943 lines
38 KiB
Plaintext
943 lines
38 KiB
Plaintext
|
|
||
|
|
R Under development (unstable) (2019-04-05 r76323) -- "Unsuffered Consequences"
|
||
|
|
Copyright (C) 2019 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.
|
||
|
|
|
||
|
|
> #
|
||
|
|
> # This is a set of tests, with printout, that tries
|
||
|
|
> # to exercise all of the splitting rules
|
||
|
|
> # It's less formal than the others in this directory, but covers
|
||
|
|
> # more.
|
||
|
|
> # For all of the cross-validations I set xgroups explicitly, so as
|
||
|
|
> # to avoid any changes in random number allocation of the groups.
|
||
|
|
>
|
||
|
|
> library(rpart)
|
||
|
|
> require(survival)
|
||
|
|
Loading required package: survival
|
||
|
|
> options(digits=4) #avoid trivial rounding changes across R versions
|
||
|
|
> set.seed(10)
|
||
|
|
> #
|
||
|
|
> #
|
||
|
|
> # Survival, using the stagec data
|
||
|
|
> #
|
||
|
|
> # Time to progression in years
|
||
|
|
> # status 1=progressed, 0= censored
|
||
|
|
> # age
|
||
|
|
> # early endocrine therapy 1=no 2=yes
|
||
|
|
> # % of cells in g2 phase, from flow cytometry
|
||
|
|
> # tumor grade (Farrow) 1,2,3,4
|
||
|
|
> # Gleason score (competing grading system)
|
||
|
|
> # ploidy
|
||
|
|
> xgroup <- rep(1:10, length=nrow(stagec))
|
||
|
|
> fit1 <- rpart(Surv(pgtime, pgstat) ~ age + eet + g2+grade+gleason +ploidy,
|
||
|
|
+ stagec, method="poisson",
|
||
|
|
+ control=rpart.control(usesurrogate=0, cp=0, xval=xgroup))
|
||
|
|
> fit1
|
||
|
|
n= 146
|
||
|
|
|
||
|
|
node), split, n, deviance, yval
|
||
|
|
* denotes terminal node
|
||
|
|
|
||
|
|
1) root 146 193.400 0.058490
|
||
|
|
2) grade< 2.5 61 46.000 0.021270
|
||
|
|
4) g2< 11.36 33 9.303 0.007174
|
||
|
|
8) g2>=6.545 26 1.847 0.004462 *
|
||
|
|
9) g2< 6.545 7 5.883 0.027860 *
|
||
|
|
5) g2>=11.36 27 27.880 0.044870
|
||
|
|
10) g2>=14.37 15 12.430 0.030940 *
|
||
|
|
11) g2< 14.37 12 13.690 0.067870 *
|
||
|
|
3) grade>=2.5 85 122.600 0.094400
|
||
|
|
6) age>=56.5 75 104.700 0.082840
|
||
|
|
12) g2>=22.77 12 14.830 0.039530 *
|
||
|
|
13) g2< 22.77 57 76.110 0.100300
|
||
|
|
26) gleason< 7.5 41 55.810 0.076860
|
||
|
|
52) g2< 13.47 23 26.800 0.050830
|
||
|
|
104) g2>=11.52 7 5.289 0.030820 *
|
||
|
|
105) g2< 11.52 16 20.270 0.063870 *
|
||
|
|
53) g2>=13.47 18 25.520 0.112300 *
|
||
|
|
27) gleason>=7.5 16 15.190 0.164400 *
|
||
|
|
7) age< 56.5 10 11.420 0.196900 *
|
||
|
|
> summary(fit1)
|
||
|
|
Call:
|
||
|
|
rpart(formula = Surv(pgtime, pgstat) ~ age + eet + g2 + grade +
|
||
|
|
gleason + ploidy, data = stagec, method = "poisson", control = rpart.control(usesurrogate = 0,
|
||
|
|
cp = 0, xval = xgroup))
|
||
|
|
n= 146
|
||
|
|
|
||
|
|
CP nsplit rel error xerror xstd
|
||
|
|
1 0.128372 0 1.0000 1.0120 0.06329
|
||
|
|
2 0.052298 1 0.8716 0.9220 0.07170
|
||
|
|
3 0.045608 3 0.7670 0.9728 0.07846
|
||
|
|
4 0.026442 4 0.7214 0.9732 0.08052
|
||
|
|
5 0.018049 5 0.6950 0.9725 0.08388
|
||
|
|
6 0.009068 6 0.6769 0.9698 0.08532
|
||
|
|
7 0.008132 7 0.6679 0.9920 0.08795
|
||
|
|
8 0.006412 8 0.6597 0.9853 0.08800
|
||
|
|
9 0.000000 9 0.6533 1.0077 0.08952
|
||
|
|
|
||
|
|
Variable importance
|
||
|
|
grade g2 gleason ploidy age eet
|
||
|
|
27 27 23 12 10 1
|
||
|
|
|
||
|
|
Node number 1: 146 observations, complexity param=0.1284
|
||
|
|
events=54, estimated rate=0.05849 , mean deviance=1.325
|
||
|
|
left son=2 (61 obs) right son=3 (85 obs)
|
||
|
|
Primary splits:
|
||
|
|
grade < 2.5 to the left, improve=24.880, (0 missing)
|
||
|
|
gleason < 5.5 to the left, improve=21.630, (3 missing)
|
||
|
|
ploidy splits as LRR, improve=13.020, (0 missing)
|
||
|
|
g2 < 13.2 to the left, improve=11.450, (7 missing)
|
||
|
|
age < 53.5 to the right, improve= 2.484, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
gleason < 5.5 to the left, agree=0.863, adj=0.672, (0 split)
|
||
|
|
ploidy splits as LRR, agree=0.644, adj=0.148, (0 split)
|
||
|
|
g2 < 9.945 to the left, agree=0.630, adj=0.115, (0 split)
|
||
|
|
age < 66.5 to the right, agree=0.589, adj=0.016, (0 split)
|
||
|
|
|
||
|
|
Node number 2: 61 observations, complexity param=0.04561
|
||
|
|
events=9, estimated rate=0.02127 , mean deviance=0.7542
|
||
|
|
left son=4 (33 obs) right son=5 (27 obs), 1 observation remains
|
||
|
|
Primary splits:
|
||
|
|
g2 < 11.36 to the left, improve=8.9650, (1 missing)
|
||
|
|
ploidy splits as LRL, improve=7.4700, (0 missing)
|
||
|
|
age < 68.5 to the right, improve=3.9560, (0 missing)
|
||
|
|
gleason < 5.5 to the left, improve=1.8010, (3 missing)
|
||
|
|
eet < 1.5 to the left, improve=0.5444, (1 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
ploidy splits as LR-, agree=0.917, adj=0.815, (0 split)
|
||
|
|
age < 65.5 to the left, agree=0.617, adj=0.148, (0 split)
|
||
|
|
|
||
|
|
Node number 3: 85 observations, complexity param=0.0523
|
||
|
|
events=45, estimated rate=0.0944 , mean deviance=1.442
|
||
|
|
left son=6 (75 obs) right son=7 (10 obs)
|
||
|
|
Primary splits:
|
||
|
|
age < 56.5 to the right, improve=7.3190, (0 missing)
|
||
|
|
g2 < 22.76 to the right, improve=6.8420, (6 missing)
|
||
|
|
gleason < 8.5 to the left, improve=4.8530, (0 missing)
|
||
|
|
ploidy splits as LLR, improve=1.7320, (0 missing)
|
||
|
|
eet < 1.5 to the right, improve=0.9628, (1 missing)
|
||
|
|
|
||
|
|
Node number 4: 33 observations, complexity param=0.008132
|
||
|
|
events=1, estimated rate=0.007174 , mean deviance=0.2819
|
||
|
|
