DATA MINING Desktop Survival Guide by Graham Williams
Desktop Survival Project Home List of Figures List of Tables Data Mining Data Mining Data Mining with Rattle Introduction Data Transform Explore A Model Building Framework Unsupervised Modelling Two Class Models Multi Class Models Regression Models Text Mining Evaluation and Deployment Moving into R Troubleshooting R for the Data Miner R Data Graphics in R Understanding Data Preparing Data Building Models Evaluating Models Algorithms Apriori Bagging Bayes Classifier Boosting Cluster Analysis Conditional Trees Hierarchical Clustering K-Means K-Nearest Neighbours Linear Models Logistic Regression Neural Networks Support Vector Machines Text Mining Open Products AlphaMiner Borgelt Data Mining Suite KNime R Rattle Weka Closed Products C4.5 Clementine Equbits Foresight GhostMiner InductionEngine ODM Enterprise Miner Statistica Data Miner TreeNet Virtual Predict Appendicies Glossary Bibliography Index

Saving and Loading R Data and Objects

All R objects can be saved using the save function and then restored at a later time using the load function. The data will be saved into a .RData file. To illustrate this we make use of a standard dataset called iris.

We create a random sample of 20 entities from the dataset. This is done by randomly sampling 20 numbers between 1 and the number of rows (nrow) in the iris dataset, using the sample function. The list of numbers generated by sample is then used to index the iris dataset, to select the sample of rows, by supplying this list of rows as the first argument in the square brackets. The second argument in the square brackets is left blank, indicating that all columns are required in our new dataset. We then save the dataset to file using the save function which compresses the data for storage:

> rows <- sample(1:nrow(iris), 20)
> myiris <- iris[rows,]
> dim(myiris)
[1] 20  5
> save(myiris, file="myiris.RData", compress=TRUE)

At a later date you can load your dataset back into R with the load function:

> load("myiris.RData")
> dim(myiris)
[1] 20  5

Using the compress option will reduce disk space required to store the dataset.

You can save any objects in an R binary file. For example, suppose you have built a model and want to save it for later exploration:

> library(rpart)
> iris.rp <- rpart(Species ~ ., data=iris)
> save(iris.rp, file="irisrp.RData", compress=TRUE)

At a later stage, perhaps on a fresh start of R, you can load the model:

> load("irisrp.RData")
> iris.rp
n= 150 

node), split, n, loss, yval, (yprob)
      * denotes terminal node

1) root 150 100 setosa (0.33333333 0.33333333 0.33333333)  
  2) Petal.Length< 2.45 50   0 setosa (1.00000000 0.00000000 0.00000000) *
  3) Petal.Length>=2.45 100  50 versicolor (0.00000000 0.50000000 0.50000000)  
    6) Petal.Width< 1.75 54   5 versicolor (0.00000000 0.90740741 0.09259259) *
    7) Petal.Width>=1.75 46   1 virginica (0.00000000 0.02173913 0.97826087) *

To identify what is saved into an RData file you can attach the file and then get a listing of its contents:

attach("irisrp.RData")
ls(2)
...
detach(2)

Support further development through the purchase of the PDF version of the book.
Brought to you by Togaware.