The R Project SVN R-packages

Rev

Rev 6350 | Blame | Compare with Previous | Last modification | View Log | Download | RSS feed 


R version 2.15.2 (2012-10-26) -- "Trick or Treat"
Copyright (C) 2012 The R Foundation for Statistical Computing
ISBN 3-900051-07-0
Platform: i686-pc-linux-gnu (32-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.

> #
> # The treble test for classification trees
> #  
> #
> library(rpart)
> xgrp <- rep(1:10,length=nrow(cu.summary))
> carfit <- rpart(Country ~ Reliability + Price + Mileage + Type,
+        method='class', data=cu.summary, 
+        control=rpart.control(xval=xgrp))
> 
> carfit2 <- rpart(Country ~ Reliability + Price + Mileage + Type,
+        method='class', data=cu.summary, 
+        weight=rep(3,nrow(cu.summary)),
+        control=rpart.control(xval=xgrp))
> 
> all.equal(carfit$frame$wt,    carfit2$frame$wt/3)
[1] TRUE
> all.equal(carfit$frame$dev,   carfit2$frame$dev/3)
[1] TRUE
> all.equal(carfit$frame[,5:7], carfit2$frame[,5:7])
[1] TRUE
> all.equal(carfit$frame$yval2[,12:21], carfit2$frame$yval2[,12:21])
[1] TRUE
> all.equal(carfit[c('where', 'csplit')],
+     carfit2[c('where', 'csplit')])
[1] TRUE
> xx <- carfit2$splits
> xx[,'improve'] <- xx[,'improve'] / ifelse(xx[,5]> 0,1,3) # surrogate?
> all.equal(xx, carfit$splits)
[1] TRUE
> all.equal(as.vector(carfit$cptable), 
+     as.vector(carfit2$cptable%*% diag(c(1,1,1,1,sqrt(3)))))
[1] TRUE
> 
> summary(carfit2)
Call:
rpart(formula = Country ~ Reliability + Price + Mileage + Type, 
    data = cu.summary, weights = rep(3, nrow(cu.summary)), method = "class", 
    control = rpart.control(xval = xgrp))
  n= 117 

          CP nsplit rel error    xerror       xstd
1 0.23529412      0 1.0000000 1.0000000 0.04530958
2 0.02941176      1 0.7647059 0.8088235 0.04583685
3 0.02205882      3 0.7058824 0.9117647 0.04583685
4 0.01000000      5 0.6617647 0.9558824 0.04563477

Variable importance
Reliability       Price        Type 
         49          30          21 

Node number 1: 117 observations,    complexity param=0.2352941
  predicted class=USA        expected loss=0.5811966  P(node) =1
    class counts:     3     3     6    33    93    27    15     9    15   147
   probabilities: 0.009 0.009 0.017 0.094 0.265 0.077 0.043 0.026 0.043 0.419 
  left son=2 (33 obs) right son=3 (84 obs)
  Primary splits:
      Reliability splits as  RRRLL,       improve=44.777630, (32 missing)
      Type        splits as  LRRLRR,      improve=11.246350, (0 missing)
      Price       < 6923    to the left,  improve=10.448720, (0 missing)
      Mileage     < 22.5    to the right, improve= 6.084489, (57 missing)
  Surrogate splits:
      Type  splits as  RRRLRR,      agree=0.706, adj=0.138, (32 split)
      Price < 6665    to the left,  agree=0.682, adj=0.069, (0 split)

Node number 2: 33 observations,    complexity param=0.02205882
  predicted class=Japan      expected loss=0.4545455  P(node) =0.2820513
    class counts:     3     0     0     3    54    27     3     3     0     6
   probabilities: 0.030 0.000 0.000 0.030 0.545 0.273 0.030 0.030 0.000 0.061 
  left son=4 (9 obs) right son=5 (24 obs)
  Primary splits:
      Price       < 13202   to the right, improve=7.621212, (0 missing)
      Type        splits as  R-LRLL,      improve=5.621212, (0 missing)
      Reliability splits as  RRRRL,       improve=5.406404, (4 missing)
      Mileage     < 23.5    to the left,  improve=3.915966, (9 missing)
  Surrogate splits:
      Type splits as  R-LRLL, agree=0.879, adj=0.556, (0 split)

