Software Defect Prediction for Healthcare Big Data: An Empirical Evaluation of Machine Learning Techniques

Table 3

List of attributes according to datasets.

Attributes		Datasets
		AR1	AR3	CM1	JM1	KC2	KC3	MC1
Halstead attributes	Halstead content	✓	✓	—	✓	-	✓	✓
	Halstead difficulty	✓	✓	✓	✓	✓	✓	✓
	Halstead effort	✓	✓	✓	✓	✓	✓	✓
	Halstead error estimator	✓	✓	—	✓	-	✓	✓
	Halstead length	✓	✓	✓	✓	✓	✓	✓
	Halstead level	✓	✓	✓	✓	✓	✓	✓
	Halstead program time	✓	✓	✓	✓	✓	✓	✓
	Halstead volume	✓	✓	✓	✓	✓	✓	✓
	Number of operands	✓	✓	✓	✓	✓	✓	✓
	Number of operators	✓	✓	✓	✓	✓	✓	✓
	Number of unique operands	✓	✓	✓	✓	✓	✓	✓
	Number of unique operators	✓	✓	✓	✓	✓	✓	✓
McCabe attributes	Essential complexity	—	—	✓	✓	✓	✓	✓
	Cyclomatic complexity	✓	✓	✓	✓	✓	✓	✓
	Design complexity	✓	✓	✓	✓	✓	✓	✓
	Cyclomatic density	✓	✓	—	—	—	✓	✓
Size attributes	Number of lines	—	—	✓	-	✓	✓	✓
	LOC total	✓	✓	✓	✓	✓	✓	✓
	LOC executable	✓	✓	—	✓	—	✓	✓
	LOC comments	✓	✓	✓	✓	✓	✓	✓
	LOC code and comments	✓	✓	✓	✓	✓	✓	✓
	LOC blank	✓	✓	✓	✓	✓	✓	✓
Others attributes	Branch count	✓	✓	✓	✓	✓	✓	✓
	Condition count	✓	✓	—	—	—	✓	✓
	EDGE count	—	—	—	—	—	✓	✓
	Parameter count	✓	✓	—	—	—	✓	✓
	Modified condition count	—	—	—	—	—	✓	✓
	Multiple condition count	✓	✓	—	—	—	✓	✓
	Node count	—	—	—	—	—	✓	✓
	Design density	✓	✓	—	—	—	✓	✓
	Essential density	—	—	—	—	—	✓	✓
	Decision count	✓	✓	—	—	—	✓	✓
	Decision density	✓	✓	—	—	—	✓	-
	Call pairs	✓	✓	—	—	—	✓	✓
	Global data complexity	—	—	—	—	—	✓	✓
	Global data density	—	—	—	—	—	✓	✓
	Maintenance severity	—	—	✓	—	✓	✓	✓
	Normalized cyclomatic complexity	✓	✓	—	—	—	✓	✓
	Pathological complexity	—	—	—	—	—	—	✓
	Percent comments	—	—	✓	—	✓	✓	✓
Class attribute	Defective	✓	✓	✓	✓	✓	✓	✓