Refresher R for Beginners

R Studio Environment

R Location (OSX)

$ ls –l /Library/Frameworks/R.framework/Versions

#Get R Version

version

R01

Environment

getwd()

setwd(“/Users/avkashchauhan/work/global”)

getwd()

dir()

#Getting Help

help(getwd)

#Reading a File

help(read.csv)

filename <- “test.csv”

filex <- read.csv(filename, header = TRUE, sep=”,”)

filex

summary(filex)

filex$id

filex$name

filex$age

filex$zip

names(filex)

attributes(filex)

# Listing All Vars

ls()

# ls() – List of all variables

# DataTypes & number Assignment

asc <- c(1,2,3,4,5,6,7,8,9,10)

# What is c? c is “combine”

asc[2]

asc[5]

asc[5:6]

asc[1:9]

View(asc)

a <- 10

a

a[1]

a[3]

help(sqrt)

a <- sqrt(10)

a

a <- sqrt(10*a)

a

asc

mean(asc)

median(asc)

help(var)

typeof(asc)

typeof(a)

# String data type

a <- c(“this”, “is”, “so”, “fun”)

a

a[1]

typeof(a)

#Understanding c or combine

a <- 10

> a

[1] 10

> a[1]

[1] 10

> a[2]

[1] NA

> a <- c(10)

> a

[1] 10

> a[2]

[1] NA

# DATAFRAME

# creating a data frame

a <- c(1,2,3,4,5,6,7,8,9,10)

b <- c(10,20,30,40,50,60,70,80,90,100)

ab <- data.frame(first=a, second=b)

ab

ab[1]

ab[1][1]

ab[1][2] ß XXX

ab[2]

ab[2][1]

ab[2][2] ß XXX

ab$first

ab$second

ab$second[1]

ab$second[3]

ab$first[10]

View(ab)

#Logical

a <- c(TRUE)

a

typeof(a)

a <- c(FALSE)

a

typeof(a)

#Conditions in R

a <- c(TRUE)

if(!a) a <- c(FALSE)

a ß Still TRUE

if(a) a <- c(FALSE)

a ß FALSE Now

a <- c(TRUE,FALSE)

a

a[1]

a[2]

if (a[1]) a[2] <- TRUE

a

R02

Factor in R – A “factor” is a vector whose elements can take on one of a specific set of values. For example, “Sex” will usually take on only the values “M” or “F,” whereas “Name” will generally have lots of possibilities. The set of values that the elements of a factor can take are called its levels.

a <- factor(c(“Male”, “Female”, “Female”, “Male”, “Male”))

a

a <- factor(c(“A”,”A”,”B”,”A”,”B”,”B”,”C”,”A”,”C”))

a

Tables: (One way and two way)

a <- factor(c(“Male”, “Female”, “Female”, “Male”, “Male”))

a

mytable <- table(a)

a

mytable

summary(a)

attributes(a)

#datatype check R

#Example #1

a <- c(1,2,4)

is.numeric(a)

is.factor(a)

#Example #2

b <- factor(c(“M”, “F”))

b

is.factor(b)

is.numeric(b)

Graph Plotting in R

Using Library ggplot2

#installing ggplot2

install.packages(“ggplot2”)

R03

also installing the dependencies ‘colorspace’, ‘Rcpp’, ‘stringr’, ‘RColorBrewer’, ‘dichromat’, ‘munsell’, ‘labeling’, ‘plyr’, ‘digest’, ‘gtable’, ‘reshape2’, ‘scales’, ‘proto’

Using ggplot2 Library

 

library(ggplot2)

detach(package:ggplot2)

head(diamonds)

View(diamonds)

qplot(clarity, data=diamonds, fill=cut, geom=”bar”)

R04

qplot(clarity, data=diamonds, geom=”bar”, fill=cut, position=”stack”)

qplot(clarity, data=diamonds, geom=”freqpoly”, group=cut, colour=cut, position=”identity”)

R05

qplot(carat, data=diamonds, geom=”histogram”, binwidth=0.1)

qplot(carat, data=diamonds, geom=”histogram”, binwidth=0.01)

R06

Graph Source: http://www.ceb-institute.org/bbs/wp-content/uploads/2011/09/handout_ggplot2.pdf

Keywords:  R, Analysis, ggplot,