Last data update: 2014.03.03
R: rfPredVar
rfPredVar
Description
Generate predictions and prediction variances from a random
forest based on the infinitesimal jackknife.
Usage
rfPredVar(random.forest, rf.data, pred.data = rf.data, CI = FALSE,
tree.type = "rf", prog.bar = FALSE)
Arguments
random.forest
A random forest trained with keep.inbag=TRUE
. See
details for more information.
rf.data
The data used to train rf
pred.data
The data used to predict with the forest; defaults to
rf.data
if not given
CI
Should 95% confidence intervals based on the CLT be returned along
with predictions and prediction variances?
tree.type
either 'ci' for conditional inference tree or 'rf' for
traditional CART tree
prog.bar
should progress bar be shown? (only applicable when
tree.type='ci'
)
Details
The random forest trained with keep.inbag=TRUE
is supplied
only for the purpose of defining the resampling scheme. The function builds
a new random forest based on the tree.type
setting. However, the
resamples are maintained identically to the supplied random forest. This
allows for direct comparison of the tree methods without having to account
for variation in resampling.
Currently, the CI methods are much more computationally intensive because
there is no C implementation of the CI random forest method that indicates
the number of times that each sample is included in each resample. In
order to carry out our simulations using V_IJ^B , we had to use a
pure R implementation of CI random forests. This is different for CART
random forests, where a C implementation already exists in the
randomForest
package. However, it should be noted that the
difference in computational times is due to the random forest creation
step, not the implementation of V_IJ^B . This should not be an
issue in the future when a C implementation of CI random forests is
created.
Note: This function does not use the default predict method for forests
produced by cforest
. The predictions here are the direct averages of
all tree predictions, instead of using the observation weights. Therefore,
predictions from this function will likely differ from
predict.cforest
when using subsampling.
This function currently only works with regression forests – not
classification forests.
Value
A data frame with the predictions and prediction variances (and
optionally 95% confidence interval)
Examples
library(randomForest)
data(airquality)
d <- na.omit(airquality)
rf <- randomForest(Ozone ~ .,data=d,keep.inbag=TRUE,sampsize=30,replace=FALSE,ntree=500)
rfPredVar(rf,rf.data=d,CI=TRUE,tree.type='rf')
Results
R version 3.3.1 (2016-06-21) -- "Bug in Your Hair"
Copyright (C) 2016 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)
R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.
R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.
Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.
> library(RFinfer)
Loading required package: randomForest
randomForest 4.6-12
Type rfNews() to see new features/changes/bug fixes.
> png(filename="/home/ddbj/snapshot/RGM3/R_CC/result/RFinfer/rfPredVar.Rd_%03d_medium.png", width=480, height=480)
> ### Name: rfPredVar
> ### Title: rfPredVar
> ### Aliases: rfPredVar
>
> ### ** Examples
>
> library(randomForest)
> data(airquality)
> d <- na.omit(airquality)
> rf <- randomForest(Ozone ~ .,data=d,keep.inbag=TRUE,sampsize=30,replace=FALSE,ntree=500)
> rfPredVar(rf,rf.data=d,CI=TRUE,tree.type='rf')
pred pred.ij.var l.ci u.ci
1 39.73059 7.7524290 24.536107 54.92507
2 28.08966 5.3934353 17.518717 38.66059
3 23.27279 4.6994501 14.062036 32.48354
4 25.55576 2.8853263 19.900620 31.21089
7 30.50232 0.3362483 29.843288 31.16136
8 20.40332 4.5428612 11.499478 29.30717
9 18.02975 5.6730639 6.910745 29.14875
12 24.34909 3.5935495 17.305861 31.39232
13 24.02742 3.5286015 17.111490 30.94335
14 22.81916 2.8134339 17.304927 28.33338
15 16.07831 1.4318998 13.271841 18.88478
16 23.07562 2.6820216 17.818957 28.33229
17 24.19359 3.6119483 17.114300 31.27288
18 16.43428 3.9431801 8.705788 24.16277
19 24.04042 2.5801882 18.983346 29.09750
