Sample R code

Was searching on good programming languages for data analysis. Open source, easy to undersand, R seems to be the language for data analysis. The following is a bit of R code for you to munch:

## N.B. If you get an error when loading the libraries
## you will need to install them using commands like
##    install.packages("gplots", repos="http://cran.uk.R-project.org/", dependencies=TRUE)
##
## You should only need to do this once for each library.
## You will then need to load them with the
##    library(gplots)
## command  or equivalent each time you use R.

library("party")
library(gplots)
library("vcd")
library("RODBC")
library(e1071)
library("nnet")
library("rpart")
library("mlbench")

## Simple Commands
1+1
10*3
c(1,2,3)
c(1,2,3)*10
x <- 5
x*x
exp(1)

## ------------------------------

## Correlation + Scatterplots
colnames(iris)
plot(iris$Sepal.Length, iris$Petal.Length)
cor(iris$Sepal.Length, iris$Petal.Length)
cor(iris$Sepal.Length, iris$Petal.Length)^2
cor(rank(iris$Sepal.Length), rank(iris$Petal.Length))

cor.sp <- function(x,y) {
  return(cor(rank(x),rank(y)))
}


## ------------------------------
## Plot Scatterplot of Iris data
plotIris1 <- function(){
  table(iris$Species) # is data.frame with 'Species' factor
  iS <- iris$Species == "setosa"
  iV <- iris$Species == "versicolor"
  matplot(c(1, 8), c(0, 4.5), type= "n", xlab = "Length", ylab = "Width",
          main = "Petal and Sepal Dimensions in Iris Blossoms")
  matpoints(iris[iS,c(1,3)], iris[iS,c(2,4)], pch = "sS", col = c(2,4))
  matpoints(iris[iV,c(1,3)], iris[iV,c(2,4)], pch = "vV", col = c(2,4))
  legend(1, 4, c("    Setosa Petals", "    Setosa Sepals",
                 "Versicolor Petals", "Versicolor Sepals"),
         pch = "sSvV", col = rep(c(2,4), 2))
}

plotIris1()
## ------------------------------

# Bar Chart Example with confidence intervals and grid
prettyBarChart <- function(){
  ## Source: R Graph Gallery
  hh <- t(VADeaths)[, 5:1]
  mybarcol <- "gray20"
  ci.l <- hh * 0.85
  ci.u <- hh * 1.15
  mp <- barplot2(hh, beside = TRUE,
                 col = c("lightblue", "mistyrose",
                   "lightcyan", "lavender"),
                 legend = colnames(VADeaths), ylim = c(0, 100),
                 main = "Stairlift Usage in Virginia", font.main = 4,
                 sub = "Faked 95 percent error bars", col.sub = mybarcol,
                 cex.names = 1.5, plot.ci = TRUE, ci.l = ci.l, ci.u = ci.u,
                 plot.grid = TRUE)
  mtext(side = 1, at = colMeans(mp), line = 2,
        text = paste("Mean", formatC(colMeans(hh))), col = "red")
  box()
}
prettyBarChart()

## ------------------------------
## Mosaic Plots
data(HairEyeColor)
mosaic(HairEyeColor, shade = TRUE)

## ------------------------------
## Linear Models
plot(iris$Sepal.Length, iris$Petal.Length)
plot(iris$Sepal.Length, iris$Petal.Length, col="blue",pch=19)

## Make a Model of Petals in terms of Sepals
irisModel <- lm(iris$Petal.Length ~ iris$Sepal.Length)

## plot the corresponding line
abline(irisModel)

## Details of the Model
summary(irisModel)

plot(iris$Petal.Length ~ iris$Species, col="cyan")


## ------------------------------

## Regression Tree

## Select data where Ozone level is known
airq <- subset(airquality, !is.na(Ozone))
## Build a regression tree predicting Ozone 
airct <- ctree(Ozone ~ ., data = airq)
## Show the tree structure
plot(airct)
## Compare actual and predicted values
plot(airq$Ozone,predict(airct))


## Classification Tree
irisct <- ctree(Species ~ .,data = iris)
plot(irisct)
table(predict(irisct), iris$Species)

## Ctree Forest
iriscf <- cforest(Species ~ .,data = iris)
table(predict(iriscf), iris$Species)

## Random Forest
irisrf <- randomForest(Species ~ .,data = iris)
table(predict(irisrf), iris$Species)
varImpPlot(irisrf)

## Naive Bayes
irisnb <- naiveBayes(Species ~ .,data = iris)
table(predict(irisnb, iris[,-5]), iris$Species)

## Neural Net
irisnn <- nnet(Species ~ .,data = iris, size=2)
table(predict(irisnn, iris, type="class"), iris$Species)

## ------------------------------
## SQL Interface

library("RODBC")
channel <- odbcConnect("PostgreSQL30w", case="postgresql")
sqlSave(channel,iris, tablename="iris")
myIris <- sqlQuery(channel, "select * from iris")
summary(myIris)

## ------------------------------
demo(graphics)