left son=8 (26 obs) right son=9 (7 obs)
|
||
|
|
Primary splits:
|
||
|
|
g2 < 6.545 to the right, improve=3.1310, (0 missing)
|
||
|
|
age < 62.5 to the right, improve=1.3520, (0 missing)
|
||
|
|
eet < 1.5 to the left, improve=0.6605, (0 missing)
|
||
|
|
gleason < 5.5 to the right, improve=0.4889, (2 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
grade < 1.5 to the right, agree=0.848, adj=0.286, (0 split)
|
||
|
|
|
||
|
|
Node number 5: 27 observations, complexity param=0.009068
|
||
|
|
events=8, estimated rate=0.04487 , mean deviance=1.033
|
||
|
|
left son=10 (15 obs) right son=11 (12 obs)
|
||
|
|
Primary splits:
|
||
|
|
g2 < 14.37 to the right, improve=1.820, (0 missing)
|
||
|
|
gleason < 5.5 to the left, improve=1.698, (1 missing)
|
||
|
|
age < 62.5 to the left, improve=1.136, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
ploidy splits as RL-, agree=0.741, adj=0.417, (0 split)
|
||
|
|
age < 65 to the left, agree=0.630, adj=0.167, (0 split)
|
||
|
|
gleason < 5.5 to the left, agree=0.630, adj=0.167, (0 split)
|
||
|
|
|
||
|
|
Node number 6: 75 observations, complexity param=0.0523
|
||
|
|
events=37, estimated rate=0.08284 , mean deviance=1.397
|
||
|
|
left son=12 (12 obs) right son=13 (57 obs), 6 observations remain
|
||
|
|
Primary splits:
|
||
|
|
g2 < 22.76 to the right, improve=4.8580, (6 missing)
|
||
|
|
gleason < 7.5 to the left, improve=4.1030, (0 missing)
|
||
|
|
age < 69.5 to the left, improve=2.7250, (0 missing)
|
||
|
|
ploidy splits as LRR, improve=0.7858, (0 missing)
|
||
|
|
eet < 1.5 to the right, improve=0.1992, (1 missing)
|
||
|
|
|
||
|
|
Node number 7: 10 observations
|
||
|
|
events=8, estimated rate=0.1969 , mean deviance=1.142
|
||
|
|
|
||
|
|
Node number 8: 26 observations
|
||
|
|
events=0, estimated rate=0.004462 , mean deviance=0.07105
|
||
|
|
|
||
|
|
Node number 9: 7 observations
|
||
|
|
events=1, estimated rate=0.02786 , mean deviance=0.8404
|
||
|
|
|
||
|
|
Node number 10: 15 observations
|
||
|
|
events=3, estimated rate=0.03094 , mean deviance=0.8289
|
||
|
|
|
||
|
|
Node number 11: 12 observations
|
||
|
|
events=5, estimated rate=0.06787 , mean deviance=1.141
|
||
|
|
|
||
|
|
Node number 12: 12 observations
|
||
|
|
events=4, estimated rate=0.03953 , mean deviance=1.236
|
||
|
|
|
||
|
|
Node number 13: 57 observations, complexity param=0.02644
|
||
|
|
events=30, estimated rate=0.1003 , mean deviance=1.335
|
||
|
|
left son=26 (41 obs) right son=27 (16 obs)
|
||
|
|
Primary splits:
|
||
|
|
gleason < 7.5 to the left, improve=5.40700, (0 missing)
|
||
|
|
g2 < 13.2 to the left, improve=4.46300, (0 missing)
|
||
|
|
ploidy splits as LRR, improve=3.49400, (0 missing)
|
||
|
|
age < 69.5 to the left, improve=3.12800, (0 missing)
|
||
|
|
eet < 1.5 to the left, improve=0.04903, (1 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
grade < 3.5 to the left, agree=0.772, adj=0.187, (0 split)
|
||
|
|
|
||
|
|
Node number 26: 41 observations, complexity param=0.01805
|
||
|
|
events=18, estimated rate=0.07686 , mean deviance=1.361
|
||
|
|
left son=52 (23 obs) right son=53 (18 obs)
|
||
|
|
Primary splits:
|
||
|
|
g2 < 13.48 to the left, improve=3.57000, (0 missing)
|
||
|
|
ploidy splits as LRR, improve=3.05800, (0 missing)
|
||
|
|
age < 65.5 to the left, improve=0.68120, (0 missing)
|
||
|
|
eet < 1.5 to the left, improve=0.09244, (0 missing)
|
||
|
|
gleason < 6.5 to the right, improve=0.01761, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
eet < 1.5 to the right, agree=0.634, adj=0.167, (0 split)
|
||
|
|
age < 58.5 to the right, agree=0.585, adj=0.056, (0 split)
|
||
|
|
|
||
|
|
Node number 27: 16 observations
|
||
|
|
events=12, estimated rate=0.1644 , mean deviance=0.9493
|
||
|
|
|
||
|
|
Node number 52: 23 observations, complexity param=0.006412
|
||
|
|
events=7, estimated rate=0.05083 , mean deviance=1.165
|
||
|
|
left son=104 (7 obs) right son=105 (16 obs)
|
||
|
|
Primary splits:
|
||
|
|
g2 < 11.52 to the right, improve=1.41100, (0 missing)
|
||
|
|
age < 62.5 to the right, improve=1.24600, (0 missing)
|
||
|
|
gleason < 6.5 to the left, improve=0.02047, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
age < 71 to the right, agree=0.826, adj=0.429, (0 split)
|
||
|
|
ploidy splits as RLR, agree=0.739, adj=0.143, (0 split)
|
||
|
|
|
||
|
|
Node number 53: 18 observations
|
||
|
|
events=11, estimated rate=0.1123 , mean deviance=1.418
|
||
|
|
|
||
|
|
Node number 104: 7 observations
|
||
|
|
events=1, estimated rate=0.03082 , mean deviance=0.7555
|
||
|
|
|
||
|
|
Node number 105: 16 observations
|
||
|
|
events=6, estimated rate=0.06387 , mean deviance=1.267
|
||
|
|
|
||
|
|
>
|
||
|
|
> fit2 <- rpart(Surv(pgtime, pgstat) ~ age + eet + g2+grade+gleason +ploidy,
|
||
|
|
+ stagec, xval=xgroup)
|
||
|
|
> fit2
|
||
|
|
n= 146
|
||
|
|
|
||
|
|
node), split, n, deviance, yval
|
||
|
|
* denotes terminal node
|
||
|
|
|
||
|
|
1) root 146 192.100 1.0000
|
||
|
|
2) grade< 2.5 61 44.800 0.3634
|
||
|
|
4) g2< 11.36 33 9.117 0.1230 *
|
||
|
|
5) g2>=11.36 28 27.600 0.7346
|
||
|
|
10) gleason< 5.5 20 14.300 0.5304 *
|
||
|
|
11) gleason>=5.5 8 11.090 1.3070 *
|
||
|
|
3) grade>=2.5 85 122.400 1.6150
|
||
|
|
6) age>=56.5 75 103.100 1.4260
|
||
|
|
12) gleason< 7.5 50 66.120 1.1410
|
||
|
|
24) g2< 13.47 24 27.200 0.8007 *
|
||
|
|
25) g2>=13.47 26 36.790 1.4570
|
||
|
|
50) g2>=17.91 15 20.330 0.9790 *
|
||
|
|
51) g2< 17.91 11 13.460 2.1710 *
|
||
|
|
13) gleason>=7.5 25 33.490 2.0310
