R : Copyright 2005, The R Foundation for Statistical Computing
Version 2.1.1  (2005-06-20), ISBN 3-900051-07-0

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 a HTML browser interface to help.
Type 'q()' to quit R.

> ### * <HEADER>
> ###
> attach(NULL, name = "CheckExEnv")
> assign(".CheckExEnv", as.environment(2), pos = length(search())) # base
> ## add some hooks to label plot pages for base and grid graphics
> setHook("plot.new", ".newplot.hook")
> setHook("persp", ".newplot.hook")
> setHook("grid.newpage", ".gridplot.hook")
> 
> assign("cleanEx",
+        function(env = .GlobalEnv) {
+ 	   rm(list = ls(envir = env, all.names = TRUE), envir = env)
+            RNGkind("default", "default")
+ 	   set.seed(1)
+    	   options(warn = 1)
+ 	   delayedAssign("T", stop("T used instead of TRUE"),
+ 		  assign.env = .CheckExEnv)
+ 	   delayedAssign("F", stop("F used instead of FALSE"),
+ 		  assign.env = .CheckExEnv)
+ 	   sch <- search()
+ 	   newitems <- sch[! sch %in% .oldSearch]
+ 	   for(item in rev(newitems))
+                eval(substitute(detach(item), list(item=item)))
+ 	   missitems <- .oldSearch[! .oldSearch %in% sch]
+ 	   if(length(missitems))
+ 	       warning("items ", paste(missitems, collapse=", "),
+ 		       " have been removed from the search path")
+        },
+        env = .CheckExEnv)
> assign("..nameEx", "__{must remake R-ex/*.R}__", env = .CheckExEnv) # for now
> assign("ptime", proc.time(), env = .CheckExEnv)
> grDevices::postscript("randomForest-Examples.ps")
> assign("par.postscript", graphics::par(no.readonly = TRUE), env = .CheckExEnv)
> options(contrasts = c(unordered = "contr.treatment", ordered = "contr.poly"))
> options(warn = 1)    
> library('randomForest')
randomForest 4.5-12 
Type rfNews() to see new features/changes/bug fixes.
> 
> assign(".oldSearch", search(), env = .CheckExEnv)
> assign(".oldNS", loadedNamespaces(), env = .CheckExEnv)
> cleanEx(); ..nameEx <- "MDSplot"
> 
> ### * MDSplot
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: MDSplot
> ### Title: Multi-dimensional Scaling Plot of Proximity matrix from
> ###   randomForest
> ### Aliases: MDSplot
> ### Keywords: classif tree
> 
> ### ** Examples
> 
> set.seed(1)
> data(iris)
> iris.rf <- randomForest(Species ~ ., iris, proximity=TRUE,
+                         keep.forest=FALSE)
> MDSplot(iris.rf, iris$Species)
Loading required package: RColorBrewer
> ## Using different symbols for the classes:
> MDSplot(iris.rf, iris$Species, palette=rep(1, 3), pch=as.numeric(iris$Species))
> 
> 
> 
> cleanEx(); ..nameEx <- "classCenter"
> 
> ### * classCenter
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: classCenter
> ### Title: Prototypes of groups.
> ### Aliases: classCenter
> ### Keywords: classif
> 
> ### ** Examples
> 
> data(iris)
> iris.rf <- randomForest(iris[,-5], iris[,5], prox=TRUE)
> iris.p <- classCenter(iris[,-5], iris[,5], iris.rf$prox)
> plot(iris[,3], iris[,4], pch=21, xlab=names(iris)[3], ylab=names(iris)[4],
+      bg=c("red", "blue", "green")[as.numeric(factor(iris$Species))],
+      main="Iris Data with Prototypes")
> points(iris.p[,3], iris.p[,4], pch=21, cex=2, bg=c("red", "blue", "green"))
> 
> 
> 
> cleanEx(); ..nameEx <- "combine"
> 
> ### * combine
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: combine
> ### Title: Combine Ensembles of Trees
> ### Aliases: combine
> ### Keywords: regression classif
> 
> ### ** Examples
> 
> data(iris)
> rf1 <- randomForest(Species ~ ., iris, ntree=50, norm.votes=FALSE)
> rf2 <- randomForest(Species ~ ., iris, ntree=50, norm.votes=FALSE)
> rf3 <- randomForest(Species ~ ., iris, ntree=50, norm.votes=FALSE)
> rf.all <- combine(rf1, rf2, rf3)
> print(rf.all)

