Random Forests

Using the ‘iris’ dataset, we create training and datasets using the createDataPartition function in the caret package.

data(iris);library(ggplot2);library(caret)

## Loading required package: lattice

inTrain<-createDataPartition(y=iris$Species,p=0.7,list=FALSE)
training<-iris[inTrain,]
testing<-iris[-inTrain,]

We then fit a model on the training set using random forests.

modFit<-train(Species~.,data=training,method="rf",prox=TRUE)

## Loading required package: randomForest
## randomForest 4.6-12
## Type rfNews() to see new features/changes/bug fixes.

modFit

## Random Forest 
## 
## 105 samples
##   4 predictor
##   3 classes: 'setosa', 'versicolor', 'virginica' 
## 
## No pre-processing
## Resampling: Bootstrapped (25 reps) 
## Summary of sample sizes: 105, 105, 105, 105, 105, 105, ... 
## Resampling results across tuning parameters:
## 
##   mtry  Accuracy   Kappa      Accuracy SD  Kappa SD  
##   2     0.9573069  0.9351308  0.02962483   0.04479868
##   3     0.9603108  0.9396813  0.03162919   0.04780683
##   4     0.9581454  0.9365125  0.03945046   0.05957527
## 
## Accuracy was used to select the optimal model using  the largest value.
## The final value used for the model was mtry = 3.

getTree(modFit$finalModel,k=2)

##    left daughter right daughter split var split point status prediction
## 1              2              3         4        0.80      1          0
## 2              0              0         0        0.00     -1          1
## 3              4              5         3        4.75      1          0
## 4              0              0         0        0.00     -1          2
## 5              6              7         3        4.95      1          0
## 6              8              9         2        3.05      1          0
## 7             10             11         1        6.05      1          0
## 8             12             13         1        6.50      1          0
## 9              0              0         0        0.00     -1          2
## 10            14             15         4        1.70      1          0
## 11             0              0         0        0.00     -1          3
## 12             0              0         0        0.00     -1          3
## 13             0              0         0        0.00     -1          2
## 14             0              0         0        0.00     -1          2
## 15             0              0         0        0.00     -1          3

irisP<-classCenter(training[,c(3,4)],training$Species,modFit$finalModel$prox)
irisP<-as.data.frame(irisP);irisP$Species<-rownames(irisP)
p<-qplot(Petal.Width,Petal.Length,col=Species,data=training)
p+geom_point(aes(x=Petal.Width,y=Petal.Length,col=Species),size=5,shape=4,data=irisP)

Prediction

pred<-predict(modFit,testing);testing$predRight<-pred==testing$Species
table(pred,testing$Species)

##             
## pred         setosa versicolor virginica
##   setosa         15          0         0
##   versicolor      0         15         2
##   virginica       0          0        13

qplot(Petal.Width,Petal.Length,colour=predRight,data=testing,main="newdata Predictions")