|
||
|
|
26) g2>=15.29 10 11.590 1.2160 *
|
||
|
|
27) g2< 15.29 15 18.940 2.7050 *
|
||
|
|
7) age< 56.5 10 13.770 3.1820 *
|
||
|
|
> summary(fit2)
|
||
|
|
Call:
|
||
|
|
rpart(formula = Surv(pgtime, pgstat) ~ age + eet + g2 + grade +
|
||
|
|
gleason + ploidy, data = stagec, xval = xgroup)
|
||
|
|
n= 146
|
||
|
|
|
||
|
|
CP nsplit rel error xerror xstd
|
||
|
|
1 0.12946 0 1.0000 1.0100 0.07108
|
||
|
|
2 0.04206 1 0.8705 0.8919 0.07420
|
||
|
|
3 0.02920 2 0.8285 0.9239 0.08004
|
||
|
|
4 0.01799 3 0.7993 0.9293 0.08292
|
||
|
|
5 0.01541 4 0.7813 0.9866 0.09214
|
||
|
|
6 0.01335 5 0.7659 1.0007 0.09161
|
||
|
|
7 0.01151 7 0.7392 0.9983 0.09065
|
||
|
|
8 0.01000 8 0.7277 1.0130 0.09176
|
||
|
|
|
||
|
|
Variable importance
|
||
|
|
grade gleason g2 ploidy age eet
|
||
|
|
27 25 22 13 11 2
|
||
|
|
|
||
|
|
Node number 1: 146 observations, complexity param=0.1295
|
||
|
|
events=54, estimated rate=1 , mean deviance=1.316
|
||
|
|
left son=2 (61 obs) right son=3 (85 obs)
|
||
|
|
Primary splits:
|
||
|
|
grade < 2.5 to the left, improve=24.920, (0 missing)
|
||
|
|
gleason < 5.5 to the left, improve=21.350, (3 missing)
|
||
|
|
ploidy splits as LRR, improve=13.790, (0 missing)
|
||
|
|
g2 < 13.2 to the left, improve=12.310, (7 missing)
|
||
|
|
age < 58.5 to the right, improve= 2.684, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
gleason < 5.5 to the left, agree=0.863, adj=0.672, (0 split)
|
||
|
|
ploidy splits as LRR, agree=0.644, adj=0.148, (0 split)
|
||
|
|
g2 < 9.945 to the left, agree=0.630, adj=0.115, (0 split)
|
||
|
|
age < 66.5 to the right, agree=0.589, adj=0.016, (0 split)
|
||
|
|
|
||
|
|
Node number 2: 61 observations, complexity param=0.04206
|
||
|
|
events=9, estimated rate=0.3634 , mean deviance=0.7344
|
||
|
|
left son=4 (33 obs) right son=5 (28 obs)
|
||
|
|
Primary splits:
|
||
|
|
g2 < 11.36 to the left, improve=8.9620, (1 missing)
|
||
|
|
ploidy splits as LRL, improve=7.5850, (0 missing)
|
||
|
|
age < 68.5 to the right, improve=4.1380, (0 missing)
|
||
|
|
gleason < 5.5 to the left, improve=1.6410, (3 missing)
|
||
|
|
eet < 1.5 to the left, improve=0.5961, (1 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
ploidy splits as LR-, agree=0.917, adj=0.815, (0 split)
|
||
|
|
age < 65.5 to the left, agree=0.617, adj=0.148, (1 split)
|
||
|
|
|
||
|
|
Node number 3: 85 observations, complexity param=0.0292
|
||
|
|
events=45, estimated rate=1.615 , mean deviance=1.44
|
||
|
|
left son=6 (75 obs) right son=7 (10 obs)
|
||
|
|
Primary splits:
|
||
|
|
age < 56.5 to the right, improve=6.3380, (0 missing)
|
||
|
|
g2 < 22.76 to the right, improve=4.7180, (6 missing)
|
||
|
|
gleason < 8.5 to the left, improve=4.2190, (0 missing)
|
||
|
|
ploidy splits as LRR, improve=1.5590, (0 missing)
|
||
|
|
eet < 1.5 to the right, improve=0.8558, (1 missing)
|
||
|
|
|
||
|
|
Node number 4: 33 observations
|
||
|
|
events=1, estimated rate=0.123 , mean deviance=0.2763
|
||
|
|
|
||
|
|
Node number 5: 28 observations, complexity param=0.01151
|
||
|
|
events=8, estimated rate=0.7346 , mean deviance=0.9858
|
||
|
|
left son=10 (20 obs) right son=11 (8 obs)
|
||
|
|
Primary splits:
|
||
|
|
gleason < 5.5 to the left, improve=2.090, (1 missing)
|
||
|
|
age < 67.5 to the right, improve=1.639, (0 missing)
|
||
|
|
g2 < 14.37 to the right, improve=1.437, (1 missing)
|
||
|
|
|
||
|
|
Node number 6: 75 observations, complexity param=0.01799
|
||
|
|
events=37, estimated rate=1.426 , mean deviance=1.374
|
||
|
|
left son=12 (50 obs) right son=13 (25 obs)
|
||
|
|
Primary splits:
|
||
|
|
gleason < 7.5 to the left, improve=3.5210, (0 missing)
|
||
|
|
g2 < 23.48 to the right, improve=3.3340, (6 missing)
|
||
|
|
age < 69.5 to the left, improve=2.2120, (0 missing)
|
||
|
|
ploidy splits as LRR, improve=1.1190, (0 missing)
|
||
|
|
eet < 1.5 to the right, improve=0.1528, (1 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
grade < 3.5 to the left, agree=0.733, adj=0.2, (0 split)
|
||
|
|
|
||
|
|
Node number 7: 10 observations
|
||
|
|
events=8, estimated rate=3.182 , mean deviance=1.377
|
||
|
|
|
||
|
|
Node number 10: 20 observations
|
||
|
|
events=4, estimated rate=0.5304 , mean deviance=0.7149
|
||
|
|
|
||
|
|
Node number 11: 8 observations
|
||
|
|
events=4, estimated rate=1.307 , mean deviance=1.387
|
||
|
|
|
||
|
|
Node number 12: 50 observations, complexity param=0.01335
|
||
|
|
events=21, estimated rate=1.141 , mean deviance=1.322
|
||
|
|
left son=24 (24 obs) right son=25 (26 obs)
|
||
|
|
Primary splits:
|
||
|
|
g2 < 13.48 to the left, improve=1.87000, (3 missing)
|
||
|
|
ploidy splits as LRR, improve=1.45100, (0 missing)
|
||
|
|
age < 62.5 to the right, improve=0.79680, (0 missing)
|
||
|
|
gleason < 6.5 to the left, improve=0.02209, (0 missing)
|
||
|
|
eet < 1.5 to the right, improve=0.01274, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
age < 66.5 to the right, agree=0.596, adj=0.174, (3 split)
|
||
|
|
eet < 1.5 to the right, agree=0.553, adj=0.087, (0 split)
|
||
|
|
gleason < 6.5 to the left, agree=0.553, adj=0.087, (0 split)
|
||
|
|
|
||
|
|
Node number 13: 25 observations, complexity param=0.01541
|
||
|
|
events=16, estimated rate=2.031 , mean deviance=1.339
|
||
|
|
left son=26 (10 obs) right son=27 (15 obs)
|
||
|
|
Primary splits:
|
||
|
|
g2 < 15.29 to the right, improve=3.893000, (3 missing)
|
||
|
|
age < 68.5 to the left, improve=1.327000, (0 missing)
|
||
|
|
ploidy splits as RLR, improve=0.858700, (0 missing)