Call:
 randomForest(formula = Species ~ ., data = iris, ntree = 50,      norm.votes = FALSE) 
               Type of random forest: classification
                     Number of trees: 150
No. of variables tried at each split: 2

> 
> 
> 
> cleanEx(); ..nameEx <- "getTree"
> 
> ### * getTree
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: getTree
> ### Title: Extract a single tree from a forest.
> ### Aliases: getTree
> ### Keywords: tree
> 
> ### ** Examples
> 
> data(iris)
> ## Look at the third trees in the forest.
> getTree(randomForest(iris[,-5], iris[,5], ntree=10), 3, labelVar=TRUE)
   left daughter right daughter    split var split point status prediction
1              2              3  Petal.Width        0.80      1       <NA>
2              0              0         <NA>        0.00     -1     setosa
3              4              5  Petal.Width        1.55      1       <NA>
4              0              0         <NA>        0.00     -1 versicolor
5              6              7 Petal.Length        5.05      1       <NA>
6              8              9 Sepal.Length        6.50      1       <NA>
7             10             11  Petal.Width        1.70      1       <NA>
8             12             13 Sepal.Length        5.95      1       <NA>
9              0              0         <NA>        0.00     -1 versicolor
10            14             15  Sepal.Width        2.85      1       <NA>
11             0              0         <NA>        0.00     -1  virginica
12            16             17 Petal.Length        4.65      1       <NA>
13             0              0         <NA>        0.00     -1  virginica
14             0              0         <NA>        0.00     -1 versicolor
15             0              0         <NA>        0.00     -1  virginica
16             0              0         <NA>        0.00     -1  virginica
17             0              0         <NA>        0.00     -1 versicolor
> 
> 
> 
> cleanEx(); ..nameEx <- "grow"
> 
> ### * grow
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: grow
> ### Title: Add trees to an ensemble
> ### Aliases: grow grow.default grow.randomForest
> ### Keywords: regression classif
> 
> ### ** Examples
> 
> data(iris)
> iris.rf <- randomForest(Species ~ ., iris, ntree=50, norm.votes=FALSE)
> iris.rf <- grow(iris.rf, 50)
> print(iris.rf)

Call:
 randomForest(formula = Species ~ ., data = iris, ntree = 50,      norm.votes = FALSE) 
               Type of random forest: classification
                     Number of trees: 100
No. of variables tried at each split: 2

> 
> 
> 
> cleanEx(); ..nameEx <- "imports85"
> 
> ### * imports85
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: imports85
> ### Title: The Automobile Data
> ### Aliases: imports85
> ### Keywords: datasets
> 
> ### ** Examples
> 
> data(imports85)
> imp85 <- imports85[,-2]  # Too many NAs in normalizedLosses.
> imp85 <- imp85[complete.cases(imp85), ]
> ## Drop empty levels for factors.
> imp85[] <- lapply(imp85, function(x) if (is.factor(x)) x[, drop=TRUE] else x)
> 
> stopifnot(require(randomForest))
> price.rf <- randomForest(price ~ ., imp85, do.trace=10, ntree=100)
     |      Out-of-bag   |
Tree |      MSE  %Var(y) |
  10 | 8.872e+06    13.63 |
  20 | 4.533e+06     6.96 |
  30 | 4.314e+06     6.63 |
  40 | 3.939e+06     6.05 |
  50 | 3.845e+06     5.91 |
  60 | 3.914e+06     6.01 |
  70 | 3.759e+06     5.77 |
  80 | 3.68e+06     5.65 |
  90 | 3.751e+06     5.76 |
 100 |  3.8e+06     5.84 |
> print(price.rf)

Call:
 randomForest(formula = price ~ ., data = imp85, do.trace = 10,      ntree = 100) 
               Type of random forest: regression
                     Number of trees: 100
No. of variables tried at each split: 8