20 15.80358 2.5859445 10.735221 20.87194
21 14.85775 4.6487349 5.746393 23.96910
22 23.15846 4.0936340 15.135080 31.18183
23 16.09588 4.2558752 7.754517 24.43724
24 20.93836 6.0948229 8.992722 32.88399
28 23.65311 3.2268074 17.328686 29.97754
29 44.30468 13.9360810 16.990461 71.61889
30 63.99303 73.0960907 -79.272680 207.25873
31 44.80748 10.7149831 23.806498 65.80846
38 29.58468 4.5451332 20.676380 38.49298
40 53.97851 22.6419014 9.601200 98.35582
41 46.54811 8.4399548 30.006104 63.09012
44 33.98474 10.5327850 13.340865 54.62862
47 26.42692 3.2943231 19.970168 32.88368
48 25.53707 4.8165143 16.096870 34.97726
49 17.93672 0.7151919 16.534972 19.33847
50 20.12607 2.4597945 15.304957 24.94717
51 21.39639 2.1847047 17.114446 25.67833
62 81.95700 62.3725557 -40.290963 204.20496
63 56.94240 20.9293277 15.921671 97.96313
64 44.04623 4.9025078 34.437495 53.65497
66 68.39603 5.4603222 57.693999 79.09807
67 44.41333 6.9680357 30.756234 58.07043
68 79.59537 8.8335027 62.282019 96.90871
69 81.66075 15.0602578 52.143187 111.17831
70 82.97542 9.2236249 64.897444 101.05339
71 70.26052 13.9028709 43.011390 97.50964
73 27.11210 9.0286387 9.416293 44.80791
74 36.82667 1.6172964 33.656824 39.99651
76 24.05843 8.3078986 7.775251 40.34162
77 49.94617 6.9466774 36.330929 63.56140
78 39.24203 1.4917598 36.318238 42.16583
79 65.49678 9.4161530 47.041463 83.95210
80 73.82062 16.4010844 41.675082 105.96615
81 51.51692 3.6778475 44.308468 58.72537
82 25.65840 3.7076386 18.391562 32.92524
85 62.61268 14.6601063 33.879403 91.34596
86 69.36035 38.9114292 -6.904650 145.62535
87 38.02567 17.8217922 3.095596 72.95574
88 46.05172 4.7864008 36.670543 55.43289
89 72.66075 14.0059433 45.209606 100.11189
90 69.36155 14.2209857 41.488930 97.23417
91 64.06288 10.8400394 42.816797 85.30897
92 55.01027 18.0118009 19.707786 90.31275
93 43.65397 13.2214869 17.740328 69.56760
94 28.97340 19.5917356 -9.425696 67.37250
95 36.73327 24.5386688 -11.361640 84.82817
99 89.35283 30.2100907 30.142144 148.56352
100 67.32147 18.3430264 31.369796 103.27314
101 74.63043 28.0188461 19.714504 129.54636
104 51.72103 7.4424839 37.134033 66.30803
105 37.81927 11.1299493 16.004967 59.63357
106 39.29910 18.8354647 2.382268 76.21593
108 21.80953 2.3460731 17.211315 26.40775
109 43.57627 18.7980031 6.732858 80.41968
110 29.37670 2.8691692 23.753232 35.00017
111 32.75123 9.0001891 15.111187 50.39128
112 34.93680 6.2462894 22.694298 47.17930
113 27.80877 5.8392693 16.364009 39.25352
114 17.99217 3.3074527 11.509679 24.47465
116 45.28803 12.4163074 20.952518 69.62355
117 76.85893 127.2356704 -172.518398 326.23626
118 69.51257 26.9025324 16.784572 122.24056
120 69.24370 9.2311753 51.150929 87.33647
121 90.49773 31.2680205 29.213539 151.78193
122 82.15027 11.7832413 59.055538 105.24500
123 80.97900 11.9652435 57.527554 104.43045
124 70.47533 41.5921501 -11.043787 151.99445
125 79.60430 21.8391098 36.800427 122.40816
126 81.93923 19.1283170 44.448417 119.43004
127 80.68966 18.2616341 44.897518 116.48181
128 49.23223 17.3232758 15.279233 83.18523
129 36.80272 11.8646974 13.548341 60.05710
130 35.82631 15.3023164 5.834322 65.81830
131 32.86494 4.2788315 24.478589 41.25130
132 28.54241 3.4639057 21.753281 35.33154
133 29.17500 0.8022814 27.602558 30.74744
134 34.66659 7.9499767 19.084924 50.24826
135 24.42233 3.0970240 18.352270 30.49238
136 44.14613 4.7936915 34.750671 53.54160
137 16.62505 1.5137115 13.658229 19.59187
138 20.21532 1.4183392 17.435422 22.99521
139 38.81493 5.1367092 28.747169 48.88270
140 23.55698 2.0953378 19.450196 27.66377
141 17.40132 1.3228870 14.808505 19.99413
142 24.78888 1.6194201 21.614877 27.96289
143 41.05297 35.8821131 -29.274682 111.38062
144 22.91002 3.6530365 15.750196 30.06984
145 18.32773 0.9136855 16.536943 20.11852
146 31.70482 9.6288819 12.832554 50.57708
147 19.05232 4.5018807 10.228792 27.87584
148 20.55829 4.3839757 11.965858 29.15073
149 38.15310 9.6559904 19.227707 57.07849
151 30.05972 9.7277813 10.993615 49.12582
152 32.69517 10.8326918 11.463482 53.92685
153 33.42828 9.8413951 14.139503 52.71706
>
>
>
>
>
> dev.off()
null device
1
>