|
||
|
|
eet < 1.5 to the right, improve=0.001483, (1 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
ploidy splits as RLR, agree=0.727, adj=0.4, (3 split)
|
||
|
|
gleason < 8.5 to the right, agree=0.636, adj=0.2, (0 split)
|
||
|
|
age < 57.5 to the left, agree=0.591, adj=0.1, (0 split)
|
||
|
|
eet < 1.5 to the left, agree=0.591, adj=0.1, (0 split)
|
||
|
|
|
||
|
|
Node number 24: 24 observations
|
||
|
|
events=7, estimated rate=0.8007 , mean deviance=1.133
|
||
|
|
|
||
|
|
Node number 25: 26 observations, complexity param=0.01335
|
||
|
|
events=14, estimated rate=1.457 , mean deviance=1.415
|
||
|
|
left son=50 (15 obs) right son=51 (11 obs)
|
||
|
|
Primary splits:
|
||
|
|
g2 < 17.92 to the right, improve=3.170000, (2 missing)
|
||
|
|
age < 64.5 to the left, improve=0.971200, (0 missing)
|
||
|
|
eet < 1.5 to the right, improve=0.961700, (0 missing)
|
||
|
|
gleason < 6.5 to the left, improve=0.005796, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
age < 65.5 to the left, agree=0.708, adj=0.364, (2 split)
|
||
|
|
eet < 1.5 to the right, agree=0.667, adj=0.273, (0 split)
|
||
|
|
gleason < 6.5 to the right, agree=0.625, adj=0.182, (0 split)
|
||
|
|
|
||
|
|
Node number 26: 10 observations
|
||
|
|
events=5, estimated rate=1.216 , mean deviance=1.159
|
||
|
|
|
||
|
|
Node number 27: 15 observations
|
||
|
|
events=11, estimated rate=2.705 , mean deviance=1.263
|
||
|
|
|
||
|
|
Node number 50: 15 observations
|
||
|
|
events=6, estimated rate=0.979 , mean deviance=1.356
|
||
|
|
|
||
|
|
Node number 51: 11 observations
|
||
|
|
events=8, estimated rate=2.171 , mean deviance=1.224
|
||
|
|
|
||
|
|
>
|
||
|
|
>
|
||
|
|
> #
|
||
|
|
> # Continuous y variable
|
||
|
|
> # Use deterministic xgroups: the first group is the 1st, 11th, 21st, etc
|
||
|
|
> # smallest obs, the second is 2, 12, 22, ...
|
||
|
|
>
|
||
|
|
> mystate <- data.frame(state.x77, region=factor(state.region))
|
||
|
|
> names(mystate) <- c("population","income" , "illiteracy","life" ,
|
||
|
|
+ "murder", "hs.grad", "frost", "area", "region")
|
||
|
|
>
|
||
|
|
> xvals <- 1:nrow(mystate)
|
||
|
|
> xvals[order(mystate$income)] <- rep(1:10, length=nrow(mystate))
|
||
|
|
>
|
||
|
|
> fit4 <- rpart(income ~ population + region + illiteracy +life + murder +
|
||
|
|
+ hs.grad + frost , mystate,
|
||
|
|
+ control=rpart.control(minsplit=10, xval=xvals))
|
||
|
|
>
|
||
|
|
> summary(fit4)
|
||
|
|
Call:
|
||
|
|
rpart(formula = income ~ population + region + illiteracy + life +
|
||
|
|
murder + hs.grad + frost, data = mystate, control = rpart.control(minsplit = 10,
|
||
|
|
xval = xvals))
|
||
|
|
n= 50
|
||
|
|
|
||
|
|
CP nsplit rel error xerror xstd
|
||
|
|
1 0.42831 0 1.0000 1.0157 0.2265
|
||
|
|
2 0.13514 1 0.5717 0.5948 0.1747
|
||
|
|
3 0.06458 2 0.4365 0.7005 0.1802
|
||
|
|
4 0.05485 3 0.3720 0.8606 0.2299
|
||
|
|
5 0.05346 4 0.3171 0.8494 0.2297
|
||
|
|
6 0.02479 5 0.2637 0.8289 0.2644
|
||
|
|
7 0.01940 6 0.2389 0.8196 0.2641
|
||
|
|
8 0.01394 7 0.2195 0.8196 0.2641
|
||
|
|
9 0.01000 8 0.2055 0.8117 0.2640
|
||
|
|
|
||
|
|
Variable importance
|
||
|
|
hs.grad life illiteracy murder region population frost
|
||
|
|
28 22 13 12 12 9 5
|
||
|
|
|
||
|
|
Node number 1: 50 observations, complexity param=0.4283
|
||
|
|
mean=4436, MSE=3.7e+05
|
||
|
|
left son=2 (10 obs) right son=3 (40 obs)
|
||
|
|
Primary splits:
|
||
|
|
hs.grad < 44.3 to the left, improve=0.4283, (0 missing)
|
||
|
|
illiteracy < 1.55 to the right, improve=0.3249, (0 missing)
|
||
|
|
region splits as RLRR, improve=0.2285, (0 missing)
|
||
|
|
murder < 11.55 to the right, improve=0.2012, (0 missing)
|
||
|
|
life < 68.9 to the left, improve=0.1672, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
illiteracy < 1.55 to the right, agree=0.90, adj=0.5, (0 split)
|
||
|
|
life < 69.26 to the left, agree=0.90, adj=0.5, (0 split)
|
||
|
|
region splits as RLRR, agree=0.88, adj=0.4, (0 split)
|
||
|
|
murder < 11.55 to the right, agree=0.88, adj=0.4, (0 split)
|
||
|
|
frost < 81 to the left, agree=0.82, adj=0.1, (0 split)
|
||
|
|
|
||
|
|
Node number 2: 10 observations, complexity param=0.0194
|
||
|
|
mean=3640, MSE=6.688e+04
|
||
|
|
left son=4 (7 obs) right son=5 (3 obs)
|
||
|
|
Primary splits:
|
||
|
|
population < 3990 to the left, improve=0.53670, (0 missing)
|
||
|
|
frost < 55 to the left, improve=0.30250, (0 missing)
|
||
|
|
illiteracy < 2.2 to the right, improve=0.29240, (0 missing)
|
||
|
|
hs.grad < 40.8 to the right, improve=0.14540, (0 missing)
|
||
|
|
murder < 12.85 to the left, improve=0.08289, (0 missing)
|
||
|
|
|
||
|
|
Node number 3: 40 observations, complexity param=0.1351
|
||
|
|
mean=4635, MSE=2.477e+05
|
||
|
|
left son=6 (34 obs) right son=7 (6 obs)
|
||
|
|
Primary splits:
|
||
|
|
life < 70.26 to the right, improve=0.25230, (0 missing)
|
||
|
|
murder < 10 to the left, improve=0.16790, (0 missing)
|
||
|
|
hs.grad < 60.95 to the left, improve=0.12350, (0 missing)
|
||
|
|
illiteracy < 0.75 to the left, improve=0.11520, (0 missing)
|
||
|
|
population < 659 to the right, improve=0.08106, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
population < 613.5 to the right, agree=0.875, adj=0.167, (0 split)
|
||
|
|
murder < 11.2 to the left, agree=0.875, adj=0.167, (0 split)
|
||
|
|
hs.grad < 64.55 to the left, agree=0.875, adj=0.167, (0 split)
|
||
|
|
|
||
|
|
Node number 4: 7 observations
|
||
|
|
mean=3516, MSE=3.844e+04
|
||
|
|
|
||
|
|