          Mean of squared residuals: 3800154
                    % Var explained: 94.16
> numDoors.rf <- randomForest(numOfDoors ~ ., imp85, do.trace=10, ntree=100)
ntree      OOB      1      2
   10:  17.19% 16.22% 18.52%
   20:  11.40%  8.04% 16.05%
   30:  13.47%  9.82% 18.52%
   40:  12.44% 10.71% 14.81%
   50:  11.40%  9.82% 13.58%
   60:  12.44% 10.71% 14.81%
   70:  11.92%  9.82% 14.81%
   80:  10.88%  8.93% 13.58%
   90:  11.40%  8.93% 14.81%
  100:  11.40%  8.04% 16.05%
> print(numDoors.rf)

Call:
 randomForest(formula = numOfDoors ~ ., data = imp85, do.trace = 10,      ntree = 100) 
               Type of random forest: classification
                     Number of trees: 100
No. of variables tried at each split: 4

        OOB estimate of  error rate: 11.4%
Confusion matrix:
     four two class.error
four  103   9  0.08035714
two    13  68  0.16049383
> 
> 
> 
> cleanEx(); ..nameEx <- "margin"
> 
> ### * margin
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: margin
> ### Title: Margins of randomForest Classifier
> ### Aliases: margin plot.margin
> ### Keywords: classif
> 
> ### ** Examples
> 
> set.seed(1)
> data(iris)
> iris.rf <- randomForest(Species ~ ., iris, keep.forest=FALSE)
> plot(margin(iris.rf, iris$Species))
Loading required package: RColorBrewer
> 
> 
> 
> cleanEx(); ..nameEx <- "na.roughfix"
> 
> ### * na.roughfix
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: na.roughfix
> ### Title: Rough Imputation of Missing Values
> ### Aliases: na.roughfix na.roughfix.default na.roughfix.data.frame
> ### Keywords: NA
> 
> ### ** Examples
> 
> data(iris)
> iris.na <- iris
> set.seed(111)
> ## artificially drop some data values.
> for (i in 1:4) iris.na[sample(150, sample(20)), i] <- NA
> iris.roughfix <- na.roughfix(iris.na)
> iris.narf <- randomForest(Species ~ ., iris.na, na.action=na.roughfix)
> print(iris.narf)

Call:
 randomForest(formula = Species ~ ., data = iris.na, na.action = na.roughfix) 
               Type of random forest: classification
                     Number of trees: 500
No. of variables tried at each split: 2

        OOB estimate of  error rate: 4.67%
Confusion matrix:
           setosa versicolor virginica class.error
setosa         50          0         0        0.00
versicolor      0         46         4        0.08
virginica       0          3        47        0.06
> 
> 
> 
> cleanEx(); ..nameEx <- "outlier"
> 
> ### * outlier
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: outlier
> ### Title: Compute outlying measures
> ### Aliases: outlier outlier.randomForest outlier.default
> ### Keywords: classif
> 
> ### ** Examples
> 
> set.seed(1)
> iris.rf <- randomForest(iris[,-5], iris[,5], proximity=TRUE)
> plot(outlier(iris.rf), type="h",
+      col=c("red", "green", "blue")[as.numeric(iris$Species)])
> 
> 
> 
> cleanEx(); ..nameEx <- "partialPlot"
> 
> ### * partialPlot
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: partialPlot
> ### Title: Partial dependence plot
> ### Aliases: partialPlot partialPlot.default partialPlot.randomForest
> ### Keywords: classif regression tree
> 
> ### ** Examples
> 
> data(airquality)
> airquality <- na.omit(airquality)
> set.seed(131)
> ozone.rf <- randomForest(Ozone ~ ., airquality)
> partialPlot(ozone.rf, airquality, Temp)
> 
> data(iris)
> set.seed(543)
> iris.rf <- randomForest(Species~., iris)
> partialPlot(iris.rf, iris, Petal.Width, "versicolor")
> 
> 
> 
> cleanEx(); ..nameEx <- "plot.randomForest"
> 
> ### * plot.randomForest
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: plot.randomForest
> ### Title: Plot method for randomForest objects
> ### Aliases: plot.randomForest
> ### Keywords: classif regression tree
> 
> ### ** Examples
> 
> data(mtcars)
> plot(randomForest(mpg ~ ., mtcars, keep.forest=FALSE, ntree=100), log="y")
> 
> 
> 
> cleanEx(); ..nameEx <- "predict.randomForest"
> 
> ### * predict.randomForest
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: predict.randomForest
> ### Title: predict method for random forest objects
> ### Aliases: predict.randomForest
> ### Keywords: classif regression
> 
> ### ** Examples
> 
> data(iris)
> set.seed(111)
> ind <- sample(2, nrow(iris), replace = TRUE, prob=c(0.8, 0.2))
> iris.rf <- randomForest(Species ~ ., data=iris[ind == 1,])
> iris.pred <- predict(iris.rf, iris[ind == 2,])
> table(observed = iris[ind==2, "Species"], predicted = iris.pred)
            predicted
observed     setosa versicolor virginica
  setosa          5          0         0
  versicolor      0          8         2
  virginica       0          1        14
> 
> 
> 
> cleanEx(); ..nameEx <- "randomForest"
> 
> ### * randomForest
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: randomForest
> ### Title: Classification and Regression with Random Forest
> ### Aliases: randomForest randomForest.formula randomForest.default
> ###   print.randomForest
> ### Keywords: classif regression tree
> 
> ### ** Examples
> 
> ## Classification:
> ##data(iris)
> set.seed(71)
> iris.rf <- randomForest(Species ~ ., data=iris, importance=TRUE,
+                         proximity=TRUE)
> print(iris.rf)

