R codes

#Extra

#.xlsx --> .csv

#Opening csv file
#data{#variable name} <- read.csv('filename.csv', header=TRUE)

#Opening text file
#data{#variable name} <- read.table('filename.txt', header=TRUE,sep=","{#Because data is seperated by ','s})

#To clear console
#Ctrl + L

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

#Set Path
setwd("F:\\SLIIT\\Practicals\\Year 02 Semester 02\\PS\\R")
getwd()

#Lab7 - 1

#read data from the text file
data<-read.table("lab7.txt",header=TRUE,sep=",")
attach(data)
fix(data)


#Lab7 - 2
#Summary/Strucure of data variable
str(data)


#Lab7 - 3
#str - Used to count obesrvations
#Observations = 517

#Lab7 - 4
min(wind)
max(wind)

#Lab7 - 5
summary(temp)

#Lab7 - 6
boxplot(wind, horizontal = TRUE, outline = TRUE, pch=16)
#pch = Symbols for representing outliers. ex:-8,16,24

#Lab7 - 7(Negative,Positive,Normal)
#Negative

#Lab7 - 8
median(temp)

#Lab7 - 9
mean(wind)
sd(wind)

sapply(data,sd)

#Lab7 - 10
IQR(wind)

#Lab7 - 11
#Create a frequency table with day &month count
freq<-table(day, month)
freq
#Answer = 21

#Lab7 - 12
#Average = Mean
mean(temp[month=='sep'])

#Lab7 - 13
barplot(freq,beside = TRUE,xlab = "Month",ylab="Frequency",legend=rownames(freq))
#Beside = TRUE --> Bars in seperate
#Beside = FALSE --> Bars in one

#Population Mean
mean(nicotine)

#Variance
var(nicotine)

#Standard Deviation
sd(nicotine)

#Lab6 - 2

#Sample values (5 samples)
sam<-sample(nicotine,5)
sam

#5 numbers of random values
#i is variable
for(i in 1:30){
s<-sample(nicotine,5)
samples1<-cbind(samples1,s)
n<-c(n,paste('s',i))
}

#Calculate the mean.
s.mean<-colMeans(samples1)
s.mean

#Calculate variance(2 ways of finding variance.row vise and column vise)

#row vise-->
s.vars<-apply(samples1,1,var)
s.vars

#column vise
s.vars1<-apply(samples1,2,var)
s.vars1

#Comparison of population mean and mean of sample means
msm<-mean(s.mean)
msm

#Comparison of population variance and mean of sample variance of sample means
vsm<-var(s.vars)
vsm

#Controll Statements
team_a <-3
team_b <-4 #Assigning values

#this is a sample if else Statement
if(team_a>team_b){
  print("Team A Wins")
}else{
  print("Team B Wins")
}

setwd("F:\\SLIIT\\Practicals\\Year 02 Semester 02\\PS\\R")

#Get the keyboard input from the keyboard
#my.name is a variable u can use any word
my.name <- readline(prompt = "Enter Name : ")
my.age <- readline(prompt = "Enter age : ")

if(myAge < 18){
  print("You are not major")
}else{
  if(myAge >= 18 & myAge <= 60){
    print("You are eligeble to work")
  }
  else{
    print("Collect your Pension")
  }
}

#Frequency Table
gender.freq<-table(Gender)
gender.freq

accomadation.freq<-table(Accomadation)
accomadation.freq

#Pie chart
pie(gender.freq, main = "Pie chart for gender")
pie(accomadation.freq, main = "Pie chart for accomadation")

#Bar chart
barplot(gender.freq,main="bar chart for Gender", ylab = "Frequency", col = "Red")
#To get x axis
abline(h=0)

barplot(accomadation.freq,main="bar chart for Accomadation", ylab = "Frequency")
#To get x axis
abline(h=0)

#Two way frequency table
gender_accomadation.freq<-table(Accomadation,Gender)
gender_accomadation.freq

#Stack bar chart
barplot(gender_accomadation.freq, main = "Gender and Accomadation",legend = rownames(gender_accomadation.freq))
abline(h=0)

#Clustered bar chart
barplot(gender_accomadation.freq, beside = TRUE, main = "Gender and Accomadation",legend = rownames(gender_accomadation.freq))
abline(h=0)

#Histogram
hist(attendance,main = "Histogram for Attendance",ylab = "Frequency")
hist(salary,main = "Histogram for Salary",ylab = "Frequency")
hist(years,main = "Histogram for Years",ylab = "Frequency")

#Stem-Leaf Plot
stem(attendance)
stem(salary)
stem(years)

#Function for find the modes of a given set of values.
get.mode<-function(x){
  counts<-table(x)
  names(counts[counts==max(counts)])
}

quantile(years)

find.outliers<-function(x){
    q1<-quantile(x)[2]
    q3<-quantile(x)[4]

    iqr<-q3-q1

    ub<-q3+1.5*iqr
    lb<-q3-1.5*iqr

    print(paste("Upper Bound = ",ub))
    print(paste("Lower Bound = ",lb))

    print(paste("Outliers : ",paste(sort(x[x<lb | x>ub]),collapse = ",")))
  }

find.outliers(years)

sheep<-data.frame(height,weight)
fix(sheep)

#Exporting Data frames

#Export Data to CSV and txt
write.csv(sheep,file = "sheepNew.csv")
write.table(sheep,file = "sheeptab1.txt")

histogram<-hist(X2,main="Histogram for number of shareholders",breaks = seq(130,270,length=8))

freq<-histogram$counts
freq

classes<-c()
for(i in 1:length(breaks)-1){
  classes[i]<-paste("[", breaks[i],",", breaks[i+1],")")
}

#column bind - can be used two combine 2 data frames with the same values
cbind(Classes = classes, Frequency = freq)

#Draw frequency polygon in a new plot.(type = p for ponts and type = l for lines)
plot(mids, freq, type = 'l', main = "Frequency Polygon for shareholders",xlab="shareholders",ylab="frequency",ylim = c(0,max(freq)))