Node number 5: 3 observations
|
||
|
|
mean=3929, MSE=1.361e+04
|
||
|
|
|
||
|
|
Node number 6: 34 observations, complexity param=0.06458
|
||
|
|
mean=4530, MSE=1.69e+05
|
||
|
|
left son=12 (12 obs) right son=13 (22 obs)
|
||
|
|
Primary splits:
|
||
|
|
population < 1374 to the left, improve=0.20790, (0 missing)
|
||
|
|
life < 70.41 to the left, improve=0.19010, (0 missing)
|
||
|
|
frost < 33.5 to the right, improve=0.10930, (0 missing)
|
||
|
|
illiteracy < 0.75 to the left, improve=0.08942, (0 missing)
|
||
|
|
hs.grad < 59.7 to the left, improve=0.06429, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
frost < 152 to the right, agree=0.794, adj=0.417, (0 split)
|
||
|
|
life < 70.41 to the left, agree=0.735, adj=0.250, (0 split)
|
||
|
|
murder < 2 to the left, agree=0.706, adj=0.167, (0 split)
|
||
|
|
region splits as RRRL, agree=0.676, adj=0.083, (0 split)
|
||
|
|
illiteracy < 1.85 to the right, agree=0.676, adj=0.083, (0 split)
|
||
|
|
|
||
|
|
Node number 7: 6 observations
|
||
|
|
mean=5230, MSE=2.768e+05
|
||
|
|
|
||
|
|
Node number 12: 12 observations, complexity param=0.05485
|
||
|
|
mean=4276, MSE=1.942e+05
|
||
|
|
left son=24 (3 obs) right son=25 (9 obs)
|
||
|
|
Primary splits:
|
||
|
|
population < 994.5 to the right, improve=0.4355, (0 missing)
|
||
|
|
life < 71.89 to the left, improve=0.2955, (0 missing)
|
||
|
|
frost < 172.5 to the left, improve=0.2333, (0 missing)
|
||
|
|
illiteracy < 0.75 to the left, improve=0.1965, (0 missing)
|
||
|
|
murder < 2.55 to the right, improve=0.1847, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
life < 70.47 to the left, agree=0.833, adj=0.333, (0 split)
|
||
|
|
|
||
|
|
Node number 13: 22 observations, complexity param=0.05346
|
||
|
|
mean=4668, MSE=1.01e+05
|
||
|
|
left son=26 (4 obs) right son=27 (18 obs)
|
||
|
|
Primary splits:
|
||
|
|
hs.grad < 52.05 to the left, improve=0.44500, (0 missing)
|
||
|
|
region splits as RLLR, improve=0.35050, (0 missing)
|
||
|
|
life < 71.56 to the left, improve=0.12220, (0 missing)
|
||
|
|
murder < 5.65 to the right, improve=0.10520, (0 missing)
|
||
|
|
population < 2980 to the left, improve=0.06276, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
region splits as RLRR, agree=0.864, adj=0.25, (0 split)
|
||
|
|
|
||
|
|
Node number 24: 3 observations
|
||
|
|
mean=3772, MSE=3.261e+04
|
||
|
|
|
||
|
|
Node number 25: 9 observations
|
||
|
|
mean=4444, MSE=1.353e+05
|
||
|
|
|
||
|
|
Node number 26: 4 observations
|
||
|
|
mean=4218, MSE=2.77e+04
|
||
|
|
|
||
|
|
Node number 27: 18 observations, complexity param=0.02479
|
||
|
|
mean=4768, MSE=6.236e+04
|
||
|
|
left son=54 (8 obs) right son=55 (10 obs)
|
||
|
|
Primary splits:
|
||
|
|
region splits as RRLR, improve=0.4086, (0 missing)
|
||
|
|
illiteracy < 1 to the left, improve=0.3653, (0 missing)
|
||
|
|
murder < 3.05 to the left, improve=0.1805, (0 missing)
|
||
|
|
hs.grad < 52.75 to the right, improve=0.1507, (0 missing)
|
||
|
|
population < 2412 to the left, improve=0.1427, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
illiteracy < 1 to the left, agree=0.833, adj=0.625, (0 split)
|
||
|
|
frost < 108.5 to the right, agree=0.833, adj=0.625, (0 split)
|
||
|
|
life < 72.31 to the right, agree=0.778, adj=0.500, (0 split)
|
||
|
|
murder < 3.05 to the left, agree=0.778, adj=0.500, (0 split)
|
||
|
|
hs.grad < 59.95 to the left, agree=0.667, adj=0.250, (0 split)
|
||
|
|
|
||
|
|
Node number 54: 8 observations
|
||
|
|
mean=4590, MSE=1.009e+04
|
||
|
|
|
||
|
|
Node number 55: 10 observations, complexity param=0.01394
|
||
|
|
mean=4911, MSE=5.832e+04
|
||
|
|
left son=110 (7 obs) right son=111 (3 obs)
|
||
|
|
Primary splits:
|
||
|
|
frost < 109 to the left, improve=0.4423, (0 missing)
|
||
|
|
population < 2820 to the left, improve=0.3546, (0 missing)
|
||
|
|
hs.grad < 57.05 to the right, improve=0.3103, (0 missing)
|
||
|
|
region splits as RL-L, improve=0.2564, (0 missing)
|
||
|
|
illiteracy < 1.2 to the right, improve=0.1921, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
life < 71.94 to the left, agree=0.8, adj=0.333, (0 split)
|
||
|
|
|
||
|
|
Node number 110: 7 observations
|
||
|
|
mean=4806, MSE=2.969e+04
|
||
|
|
|
||
|
|
Node number 111: 3 observations
|
||
|
|
mean=5156, MSE=3.914e+04
|
||
|
|
|
||
|
|
>
|
||
|
|
>
|
||
|
|
> #
|
||
|
|
> # Check out xpred.rpart
|
||
|
|
> #
|
||
|
|
> meany <- mean(mystate$income)
|
||
|
|
> xpr <- xpred.rpart(fit4, xval=xvals)
|
||
|
|
> xpr2 <- (xpr - mystate$income)^2
|
||
|
|
> risk0 <- mean((mystate$income - meany)^2)
|
||
|
|
> xpmean <- as.vector(apply(xpr2, 2, mean)) #kill the names
|
||
|
|
> all.equal(xpmean/risk0, as.vector(fit4$cptable[,'xerror']))
|
||
|
|
[1] TRUE
|
||
|
|
>
|
||
|
|
> xpstd <- as.vector(apply((sweep(xpr2, 2, xpmean))^2, 2, sum))
|
||
|
|
> xpstd <- sqrt(xpstd)/(50*risk0)
|
||
|
|
> all.equal(xpstd, as.vector(fit4$cptable[,'xstd']))
|
||
|
|
[1] TRUE
|
||
|
|
>
|
||
|
|
> #
|
||
|
|
> # recreate subset #3 of the xval
|
||
|
|
> #
|
||
|
|
> tfit4 <- rpart(income ~ population + region + illiteracy +life + murder +
|
||
|
|
+ hs.grad + frost , mystate, subset=(xvals!=3),
|
||
|
|
+ control=rpart.control(minsplit=10, xval=0))
|
||
|
|
> tpred <- predict(tfit4, mystate[xvals==3,])
|
||
|
|
> all.equal(tpred, xpr[xvals==3,ncol(xpr)])
|
||
|
|
[1] TRUE
|
||
|
|
>
|
||
|
|
> # How much does this differ from the "real" formula, more complex,
|
||
|
|
> # found on page 309 of Breiman et al. ?
