% Datasets for `Pattern Recognition and Neural Networks' by B.D. Ripley
% =====================================================================
% 
% Cambridge University Press (1996)  ISBN  0-521-46086-7
% 
% The background to the datasets is described in section 1.4; this file
% relates the computer-readable files to that description.
% 
% 
% 
% Cushing's syndrome
% ------------------
% 
% Data from Aitchison & Dunsmore (1975, Tables 11.1-3).
% 
% Data file Cushings.dat has four columns, 
% 
% Label of the patient
% Tetrhydrocortisone  (mg/24hr)
% Pregnanetriol  (mg/24hr)
% Type
% 
% The type of the last six patients (u1 to u6) should be
% regarded as unknown.  (The code `o' indicates `other').
% 
% 
% 
% synthetic two-class problem
% ---------------------------
% 
% Data from Ripley (1994a).
% 
% This has two real-valued co-ordinates (xs and ys) and a class (xc)
% which is 0 or 1.
% 
% Data file  synth.tr   has 250 rows of the training set
%            synth.te   has 1000 rows of the test set  (not used here)
% 
% 
% 
% viruses
% -------
% 
% This is a dataset on 61 viruses with rod-shaped particles affecting
% various crops (tobacco, tomato, cucumber and others) described by
% {Fauquet et al. (1988) and analysed by Eslava-G\'omez (1989).  There
% are 18 measurements on each virus,  the number of amino acid residues
% per molecule of coat protein.
% 
% Data file  viruses.dat  has 61 rows of 18 counts
% 	   virus3.dat   has 38 rows corresponding to the distinct
% 	   		Tobamoviruses.
% 
% The whole dataset is in order Hordeviruses (3), Tobraviruses (6),
% Tobamoviruses (39) and `furoviruses' (13).
% 
% 
% 
% Leptograpsus crabs
% ------------------
% 
% Data from Campbell & Mahon (1974) on the morphology of rock crabs of
% genus Leptograpsus.
% 
% There are 50 specimens of each sex of each of two colour forms.
% 
% Data file  crabs.dat has rows
% 
% sp	`species', coded B (blue form) or O (orange form)
% sex	coded M or F
% index	within each group of 50
% FL	frontal lip of carapace (mm)
% RW	rear width of carapace (mm)
% CL	length along the midline of carapace (mm)
% CW	maximum width of carapace (mm)
% BD	body depth (mm)
% 
% 
% 
% Forensic glass
% --------------
% 
% This example comes from forensic testing of glass collected by
% B. German on 214 fragments of glass.  It is also contained in the
% UCI machine-learning database collection (Murphy & Aha, 1995).
% 
% Data file fglass.dat has 214 rows with data for a single glass
% fragment.
% 
% RI	refractive index
% Na	% weight of sodium oxide(s)
% Mg	% weight of magnesium oxide(s)
% Al	% weight of aluminium oxide(s)
% Si	% weight of silicon oxide(s)
% K	% weight of potassium oxide(s)
% Ca	% weight of calcium oxide(s)
% Ba	% weight of barium oxide(s)
% Fe	% weight of iron oxide(s)
% type	coded 1 to 7
% 
% The type codes are:
% 
% 	1 (WinF) window float glass
% 	2 (WinNF) window non-float glass
% 	3 (Veh) vehicle glass
% 	5 (Con)  containers
% 	6 (Tabl) tableware
% 	7 (Head) vehicle headlamp glass
% 
% The ten groups used for the cross-validation experiments (I believe)
% are listed as row numbers in the file fglass.grp,
% 
% 
% 
% Diabetes in Pima Indians
% ------------------------
% 
% A population of women who were at least 21 years old, of Pima Indian heritage
% and living near Phoenix, Arizona,  was tested for diabetes
% according to World Health Organization criteria.  The data
% were collected by the US National Institute of Diabetes and Digestive and
% Kidney Diseases (Smith et al, 1988). This example is also contained in the
% UCI machine-learning database collection (Murphy & Aha, 1995).
% 
% The data files have rows containing
% 
% npreg 	number of pregnancies
% glu 	plasma glucose concentration in an oral glucose tolerance test
% bp 	diastolic blood pressure (mm Hg)
% skin 	triceps skin fold thickness (mm)
% ins	serum insulin (micro U/ml)
% bmi 	body mass index (weight in kg/(height in m)^2)
% ped 	diabetes pedigree function
% age 	in years
% type	No / Yes
% 
% Data file pima.tr   has 200 rows of complete training data.
%           pima.te   has 332 rows of complete test data.
%           pima.tr2  has the 200 rows of pima.tr plus 100 incomplete rows.
% 
%
%
% Information about the dataset
% CLASSTYPE: nominal
% CLASSINDEX: last
%

@relation prnn-cushings

@attribute Label {a1,a2,a3,a4,a5,a6,b1,b10,b2,b3,b4,b5,b6,b7,b8,b9,c1,c2,c3,c4,c5,u1,u2,u3,u4,u5,u6}
@attribute Tetrahydrocortisone REAL
@attribute Pregnanetriol REAL
@attribute Type {a,b,c,o}

@data
a1,3.1,11.70,a
a2,3.0,1.30,a
a3,1.9,0.10,a
a4,3.8,0.04,a
a5,4.1,1.10,a
a6,1.9,0.40,a
b1,8.3,1.00,b
b2,3.8,0.20,b
b3,3.9,0.60,b
b4,7.8,1.20,b
b5,9.1,0.60,b
b6,15.4,3.60,b
b7,7.7,1.60,b
b8,6.5,0.40,b
b9,5.7,0.40,b
b10,13.6,1.60,b
c1,10.2,6.40,c
c2,9.2,7.90,c
c3,9.6,3.10,c
c4,53.8,2.50,c
c5,15.8,7.60,c
u1,5.1,0.4,b
u2,12.9,5.0,c
u3,13.0,0.8,b
u4,2.6,0.1,a
u5,30.0,0.1,o
u6,20.5,0.8,o