Call:
 randomForest(formula = Species ~ ., data = iris, importance = TRUE,      proximity = TRUE) 
               Type of random forest: classification
                     Number of trees: 500
No. of variables tried at each split: 2

        OOB estimate of  error rate: 4%
Confusion matrix:
           setosa versicolor virginica class.error
setosa         50          0         0        0.00
versicolor      0         47         3        0.06
virginica       0          3        47        0.06
> ## Look at variable importance:
> round(importance(iris.rf), 2)
             setosa versicolor virginica MeanDecreaseAccuracy MeanDecreaseGini
Sepal.Length   1.45       1.89      1.91                 1.35             9.88
Sepal.Width    1.12       0.74      1.07                 0.82             2.52
Petal.Length   3.67       4.39      4.19                 2.51            41.27
Petal.Width    3.83       4.49      4.30                 2.52            45.58
> ## Do MDS on 1 - proximity:
> iris.mds <- cmdscale(1 - iris.rf$proximity, eig=TRUE)
> op <- par(pty="s")
> pairs(cbind(iris[,1:4], iris.mds$points), cex=0.6, gap=0, 
+       col=c("red", "green", "blue")[as.numeric(iris$Species)],
+       main="Iris Data: Predictors and MDS of Proximity Based on RandomForest")
> par(op)
> print(iris.mds$GOF)
[1] 0.4810833 0.5046561
> 
> ## The `unsupervised' case:
> set.seed(17)
> iris.urf <- randomForest(iris[, -5])
> MDSplot(iris.urf, iris$Species)
Loading required package: RColorBrewer
> 
> ## Regression:
> ## data(airquality)
> set.seed(131)
> ozone.rf <- randomForest(Ozone ~ ., data=airquality, mtry=3,
+                          importance=TRUE, na.action=na.omit)
> print(ozone.rf)

Call:
 randomForest(formula = Ozone ~ ., data = airquality, mtry = 3,      importance = TRUE, na.action = na.omit) 
               Type of random forest: regression
                     Number of trees: 500
No. of variables tried at each split: 3