|
||
|
|
> #xtemp <- (xpr2/outer(rep(1,50),xpmean)) - ((mystate$income - meany)^2)/risk0
|
||
|
|
> #real.se<- xpmean* sqrt(apply(xtemp^2,2,sum))/(risk0*50)
|
||
|
|
>
|
||
|
|
>
|
||
|
|
> # Simple yes/no classification model
|
||
|
|
> fit5 <- rpart(factor(pgstat) ~ age + eet + g2+grade+gleason +ploidy,
|
||
|
|
+ stagec, xval=xgroup)
|
||
|
|
>
|
||
|
|
> fit5
|
||
|
|
n= 146
|
||
|
|
|
||
|
|
node), split, n, loss, yval, (yprob)
|
||
|
|
* denotes terminal node
|
||
|
|
|
||
|
|
1) root 146 54 0 (0.6301 0.3699)
|
||
|
|
2) grade< 2.5 61 9 0 (0.8525 0.1475) *
|
||
|
|
3) grade>=2.5 85 40 1 (0.4706 0.5294)
|
||
|
|
6) g2< 13.2 40 17 0 (0.5750 0.4250)
|
||
|
|
12) ploidy=diploid,tetraploid 31 11 0 (0.6452 0.3548)
|
||
|
|
24) g2>=11.84 7 1 0 (0.8571 0.1429) *
|
||
|
|
25) g2< 11.84 24 10 0 (0.5833 0.4167)
|
||
|
|
50) g2< 11 17 5 0 (0.7059 0.2941) *
|
||
|
|
51) g2>=11 7 2 1 (0.2857 0.7143) *
|
||
|
|
13) ploidy=aneuploid 9 3 1 (0.3333 0.6667) *
|
||
|
|
7) g2>=13.2 45 17 1 (0.3778 0.6222)
|
||
|
|
14) g2>=17.91 22 8 0 (0.6364 0.3636)
|
||
|
|
28) age>=62.5 15 4 0 (0.7333 0.2667) *
|
||
|
|
29) age< 62.5 7 3 1 (0.4286 0.5714) *
|
||
|
|
15) g2< 17.91 23 3 1 (0.1304 0.8696) *
|
||
|
|
>
|
||
|
|
> fit6 <- rpart(factor(pgstat) ~ age + eet + g2+grade+gleason +ploidy,
|
||
|
|
+ stagec, parm=list(prior=c(.5,.5)), xval=xgroup)
|
||
|
|
> summary(fit6)
|
||
|
|
Call:
|
||
|
|
rpart(formula = factor(pgstat) ~ age + eet + g2 + grade + gleason +
|
||
|
|
ploidy, data = stagec, parms = list(prior = c(0.5, 0.5)),
|
||
|
|
xval = xgroup)
|
||
|
|
n= 146
|
||
|
|
|
||
|
|
CP nsplit rel error xerror xstd
|
||
|
|
1 0.39855 0 1.0000 1.2081 0.09381
|
||
|
|
2 0.02335 1 0.6014 0.6679 0.07684
|
||
|
|
3 0.02275 3 0.5548 0.8378 0.08445
|
||
|
|
4 0.01892 5 0.5093 0.8857 0.08585
|
||
|
|
5 0.01530 7 0.4714 0.8857 0.08585
|
||
|
|
6 0.01000 9 0.4408 0.8639 0.08599
|
||
|
|
|
||
|
|
Variable importance
|
||
|
|
g2 grade gleason ploidy age eet
|
||
|
|
28 26 20 18 6 2
|
||
|
|
|
||
|
|
Node number 1: 146 observations, complexity param=0.3986
|
||
|
|
predicted class=0 expected loss=0.5 P(node) =1
|
||
|
|
class counts: 92 54
|
||
|
|
probabilities: 0.500 0.500
|
||
|
|
left son=2 (61 obs) right son=3 (85 obs)
|
||
|
|
Primary splits:
|
||
|
|
grade < 2.5 to the left, improve=12.490, (0 missing)
|
||
|
|
gleason < 5.5 to the left, improve=10.510, (3 missing)
|
||
|
|
ploidy splits as LRR, improve= 9.018, (0 missing)
|
||
|
|
g2 < 13.2 to the left, improve= 8.281, (7 missing)
|
||
|
|
age < 58.5 to the right, improve= 1.520, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
gleason < 5.5 to the left, agree=0.863, adj=0.672, (0 split)
|
||
|
|
ploidy splits as LRR, agree=0.644, adj=0.148, (0 split)
|
||
|
|
g2 < 9.945 to the left, agree=0.630, adj=0.115, (0 split)
|
||
|
|
age < 66.5 to the right, agree=0.589, adj=0.016, (0 split)
|
||
|
|
|
||
|
|
Node number 2: 61 observations, complexity param=0.0153
|
||
|
|
predicted class=0 expected loss=0.2277 P(node) =0.3659
|
||
|
|
class counts: 52 9
|
||
|
|
probabilities: 0.772 0.228
|
||
|
|
left son=4 (33 obs) right son=5 (28 obs)
|
||
|
|
Primary splits:
|
||
|
|
g2 < 11.36 to the left, improve=3.5470, (1 missing)
|
||
|
|
ploidy splits as LRL, improve=3.2970, (0 missing)
|
||
|
|
age < 68.5 to the right, improve=1.2020, (0 missing)
|
||
|
|
gleason < 5.5 to the left, improve=0.6474, (3 missing)
|
||
|
|
eet < 1.5 to the left, improve=0.1910, (1 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
ploidy splits as LR-, agree=0.917, adj=0.815, (0 split)
|
||
|
|
age < 65.5 to the left, agree=0.617, adj=0.148, (1 split)
|
||
|
|
|
||
|
|
Node number 3: 85 observations, complexity param=0.02335
|
||
|
|
predicted class=1 expected loss=0.3429 P(node) =0.6341
|
||
|
|
class counts: 40 45
|
||
|
|
probabilities: 0.343 0.657
|
||
|
|
left son=6 (40 obs) right son=7 (45 obs)
|
||
|
|
Primary splits:
|
||
|
|
g2 < 13.2 to the left, improve=1.96800, (6 missing)
|
||
|
|
ploidy splits as LRR, improve=1.84100, (0 missing)
|
||
|
|
age < 56.5 to the right, improve=1.32300, (0 missing)
|
||
|
|
gleason < 8.5 to the left, improve=1.26900, (0 missing)
|
||
|
|
eet < 1.5 to the right, improve=0.09632, (1 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
ploidy splits as LRL, agree=0.962, adj=0.914, (6 split)
|
||
|
|
age < 68.5 to the right, agree=0.608, adj=0.114, (0 split)
|
||
|
|
gleason < 6.5 to the left, agree=0.582, adj=0.057, (0 split)
|
||
|
|
|
||
|
|
Node number 4: 33 observations
|
||
|
|
predicted class=0 expected loss=0.05055 P(node) =0.1832
|
||
|
|
class counts: 32 1
|
||
|
|
probabilities: 0.949 0.051
|
||
|
|
|
||
|
|
Node number 5: 28 observations, complexity param=0.0153
|
||
|
|
predicted class=0 expected loss=0.4053 P(node) =0.1828
|
||
|
|
class counts: 20 8
|
||
|
|
probabilities: 0.595 0.405
|
||
|
|
left son=10 (20 obs) right son=11 (8 obs)
|
||
|
|
Primary splits:
|
||
|
|
gleason < 5.5 to the left, improve=1.1580, (1 missing)
|
||
|
|
age < 67.5 to the right, improve=1.1420, (0 missing)
|
||
|
|
g2 < 14.37 to the right, improve=0.8086, (1 missing)
|
||
|
|
|
||
|
|
Node number 6: 40 observations, complexity param=0.02335