Node number 3: 84 observations,    complexity param=0.02941176
  predicted class=USA        expected loss=0.4404762  P(node) =0.7179487
    class counts:     0     3     6    30    39     0    12     6    15   141
   probabilities: 0.000 0.012 0.024 0.119 0.155 0.000 0.048 0.024 0.060 0.560 
  left son=6 (30 obs) right son=7 (54 obs)
  Primary splits:
      Price       < 16668.5 to the right, improve=10.403170, (0 missing)
      Type        splits as  RRRLRR,      improve= 6.025974, (0 missing)
      Mileage     < 22.5    to the right, improve= 3.132611, (48 missing)
      Reliability splits as  RLLLL,       improve= 2.195489, (28 missing)
  Surrogate splits:
      Type splits as  RLLRRR, agree=0.714, adj=0.2, (0 split)

Node number 4: 9 observations
  predicted class=Japan      expected loss=0.1111111  P(node) =0.07692308
    class counts:     0     0     0     3    24     0     0     0     0     0
   probabilities: 0.000 0.000 0.000 0.111 0.889 0.000 0.000 0.000 0.000 0.000 

Node number 5: 24 observations,    complexity param=0.02205882
  predicted class=Japan      expected loss=0.5833333  P(node) =0.2051282
    class counts:     3     0     0     0    30    27     3     3     0     6
   probabilities: 0.042 0.000 0.000 0.000 0.417 0.375 0.042 0.042 0.000 0.083 
  left son=10 (7 obs) right son=11 (17 obs)
  Primary splits:
      Price   < 7038    to the left,  improve=4.836134, (0 missing)
      Type    splits as  R--LR-,      improve=1.966667, (0 missing)
      Mileage < 30.5    to the right, improve=1.716667, (6 missing)

Node number 6: 30 observations,    complexity param=0.02941176
  predicted class=USA        expected loss=0.6333333  P(node) =0.2564103
    class counts:     0     3     3    24    12     0     0     0    15    33
   probabilities: 0.000 0.033 0.033 0.267 0.133 0.000 0.000 0.000 0.167 0.367 
  left son=12 (10 obs) right son=13 (20 obs)
  Primary splits:
      Type        splits as  LRR-L-,      improve=6.6000000, (0 missing)
      Price       < 30511   to the right, improve=5.3739130, (0 missing)
      Reliability splits as  RRLLL,       improve=0.3333333, (12 missing)
  Surrogate splits:
      Price < 19422.5 to the left,  agree=0.767, adj=0.3, (0 split)

Node number 7: 54 observations
  predicted class=USA        expected loss=0.3333333  P(node) =0.4615385
    class counts:     0     0     3     6    27     0    12     6     0   108
   probabilities: 0.000 0.000 0.019 0.037 0.167 0.000 0.074 0.037 0.000 0.667 

Node number 10: 7 observations
  predicted class=Japan      expected loss=0.2857143  P(node) =0.05982906
    class counts:     0     0     0     0    15     3     3     0     0     0
   probabilities: 0.000 0.000 0.000 0.000 0.714 0.143 0.143 0.000 0.000 0.000 

Node number 11: 17 observations
  predicted class=Japan/USA  expected loss=0.5294118  P(node) =0.1452991
    class counts:     3     0     0     0    15    24     0     3     0     6
   probabilities: 0.059 0.000 0.000 0.000 0.294 0.471 0.000 0.059 0.000 0.118 

Node number 12: 10 observations
  predicted class=Germany    expected loss=0.5  P(node) =0.08547009
    class counts:     0     0     0    15     3     0     0     0     9     3
   probabilities: 0.000 0.000 0.000 0.500 0.100 0.000 0.000 0.000 0.300 0.100 

Node number 13: 20 observations
  predicted class=USA        expected loss=0.5  P(node) =0.1709402
    class counts:     0     3     3     9     9     0     0     0     6    30
   probabilities: 0.000 0.050 0.050 0.150 0.150 0.000 0.000 0.000 0.100 0.500 

> 
> 
> proc.time()
   user  system elapsed 
  0.188   0.012   0.196