the other containing 8 selected attributes. With four
experiments and eight different situations a total of
eight models were developed.
The performances of the models in this
study were evaluated using the standard metrics
of accuracy, precision, recall and F-measure which
were calculated using the predictive classification
table, known as Confusion Matrix. ROC area was
also used to compare the performances of the
classifiers.
In this regard I have conducted four
experiments. For all the experiments two settings
was done, one containing all the 15 variables and
the other containing 8 chosen variables. All the
experiments were done on a full training dataset
containing all the instances and cross validation
was used for randomly sampling the training and
test sets.
The first experiment was designed to
evaluate the performance of a J48 classifier
Unpruned tree in predicting heart disease and to
investigate the effect of attribute selection on the
performance of the model. In this experiment two
situations were considered, one containing all 15
attributes and the other containing the selected 8
attributes.
On the first scenario the algorithm was run
on a full training set containing 7,339 instances with