R

Text file with code for today:  code.txt

Some other code to try: R plays "Let it Snow"

----------------------------

The code:

#A) Messing Around

#1

  seq(1,10)

  sum(seq(1,10))

#2

  sum(seq(1,1000000))

  sum(as.numeric(seq(1,1000000)))

#3

  mydata<-seq(1,1000, by=2)

  head(mydata)

  mydata[25]

  summary(mydata)

#B) A "FOR" Loop

#Let's repeat ourselves!  A basic "For Loop"

 #4

for(i in 1:15) {

 print("Aggie Pride!")

}

#A MORE INVOLVED LOOP!

#Let's take the 20th-30th items from the our list of numbers 1 to 100 and square them, one at a time, 

#save it to a new data item, and also print them to the screen.

#Initialize variable `my.sq` and run a repeating loop

#5 

 my.sq <- 0

 for(i in 20:30) {

  #put i-th element of `mydata` squared into `i minus 19th` position of `my.sq`

  my.sq[i-19] <- mydata[i]^2

  print(c(i,mydata[i],my.sq[i-19]))

 }

#6 Let's look at the results again

 my.sq

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

#C) Make a list of all numbers from 1 to 1,000 not divisible by 2,3,4,5, 6 or 7

#%% is the mod or modulo operator.

#7

 mydata2<-seq(1,1000)  

 mylist<-mydata[which(mydata2%%2!=0)]

#8

 mylist<-mylist[which(mylist%%3!=0)]

#9

 mylist<-mylist[which(mylist%%5!=0)]

#10

 mylist<-mylist[which(mylist%%7!=0)]

#11

 mylist

#12

 length(mylist)

#D) Let's look at some data from the Titanic shipwreck

#13   install titanic package

  install.packages("titanic")

#14

#load the package into memory for use

 library(titanic)

#15

#make a copy of the main dataset to play with

 data1<-titanic_train

#16

 summary(data1)

#17

 table(data1$Survived)

 attach(data1)

 table(Survived)

#18

 prop.table(table(Survived))

#19

 prop.table(table(Survived,Sex))

 prop.table(table(Survived,Sex),1)

#20

#tell R that some variables should be treated as categories (factors), making a copy

 Survived1<-as.factor(Survived)

 Pclass1<-as.factor(Pclass)

 Sex1<-as.factor(Sex)

#21 A regression, so I don’t get hounded by people

 summary(lm(Fare~Age+Pclass1+Survived1)) 

#22

#make some interesting graphs

 plot(Pclass1,Survived1)

 plot(Sex1,Survived1)

 boxplot(Age)

 boxplot(Age~Pclass1)

#23 two ways of getting average fare by ticket class

 aggregate(Fare,by=list(Pclass1),FUN=mean)

 tapply(Fare, Pclass1, mean)

#24 I don't like the output of the default "summary" command. Let's program a new one!

 sumstats= function(y){

  nums<-sapply(y, is.numeric)

  sumst=sapply(y[,nums], function(x){ sumstat=c(mean(x,na.rm=TRUE),median(x,na.rm=TRUE),sd(x,na.rm=TRUE),min(x,na.rm=TRUE),max(x,na.rm=TRUE))

  names(sumstat)=c("Mean","Median","SD","Min","Max")

  sumstat})

  aperm(sumst)

 }

#25

 sumstats(data1)

#26

 by(data1,Pclass1,sumstats)

#27 A few more graphs

 hist(Fare)

 hist(Fare, breaks=100)

 hist(Fare, breaks=100, xlim=c(0,100))

 plot(Age~Fare)

 plot(Age~Fare,pch=16)

 plot(Age~Fare, col=Pclass,pch=16)

 legend(400,70,legend=c("1st Class","2nd Class","3rd Class"),col=c(1,2,3), pch=16)

#28 another nice graph...

 plot(Age~data1$Fare, col=Pclass,pch=1+15*Survived,xlim=c(-100,500))

 legend(400,80,legend=c("1st Class","2nd Class","3rd Class"),col=c(1,2,3), pch=16, title="Survived")

 legend(400,60,legend=c("1st Class","2nd Class","3rd Class"),col=c(1,2,3), pch=1,title="Perished")

#29 Now let's see who these people in the graph are!

 identify(Age, Fare, labels=Name, tolerance=1)

 identify(data1$Age,data1$Fare,labels=data1$Name,tolerance=1)

#30  Last trick for the day: You can read your own data into R in lots of ways.  On Windows, the easiest way is to copy your data to the clipboard (select data, and hit edit, copy or control-c), then in R type:

 mydata.b=read.delim("clipboard")

#now you can analyze data in R! Note: This is not considered a "professional" way to get your data into R, but it works!