,failure