R workshop - 1

R as a calculator

10+5
10-5
4*6
16/4
2^8

2*5-(2^5)/8

Logical operators

2 == 2 # is it equal?
3 > 2 # is it larger?
3 < 1 # is it smaller?
4 != 0 # is it not equal?

Variables and funcions

Lets define some variables

x <- 1
y <- 2
str1 <- "hello world"

print( str1 )
x; y; str1

z <- x+y
z

z = z + 1

z

Variables stored in our workspace

ls() 
#or
objects()

rm(z) #remove
# save.image() # save variables in the workspace
#q() #quits the session
# load( ".RData" ) # load the workspace

z

ls()

Built-in functions

sqrt(1024) # square root
log(4) # Ln
mean(c(100,50,35)) # mean
exp(2) #e^2
round( exp(2), digits=1 ) # most built-in functions have options

Getting some help with built-in functions

?round # documentation

help(round)

We can also built functions

mySEM <- function(x){
return(sd(x)/sqrt(length(x)))
}

example_list <- c(1,5,8,2,4,5,6,7,44,1,5,6,7,8,6,8,9)
mySEM(example_list)

Where are we working?

getwd() # get working directory
dir <- getwd()

setwd("/home/jovyan/work/data/") # set working directory
getwd() 
list.files(path = ".")

setwd("/home/jovyan/work") # set working directory
getwd()

current_dir="."
list.files(path = current_dir)

Executing script from file

myCofV(example_list)

source("my-functions.R") # run from script

myCofV(example_list)

There are various types of objects

class( 2 )  # find the object type of v1
class( c(1,5,7) )
mode("Hello")  # and similarly
mode(2==2)
mode(TRUE)

Vectors

x <- c(1, 2, 3) # Combine Values into a Vector or List

mean(x)
min(x)
max(x)

s <- c( min(x),max(x) )

s

Operationson vector elements

v1 <- c(1,2,3)
c1 <- c( "a", "b", "c", "d" )

v1 * 3 
toupper( c1 )

Matrixes

testVector<-c(1,2,3,4,5,6,7,8,9)
m1 <- matrix( testVector, nrow=3, ncol=3 ) # matrix: table of n rows and m columns, only one type of data allowed and equal length  required
colnames(m1)<-c('1','2','3')
rownames(m1)<-c('A','B','C')
m1

cbind(m1,"4"=c(1,2,3))
rbind(m1,"D"=c(6,5,4))

Data frame

var1 <- c( "John", "Paul", "George", "Ringo" )
var2 <- c( 123456, 234567, 345678, 456789 )
var3 <- c( 8.5, 9.0, 5.0, 6.75 )
classroom <- data.frame( ID=var2, Score=var3 ) #data.frame: table of n rows and c columns, different types per column allowed
rownames( classroom ) <- var1

classroom

Retrieving data

classroom[1]

classroom$ID # each column can be accessed with its name

classroom[,1]

classroom[1,]

classroom[1,2]

classroom[classroom$ID==234567,]

classroom["Paul",]

classroom["Paul","Score"]

Activity

RECORDS <- data.frame(
ID=seq(from=1, to=40, by=1),
Sex=c(rep("Male",times=20),rep("Female",times=20)), 
Age=round(rnorm(40, mean=55, sd=5),digits=0),
Score=c(rnorm(20, mean=70, sd=10),rnorm(20, mean=20, sd=15))
)

RECORDS

# 1 Get a new table just for women
# 2 Select only the indivuduals with score higher than the mean score 
# 3 Select only the men with a score higher than 70 and age lower than 55
# 4 Order all individuals by score