          Mean of squared residuals: 293.4674
                    % Var explained: 73.26
> ## Show "importance" of variables: higher value mean more important:
> round(importance(ozone.rf), 2)
        %IncMSE IncNodePurity
Solar.R   11.95      10603.58
Wind      23.84      45485.92
Temp      45.27      54250.22
Month      5.26       1934.22
Day        1.23       6756.16
> 
> 
> 
> graphics::par(get("par.postscript", env = .CheckExEnv))
> cleanEx(); ..nameEx <- "rfImpute"
> 
> ### * rfImpute
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: rfImpute
> ### Title: Missing Value Imputations by randomForest
> ### Aliases: rfImpute rfImpute.formula rfImpute.default
> ### Keywords: regression classif tree
> 
> ### ** Examples
> 
> data(iris)
> iris.na <- iris
> set.seed(111)
> ## artificially drop some data values.
> for (i in 1:4) iris.na[sample(150, sample(20)), i] <- NA
> set.seed(222)
> iris.imputed <- rfImpute(Species ~ ., iris.na)
ntree      OOB      1      2      3
  300:   4.67%  0.00%  8.00%  6.00%
ntree      OOB      1      2      3
  300:   5.33%  0.00%  8.00%  8.00%
ntree      OOB      1      2      3
  300:   5.33%  0.00%  8.00%  8.00%
ntree      OOB      1      2      3
  300:   6.00%  0.00%  8.00% 10.00%
ntree      OOB      1      2      3
  300:   6.00%  0.00%  8.00% 10.00%
> set.seed(333)
> iris.rf <- randomForest(Species ~ ., iris.imputed)
> print(iris.rf)

Call:
 randomForest(formula = Species ~ ., data = iris.imputed) 
               Type of random forest: classification
                     Number of trees: 500
No. of variables tried at each split: 2

        OOB estimate of  error rate: 5.33%
Confusion matrix:
           setosa versicolor virginica class.error
setosa         50          0         0        0.00
versicolor      0         46         4        0.08
virginica       0          4        46        0.08
> 
> 
> 
> cleanEx(); ..nameEx <- "treesize"
> 
> ### * treesize
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: treesize
> ### Title: Size of trees in an ensemble
> ### Aliases: treesize
> ### Keywords: regression classif
> 
> ### ** Examples
> 
> data(iris)
> iris.rf <- randomForest(Species ~ ., iris)
> hist(treesize(iris.rf))
> 
> 
> 
> cleanEx(); ..nameEx <- "tuneRF"
> 
> ### * tuneRF
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: tuneRF
> ### Title: Tune randomForest for the optimal mtry parameter
> ### Aliases: tuneRF
> ### Keywords: classif tree
> 
> ### ** Examples
> 
> data(fgl, package="MASS")
> fgl.res <- tuneRF(fgl[,-10], fgl[,10], stepFactor=1.5)
mtry = 3  OOB error = 25.7% 
Searching left ...
mtry = 2 	OOB error = 25.7% 
0 0.05 
Searching right ...
mtry = 4 	OOB error = 24.3% 
0.05454545 0.05 
mtry = 6 	OOB error = 24.3% 
0 0.05 
> 
> 
> 
> cleanEx(); ..nameEx <- "varImpPlot"
> 
> ### * varImpPlot
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: varImpPlot
> ### Title: Variable Importance Plot
> ### Aliases: varImpPlot
> ### Keywords: regression classif tree
> 
> ### ** Examples
> 
> set.seed(4543)
> data(mtcars)
> mtcars.rf <- randomForest(mpg ~ ., data=mtcars, ntree=1000, keep.forest=FALSE,
+                           importance=TRUE)
> varImpPlot(mtcars.rf)
> 
> 
> 
> cleanEx(); ..nameEx <- "varUsed"
> 
> ### * varUsed
> 
> flush(stderr()); flush(stdout())
> 
> ### Name: varUsed
> ### Title: Variables used in a random forest
> ### Aliases: varUsed
> ### Keywords: tree
> 
> ### ** Examples
> 
> data(iris)
> set.seed(17)
> varUsed(randomForest(Species~., iris, ntree=100))
[1] 171 113 265 254
> 
> 
> 
> ### * <FOOTER>
> ###
> cat("Time elapsed: ", proc.time() - get("ptime", env = .CheckExEnv),"\n")
Time elapsed:  6.71 1.07 7.91 0 0 
> grDevices::dev.off()
null device 
          1 
> ###
> ### Local variables: ***
> ### mode: outline-minor ***
> ### outline-regexp: "\\(> \\)?### [*]+" ***
> ### End: ***
> quit('no')