| same as cleveland dataset but with all continuous attributes stripped out

0, 1, 2, 3, 4.		| classes

| Note that according to the .names file:
|      Experiments with the Cleveland database have concentrated on simply
|      attempting to distinguish presence (values 1,2,3,4) from absence (value
|      0).  

| Note that there is a single missing value in 2 instances.

sex:		0, 1.
cp:		1, 2, 3, 4.
fbs:		0, 1.
restecg:	0, 1, 2.
exang:		0, 1.
slope:		1, 2, 3.
thal:		3, 6, 7.