ls()

rm(x)

rm(list = ls())

help(rm)

x <- c(1:4,10,"Ram");x

y <- 3:10

rm(x)

# setting working directory

getwd()

setwd("E:\\DataScience\\Week1")

history()

[Link]()

###ctrl+L

version

[Link]("installr")

require(installr)

library(installr)

if(!require(installr)) {
 [Link]("installr");require(installr)

updateR()

###Installing and using packages

[Link]('reshape2')

library(reshape2)

[Link]("installR")

# The basic arithmetic operator

# Addition

x <- 3 + 7

# Substraction

7-3

# Multiplication

3*7

# Divison

7/3

# Exponentiation

2^3

# Modulo: returns the remainder of the division of 8/3

8 %% 3
log2(x) # logarithms base 2 of x

log10(x) # logaritms base 10 of x

exp(x) # Exponential of x

cos(x) # Cosine of x

sin(x) # Sine of x

tan(x) #Tangent of x

abs(x) # absolute value of x

sqrt(x) # square root of x

# Logical

logi <- c(TRUE,FALSE, TRUE, TRUE)

class(logi)

age <- c(34,35,36,34,34,35,36,35)

class(age)

[Link](age)

[Link](age)

[Link](age)

[Link](logi)

age <- [Link](age)

median(x <- 1:10)

# x <- y <- 5

# x <- y = 5

# Vectors

car_name <- c("Honda","BMW","Ferrari")

car_color = c("Black","Blue","Red")

car_cc = c(2000,3400,4000)

# List

cars <- list(name =c("Honda","BMW","Ferrari"),

color =c("Black","Blue","Red"),

cc =c(2000,3400,4000,6000,5000))

list(car_name,car_color,car_cc)

cars

class(cars)
# Matrix

mdat <- matrix(c(1,2,3, 11,12,13), nrow =2, ncol =3, byrow =F,

dimnames =list(c("row1", "row2"), c("C.1", "C.2", "C.3")));mdat

t(mdat)

# Deconstruction

c(mdat)

rowSums(mdat)

colSums(mdat)

# dataframe

cars <- [Link](name =c("Honda","BMW","Ferrari"),

color =c("Black","Blue","Red"),

cc =c(2000,3400,4000));cars

cars

# Factors

apple_colors <- c('green','green','yellow','red','red','red','green')

class(apple_colors)

factor_apple <- factor(apple_colors)

nlevels(factor_apple)

levels(factor_apple)

# String
x <- c("Hello World!")

print(x)

class(x)

length(x)

nchar(x)

substr(x,2,4)

substring(x, 2, 4:6)

######Indexing#######

# A sample vector

v <- c(1,4,4,3,2,2,3)

y <- c(v,c(1,23))

v[c(2,3,4)]

v[c(1,3,6)]

v[-1]

v[c(-1,-3)]

v[2:4]

length(v)

v[length(v)]

# Create a sample data frame

data <- [Link](header=T, text='

subject gender size

1 M 7
 2 F 6

3 F 9

4 M 11

'); data

names(data)

colnames(data)

dimnames(data)

rownames(data)

dim(data)

# Get the element at row 1, column 3

data[1,3]

data[1,"size"]

# Get rows 1 and 2, and all columns

data[1:2, ]

data[,1:2]

dimnames(data)

dimnames(data)[[1]]

data[c(1,3), ]
# Get rows 1 and 2, and only column 2

data[1:2, c(1,2)]

data[c(1,3), 2]

# Get rows 1 and 2, and only the columns named "gender" and "size"

data[1:2, c("gender","size")]

data[c(1,2), c(2,3)]

data[['size']]

###Indexing with a boolean vector

v>2

v[v>2]

v[ c(F,T,T,T,F,F,T)]

# A boolean vector

data$subject < 3

data[data$subject < 3, ]

data[c(TRUE,TRUE,FALSE,FALSE), ]

which(data$subject < 3)

data

##Negative indexing

# Drop the first element

v[-1]

# Drop first three

# Drop just the last element

v[-length(v)]

#####Getting a subset of a data structure

subset(v, v<3)

v[v<3]

# Another vector

t <- c("small", "small", "large", "medium")

# Remove "small" entries

subset(t, t!="small")

t[t!="small"]

# One important difference between the two methods is that you can assign values to

# elements with square bracket indexing, but you cannot with subset().

v[v>3] <- 9

subset(v, v<3) <- 9

subset(data, subject < 3)

data[data$subject < 3, ]

# Subset of particular rows and columns

subset(data, subject < 3, select = c(gender,size))

subset(data, subject < 3, select = gender:size)

data[data$subject < 3, c("gender","size")]

# Logical AND of two conditions

subset(data, subject < 3 & gender=="M")

data[data$subject < 3 & data$gender=="M", ]

# Logical OR of two conditions

subset(data, subject < 3 | gender=="M")

data[data$subject < 3 | data$gender=="M", ]

# Condition based on transformed data

subset(data, log2(size) > 3 )

data[log2(data$size) > 3, ]

# Subset if elements are in another vector

# subset(data, subject %in% c(1,3))

# data[data$subject %in% c(1,3), ]

####vector filled with values########

rep(1, 50)

rep(F, 20)
rep(1:5, 4)

rep(1:5, each=4)

