Forest Pruning Based on Branch Importance

Table 2

The accuracy of FP, bagging, and random forest. represents that FP outperforms bagging in pairwise t-tests at 95% significance level and denotes that FP is outperformed by bagging.

Dataset	Unpruned C4.5		Pruned C4.5		PF	RF
	PF	Bagging	PF	Bagging
Australian	87.14 (2.0)	86.09	86.80 (3.0)	85.86	87.21 (1.0)	86.14
Autos	74.40 (2.0)	73.30	74.20 (3.0)	73.20	74.72 (1.0)	73.10
Backache	85.07 (3.0)	83.17	85.89 (1.0)	83.17	85.21 (2.0)	83.22
Balance-scale	78.89 (3.0)	75.07	79.79 (1.0)	76.64	79.65 (2.0)	76.32
Breast-cancer	69.98 (2.0)	67.10	69.97 (3.0)	66.58	70.11 (1.0)	68.88
Cars	86.51 (4.0)	86.78 (2.0)	86.88 (1.0)	86.28 (5.0)	86.55 (3.0)	86.11 (6.0)
Credit-rating	86.44 (2.0)	85.54	86.34 (3.0)	85.43	86.82 (1.0)	85.42
German-credit	75.33 (1.0)	73.83	74.86 (3.0)	73.11	75.22 (2.0)	73.18
Ecoli	84.47 (2.0)	83.32	84.20 (3.0)	83.40	84.52 (1.0)	83.89
Hayes-roth	78.75 (3.0)	78.63 (5.0)	78.77 (1.0)	76.31	78.76 (2.0)	77.77 (4.0)
Heart-c	80.94 (2.0)	80.34 (5.0)	81.01 (1.0)	80.27 (6.0)	80.90 (3.0)	80.87 (4.0)
Horse-colic	84.52 (1.0)	83.29	84.33 (2.0)	83.42	84.31 (3.0)	83.99 (4.0)
Ionosphere	93.99 (1.0)	93.93 (2.0)	93.59 (6.0)	93.71 (4.0)	93.87 (3.0)	93.56 (5.0)
Iris	93.55 (6.0)	94.24 (4.0)	94.52 (3.0)	94.53 (2.0)	94.21 (5.0)	94.62 (1.0)
Lymphography	83.81 (5.0)	83.43 (6.0)	84.55 (2.0)	84.53 (3.0)	84.38 (4.0)	84.82 (1.0)
Page-blocks	97.03 (4.5)	97.04 (2.5)	97.04 (2.5)	97.06 (1.0)	97.03 (4.5)	97.01 (6.0)
Pima	75.09 (3.0)	74.27	75.46 (1.0)	74.06	75.43 (2.0)	73.21
prnn-fglass	78.14 (4.0)	78.46 (1.0)	77.62 (6.0)	77.84 (5.0)	78.18 (3.0)	78.32 (2.0)
Vote	95.77 (1.0)	95.13	95.67 (3.0)	95.33 (4.0)	95.72 (2.0)	95.31 (5.0)