|
||
|
|
predicted class=1 expected loss=0.4426 P(node) =0.2824
|
||
|
|
class counts: 23 17
|
||
|
|
probabilities: 0.443 0.557
|
||
|
|
left son=12 (7 obs) right son=13 (33 obs)
|
||
|
|
Primary splits:
|
||
|
|
g2 < 11.84 to the right, improve=1.42400, (5 missing)
|
||
|
|
ploidy splits as LLR, improve=1.31000, (0 missing)
|
||
|
|
gleason < 7.5 to the left, improve=0.86340, (0 missing)
|
||
|
|
age < 61.5 to the right, improve=0.57940, (0 missing)
|
||
|
|
eet < 1.5 to the left, improve=0.05363, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
ploidy splits as RLR, agree=0.857, adj=0.286, (5 split)
|
||
|
|
|
||
|
|
Node number 7: 45 observations, complexity param=0.02275
|
||
|
|
predicted class=1 expected loss=0.2627 P(node) =0.3517
|
||
|
|
class counts: 17 28
|
||
|
|
probabilities: 0.263 0.737
|
||
|
|
left son=14 (22 obs) right son=15 (23 obs)
|
||
|
|
Primary splits:
|
||
|
|
g2 < 17.91 to the right, improve=4.07900, (1 missing)
|
||
|
|
age < 62.5 to the right, improve=0.66100, (0 missing)
|
||
|
|
gleason < 7.5 to the left, improve=0.16170, (0 missing)
|
||
|
|
eet < 1.5 to the right, improve=0.09922, (1 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
age < 61.5 to the right, agree=0.614, adj=0.190, (1 split)
|
||
|
|
eet < 1.5 to the right, agree=0.591, adj=0.143, (0 split)
|
||
|
|
grade < 3.5 to the right, agree=0.545, adj=0.048, (0 split)
|
||
|
|
gleason < 6.5 to the right, agree=0.545, adj=0.048, (0 split)
|
||
|
|
|
||
|
|
Node number 10: 20 observations
|
||
|
|
predicted class=0 expected loss=0.2987 P(node) =0.124
|
||
|
|
class counts: 16 4
|
||
|
|
probabilities: 0.701 0.299
|
||
|
|
|
||
|
|
Node number 11: 8 observations
|
||
|
|
predicted class=1 expected loss=0.3699 P(node) =0.05878
|
||
|
|
class counts: 4 4
|
||
|
|
probabilities: 0.370 0.630
|
||
|
|
|
||
|
|
Node number 12: 7 observations
|
||
|
|
predicted class=0 expected loss=0.2212 P(node) =0.04187
|
||
|
|
class counts: 6 1
|
||
|
|
probabilities: 0.779 0.221
|
||
|
|
|
||
|
|
Node number 13: 33 observations, complexity param=0.01892
|
||
|
|
predicted class=1 expected loss=0.3841 P(node) =0.2405
|
||
|
|
class counts: 17 16
|
||
|
|
probabilities: 0.384 0.616
|
||
|
|
left son=26 (25 obs) right son=27 (8 obs)
|
||
|
|
Primary splits:
|
||
|
|
g2 < 11 to the left, improve=1.06300, (5 missing)
|
||
|
|
ploidy splits as L-R, improve=0.73950, (0 missing)
|
||
|
|
gleason < 6.5 to the left, improve=0.57220, (0 missing)
|
||
|
|
age < 62.5 to the right, improve=0.13320, (0 missing)
|
||
|
|
eet < 1.5 to the left, improve=0.05492, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
age < 70.5 to the left, agree=0.821, adj=0.286, (5 split)
|
||
|
|
|
||
|
|
Node number 14: 22 observations, complexity param=0.02275
|
||
|
|
predicted class=0 expected loss=0.4933 P(node) =0.1502
|
||
|
|
class counts: 14 8
|
||
|
|
probabilities: 0.507 0.493
|
||
|
|
left son=28 (15 obs) right son=29 (7 obs)
|
||
|
|
Primary splits:
|
||
|
|
age < 62.5 to the right, improve=0.976400, (0 missing)
|
||
|
|
g2 < 23.48 to the right, improve=0.284300, (1 missing)
|
||
|
|
gleason < 7.5 to the left, improve=0.003765, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
gleason < 6.5 to the right, agree=0.773, adj=0.286, (0 split)
|
||
|
|
|
||
|
|
Node number 15: 23 observations
|
||
|
|
predicted class=1 expected loss=0.08092 P(node) =0.2015
|
||
|
|
class counts: 3 20
|
||
|
|
probabilities: 0.081 0.919
|
||
|
|
|
||
|
|
Node number 26: 25 observations, complexity param=0.01892
|
||
|
|
predicted class=1 expected loss=0.4276 P(node) =0.1779
|
||
|
|
class counts: 14 11
|
||
|
|
probabilities: 0.428 0.572
|
||
|
|
left son=52 (17 obs) right son=53 (8 obs)
|
||
|
|
Primary splits:
|
||
|
|
ploidy splits as L-R, improve=2.157000, (0 missing)
|
||
|
|
gleason < 6.5 to the left, improve=1.972000, (0 missing)
|
||
|
|
age < 61.5 to the right, improve=0.971800, (0 missing)
|
||
|
|
g2 < 7.65 to the right, improve=0.404500, (4 missing)
|
||
|
|
eet < 1.5 to the left, improve=0.002614, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
eet < 1.5 to the right, agree=0.72, adj=0.125, (0 split)
|
||
|
|
g2 < 4.33 to the right, agree=0.72, adj=0.125, (0 split)
|
||
|
|
|
||
|
|
Node number 27: 8 observations
|
||
|
|
predicted class=1 expected loss=0.2605 P(node) =0.0626
|
||
|
|
class counts: 3 5
|
||
|
|
probabilities: 0.260 0.740
|
||
|
|
|
||
|
|
Node number 28: 15 observations
|
||
|
|
predicted class=0 expected loss=0.3825 P(node) =0.09682
|
||
|
|
class counts: 11 4
|
||
|
|
probabilities: 0.617 0.383
|
||
|
|
|
||
|
|
Node number 29: 7 observations
|
||
|
|
predicted class=1 expected loss=0.3057 P(node) =0.05334
|
||
|
|
class counts: 3 4
|
||
|
|
probabilities: 0.306 0.694
|
||
|
|
|
||
|
|
Node number 52: 17 observations
|
||
|
|
predicted class=0 expected loss=0.4152 P(node) =0.1115
|
||
|
|
class counts: 12 5
|
||
|
|
probabilities: 0.585 0.415
|
||
|
|
|
||
|
|
Node number 53: 8 observations
|
||
|
|
predicted class=1 expected loss=0.1636 P(node) =0.06643
|
||
|
|
class counts: 2 6
|
||
|
|
probabilities: 0.164 0.836
|
||
|
|
|
||
|
|
> #
|
||
|
|
> # Fit a classification model to the car data.