# Use it on a factor

rep(factor(LETTERS[1:3]), 5)

seq(0,10, by=2)

seq(0,10,length=20)

round(seq(0,10,length=20),2)

###Information about variables####

n <- 1:4

let <- LETTERS[1:4]

df <- [Link](n, let)

# List currently defined variables

ls()

# Check if a variable named "x" exists

exists("x")

# Delete variable x

rm(x)

###Information about size/structure

str(n)

str(df)

# Get the length of a vector

length(n)

# Length probably doesn't give us what we want here:

length(df)

# Number of rows

nrow(df)

# Number of columns

ncol(df)

# Get rows and columns

dim(df)

########Working with NULL, NA, and NaN#######

x <- 5

x>2

y <- NA

y>5

z <- NaN

z>5
[Link](x)

[Link](y)

[Link](z)

vy <- c(1, 2, 3, NA, 5)

sum(vy)

sum(vy, [Link]=TRUE)

vz <- c(1, 2, 3, NaN, 5)

sum(vz, [Link]=TRUE)

vx <- c(1, 2, 3, NULL, 5)

sum(vx)

vy[]

vz[]

# R Datasets

data()

data(mtcars)

str(mtcars)

help(mtcars)

head(mtcars)

tail(mtcars)

dim(mtcars)
colnames(mtcars)

summary(mtcars)

# Apply functions

data <- matrix(c(1:10, 21:30), nrow = 5, ncol = 4)

data <- matrix(c(1:10, 21:30), nrow = 5, ncol = 4, byrow = TRUE)

data

# apply

apply(data, 1, sum)

apply(data, 2, mean)

# lapply

data <- list(x = 1:5, y = 6:10, z = 11:15)

lapply(data, FUN = mean)

# sapply

# sapply is the same as lapply, but returns a vector instead of a list.

sapply(data, FUN = mean)

i39 <- sapply(3:9, seq)

sapply(i39, fivenum)
# tapply

# tapply splits the array based on specified data, usually factor levels and then applies the function to it.

library(datasets)

data()

data(mtcars)

help(mtcars)

str(mtcars)

head(mtcars)

apply(mtcars,2,mean)

tapply(mtcars$wt, mtcars$cyl, mean)

groups <- [Link](c(1,1,1,3,4,4,5,6,2,3,5))

#Calculate the number of times each number repeats

tapply(groups, groups, length)

#The output is similar to the function table

table(groups)

# mapply

# mapply is a multivariate version of sapply. It will apply the specified

# function to the first element of each argument first, followed by the

# second element, and so on.

# x <- 1:5
# b <- 6:10

# mapply(sum, x, b)

# # vapply

# vapply(i39, fivenum,c("Min." =0, "1st Qu." =0, "Median" =0, "3rd Qu." =0, "Max." =0))

#Rowbind

x <- c(1:10)

y <- c(11:20)

z <- c(21:30)

a <- rbind(x,y,z);a

# column bind

b <- cbind(x,y,z);b

# Data description

data(mtcars)

head(mtcars$mpg)

help(mtcars)

head(mpg)

attach(mtcars)

head(disp)

detach(mtcars)

dim(mtcars)
str(mtcars)

class(mtcars)

head(mtcars)

tail(mtcars)

# UDF

totalsum <- function(x){

y = sum(x)

return(y)

x <- c(1:130)

totalsum(x)

fib <- function(Fibonacci_terms){

for(i in Fibonacci_terms){

Fibonacci_ter1[i] <- Fibonacci_terms[i-2] + Fibonacci_terms[i-1]

return(Fibonacci_ter1)

xterms <- seq(3, 15, by=1)

fib(xterms)
n <- 1:4

let <- LETTERS[1:4]

df <- [Link](n,let)

myfunction <- function(x) {

y=x-5

return (y)

x<-c(1:10)

myfunction(x)

x <- c(1:10)

y <- c(11:20)

z <- c(21:30)
myfunction <- function( x,y,z) {

y = x+y+z

return (y)

mytable <- [Link](x,y,z,total = myfunction(x,y,z))

mytable

x <- c(1:10)

y <- c(11:20)

z <- c(21:30)

total<-myfunction(x,y,z)

check_total <- function(x) {

y=ifelse(total>5,"yes","no")

return(y)

mydata <- [Link](x,y,z,total,status=ifelse(total>5,"yes","no"))

mydata

mydata$status2 <- ifelse(total>40,"yes","no")

mydata

mydata1 <-subset(mydata,mydata$status=="yes")
mydata2 <-subset(mydata,mydata$status=="no")

mydata1

mydata2

xterm <- seq(3,15,by=1);xterm

fib <- function(fibonacii_terms){

for (i in fibonacii_terms)

fibonacii_terms[i]=fibonacii_terms[i-2] + fibonacii_terms[i-1]

return(fibonacii_terms)

y<-fib(xterm)

mydata

[Link](mydata,"d:/[Link]",[Link]=FALSE,[Link]=TRUE,sep="\t")

str(mtcars)

arrange

mydata<-order(mtcars$mpg ,mtcars$cyl,decreasing =TRUE)

head(mydata)