importance_frame <- structure(list(variable = structure(1:20, .Label = c(
"A", "C",
"D", "E", "F", "G", "H", "I", "K", "L", "M", "N", "P", "Q", "R",
"S", "T", "V", "W", "Y"
), class = "factor"), mean_min_depth = c(
1.9761861386314,
2.5220853029533, 2.15539883255869, 1.61935396654558, 1.45123463631321,
1.53296953170083, 1.77518115811586, 1.52151167552988, 1.89182019096144,
2.14429040818413, 1.26326405034901, 1.93502763567771, 1.26898183744519,
2.02060547195198, 1.54217481302459, 1.67384650439192, 1.5485857685783,
2.09727178410599, 2.75747046937195, 2.35864404092358
), times_a_root = c(
23.4,
5.5, 13.3, 27.9, 39.3, 31.3, 29.7, 34.2, 24.2, 13, 43, 22.7,
45.3, 16.8, 31.5, 30.1, 33.5, 19.3, 1.75, 14.6
), no_of_nodes = c(
68.1,
32.6, 62.2, 103.2, 103.3, 104.7, 75.6, 105.7, 72.4, 64.6, 118.4,
73.6, 116.6, 74.5, 104.6, 95.6, 103.2, 60.3, 8.875, 36.1
), no_of_trees = c(
65.1,
32.3, 59.8, 96.1, 94.7, 99.9, 74.8, 100.6, 69.4, 62.8, 111.2,
71.2, 108.3, 72.4, 98.8, 90, 97.6, 58.4, 8.875, 35.9
), p_value = c(
0.669119230058558,
0.999999783867775, 0.824720803698331, 0.10305110839386, 0.160596787513604,
0.141119826647113, 0.52735342045046, 0.162403671879659, 0.713272963278132,
0.817225145266696, 0.0104446472288876, 0.546649197487473, 0.0330726857615005,
0.672936592800508, 0.0310135225001855, 0.182169849737794, 0.274905137508873,
0.873388429679101, 1, 0.999021554764331
), gini_decrease = c(
0.233831386391386,
0.0886505361305361, 0.185330422910423, 0.358267377067377, 0.401108053058053,
0.397634655344655, 0.308835228105228, 0.389097318237318, 0.250707615717616,
0.191033563103563, 0.476535763125763, 0.249038827838828, 0.47133199023199,
0.243902473082473, 0.372547632367632, 0.33646759018759, 0.382999447219447,
0.203790450660451, 0.0253906843156843, 0.133164814074814
), accuracy_decrease = c(
-0.00445119047619048,
-0.00289380952380952, -0.00482809523809524, -0.00530904761904762,
0.0051652380952381, 0.00616785714285714, 0.00289238095238095,
-0.00079095238095238, -0.00239095238095238, -0.00648809523809524,
0.00383690476190476, -0.00413857142857143, 0.00331214285714286,
-0.00290619047619048, -0.00131714285714286, -0.0046781746031746,
0.00534214285714286, -0.00532571428571429, 0, -0.000374047619047619
)), class = "data.frame", .Names = c(
"variable", "mean_min_depth",
"times_a_root", "no_of_nodes", "no_of_trees", "p_value", "gini_decrease",
"accuracy_decrease"
), row.names = c(NA, -20L), na.action = structure(c(
80L,
180L
), .Names = c("80", "180"), class = "omit"))
importance_frame
#> variable mean_min_depth times_a_root no_of_nodes no_of_trees p_value
#> 1 A 1.976186 23.40 68.100 65.100 0.66911923
#> 2 C 2.522085 5.50 32.600 32.300 0.99999978
#> 3 D 2.155399 13.30 62.200 59.800 0.82472080
#> 4 E 1.619354 27.90 103.200 96.100 0.10305111
#> 5 F 1.451235 39.30 103.300 94.700 0.16059679
#> 6 G 1.532970 31.30 104.700 99.900 0.14111983
#> 7 H 1.775181 29.70 75.600 74.800 0.52735342
#> 8 I 1.521512 34.20 105.700 100.600 0.16240367
#> 9 K 1.891820 24.20 72.400 69.400 0.71327296
#> 10 L 2.144290 13.00 64.600 62.800 0.81722515
#> 11 M 1.263264 43.00 118.400 111.200 0.01044465
#> 12 N 1.935028 22.70 73.600 71.200 0.54664920
#> 13 P 1.268982 45.30 116.600 108.300 0.03307269
#> 14 Q 2.020605 16.80 74.500 72.400 0.67293659
#> 15 R 1.542175 31.50 104.600 98.800 0.03101352
#> 16 S 1.673847 30.10 95.600 90.000 0.18216985
#> 17 T 1.548586 33.50 103.200 97.600 0.27490514
#> 18 V 2.097272 19.30 60.300 58.400 0.87338843
#> 19 W 2.757470 1.75 8.875 8.875 1.00000000
#> 20 Y 2.358644 14.60 36.100 35.900 0.99902155
#> gini_decrease accuracy_decrease
#> 1 0.23383139 -0.0044511905
#> 2 0.08865054 -0.0028938095
#> 3 0.18533042 -0.0048280952
#> 4 0.35826738 -0.0053090476
#> 5 0.40110805 0.0051652381
#> 6 0.39763466 0.0061678571
#> 7 0.30883523 0.0028923810
#> 8 0.38909732 -0.0007909524
#> 9 0.25070762 -0.0023909524
#> 10 0.19103356 -0.0064880952
#> 11 0.47653576 0.0038369048
#> 12 0.24903883 -0.0041385714
#> 13 0.47133199 0.0033121429
#> 14 0.24390247 -0.0029061905
#> 15 0.37254763 -0.0013171429
#> 16 0.33646759 -0.0046781746
#> 17 0.38299945 0.0053421429
#> 18 0.20379045 -0.0053257143
#> 19 0.02539068 0.0000000000
#> 20 0.13316481 -0.0003740476
library(randomForestExplainer)
x_measure <- "gini_decrease"
y_measure <- "accuracy_decrease"
important_variables(importance_frame,
k = 10,
measures = c(x_measure, y_measure, size_measure)
)