|
||
|
|
> # Now, since Reliability is an ordered category, this model doesn't
|
||
|
|
> # make a lot of statistical sense, but it does test out some
|
||
|
|
> # areas of the code that nothing else does
|
||
|
|
> #
|
||
|
|
> xcar <- rep(1:8, length=nrow(cu.summary))
|
||
|
|
> carfit <- rpart(Reliability ~ Price + Country + Mileage + Type,
|
||
|
|
+ method='class', data=cu.summary, xval=xcar)
|
||
|
|
>
|
||
|
|
> summary(carfit)
|
||
|
|
Call:
|
||
|
|
rpart(formula = Reliability ~ Price + Country + Mileage + Type,
|
||
|
|
data = cu.summary, method = "class", xval = xcar)
|
||
|
|
n=85 (32 observations deleted due to missingness)
|
||
|
|
|
||
|
|
CP nsplit rel error xerror xstd
|
||
|
|
1 0.30508 0 1.0000 1.0000 0.07200
|
||
|
|
2 0.08475 1 0.6949 0.6949 0.07808
|
||
|
|
3 0.05085 2 0.6102 0.7119 0.07813
|
||
|
|
4 0.03390 3 0.5593 0.6780 0.07800
|
||
|
|
5 0.01000 4 0.5254 0.6780 0.07800
|
||
|
|
|
||
|
|
Variable importance
|
||
|
|
Country Type Price
|
||
|
|
66 22 12
|
||
|
|
|
||
|
|
Node number 1: 85 observations, complexity param=0.3051
|
||
|
|
predicted class=average expected loss=0.6941 P(node) =1
|
||
|
|
class counts: 18 12 26 8 21
|
||
|
|
probabilities: 0.212 0.141 0.306 0.094 0.247
|
||
|
|
left son=2 (58 obs) right son=3 (27 obs)
|
||
|
|
Primary splits:
|
||
|
|
Country splits as ---LRRLLLL, improve=15.220, (0 missing)
|
||
|
|
Type splits as RLLRLL, improve= 4.288, (0 missing)
|
||
|
|
Price < 11970 to the right, improve= 3.200, (0 missing)
|
||
|
|
Mileage < 24.5 to the left, improve= 2.476, (36 missing)
|
||
|
|
|
||
|
|
Node number 2: 58 observations, complexity param=0.08475
|
||
|
|
predicted class=average expected loss=0.6034 P(node) =0.6824
|
||
|
|
class counts: 18 12 23 5 0
|
||
|
|
probabilities: 0.310 0.207 0.397 0.086 0.000
|
||
|
|
left son=4 (9 obs) right son=5 (49 obs)
|
||
|
|
Primary splits:
|
||
|
|
Type splits as RRRRLR, improve=3.187, (0 missing)
|
||
|
|
Price < 11230 to the left, improve=2.564, (0 missing)
|
||
|
|
Mileage < 24.5 to the left, improve=1.802, (30 missing)
|
||
|
|
Country splits as ---L--RLRL, improve=1.329, (0 missing)
|
||
|
|
|
||
|
|
Node number 3: 27 observations
|
||
|
|
predicted class=Much better expected loss=0.2222 P(node) =0.3176
|
||
|
|
class counts: 0 0 3 3 21
|
||
|
|
probabilities: 0.000 0.000 0.111 0.111 0.778
|
||
|
|
|
||
|
|
Node number 4: 9 observations
|
||
|
|
predicted class=Much worse expected loss=0.2222 P(node) =0.1059
|
||
|
|
class counts: 7 0 2 0 0
|
||
|
|
probabilities: 0.778 0.000 0.222 0.000 0.000
|
||
|
|
|
||
|
|
Node number 5: 49 observations, complexity param=0.05085
|
||
|
|
predicted class=average expected loss=0.5714 P(node) =0.5765
|
||
|
|
class counts: 11 12 21 5 0
|
||
|
|
probabilities: 0.224 0.245 0.429 0.102 0.000
|
||
|
|
left son=10 (27 obs) right son=11 (22 obs)
|
||
|
|
Primary splits:
|
||
|
|
Type splits as RLLR-L, improve=2.880, (0 missing)
|
||
|
|
Mileage < 24.5 to the left, improve=2.500, (25 missing)
|
||
|
|
Price < 11470 to the right, improve=2.424, (0 missing)
|
||
|
|
Country splits as ---R--LRLR, improve=1.027, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
Price < 11470 to the right, agree=0.898, adj=0.773, (0 split)
|
||
|
|
Country splits as ---R--RRRL, agree=0.755, adj=0.455, (0 split)
|
||
|
|
|
||
|
|
Node number 10: 27 observations
|
||
|
|
predicted class=average expected loss=0.4074 P(node) =0.3176
|
||
|
|
class counts: 7 4 16 0 0
|
||
|
|
probabilities: 0.259 0.148 0.593 0.000 0.000
|
||
|
|
|
||
|
|
Node number 11: 22 observations, complexity param=0.0339
|
||
|
|
predicted class=worse expected loss=0.6364 P(node) =0.2588
|
||
|
|
class counts: 4 8 5 5 0
|
||
|
|
probabilities: 0.182 0.364 0.227 0.227 0.000
|
||
|
|
left son=22 (14 obs) right son=23 (8 obs)
|
||
|
|
Primary splits:
|
||
|
|
Country splits as ---R--LRRL, improve=1.5190, (0 missing)
|
||
|
|
Price < 8646 to the left, improve=1.2720, (0 missing)
|
||
|
|
Type splits as L--R--, improve=0.1909, (0 missing)
|
||
|
|
Surrogate splits:
|
||
|
|
Price < 13970 to the left, agree=0.864, adj=0.625, (0 split)
|
||
|
|
|
||
|
|
Node number 22: 14 observations
|
||
|
|
predicted class=worse expected loss=0.5714 P(node) =0.1647
|
||
|
|
class counts: 4 6 1 3 0
|
||
|
|
probabilities: 0.286 0.429 0.071 0.214 0.000
|
||
|
|
|
||
|
|
Node number 23: 8 observations
|
||
|
|
predicted class=average expected loss=0.5 P(node) =0.09412
|
||
|
|
class counts: 0 2 4 2 0
|
||
|
|
probabilities: 0.000 0.250 0.500 0.250 0.000
|
||
|
|
|
||
|
|
>
|
||
|
|
>
|
||
|
|
> proc.time()
|
||
|
|
user system elapsed
|
||
|
|
0.742 0.040 0.776
|