Scribd
Upload
14 views9 pages

Toc ch1

The document contains code for performing various statistical analyses in R including principal component analysis, k-means clustering, hierarchical clustering, hypothesis testing, time series analysis, linear regression, ANOVA, and data visualization techniques like histograms, dot plots, and bar plots using the built-in mtcars dataset. Various packages are also loaded and functions used to conduct the analyses and visualize the results.

Uploaded by

Sahil Shete
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
14 views9 pages

Toc ch1

The document contains code for performing various statistical analyses in R including principal component analysis, k-means clustering, hierarchical clustering, hypothesis testing, time series analysis, linear regression, ANOVA, and data visualization techniques like histograms, dot plots, and bar plots using the built-in mtcars dataset. Various packages are also loaded and functions used to conduct the analyses and visualize the results.

Uploaded by

Sahil Shete
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 9

1.

Pca

data("iris")

head(iris)

summary(iris)

library()

"to find principal component"

mypr<-prcomp(iris[,-5],scale=T)

"to understand use of scale"

plot(iris$Sepal.Length,iris$Sepal.Width)

plot(scale(iris$Sepal.Length),scale(iris$Sepal.Width))

mypr

summary(mypr)

plot(mypr,type="l")

biplot(mypr,scale=0)

"extract pc scores"

str(mypr)

mypr$x

iris2<-cbind(iris,mypr$x[,1:2])

head(iris2)

cor(iris[,-5],iris2[,6:7])

"End of prog"

install.packages("pls")

library(pls)

names(iris)

pcmodel<-pcr(Sepal.Length~Species+Sepal.Width+Petal.Length+Petal.Width,ncomp=3,data=iris,scale=T)

iris$pred<-predict(pcmodel,iris,ncomp = 2)

head(iris)
2. "k-means clustering "

data("iris")

names(iris)

new_data<-subset(iris,select = c(-Species))

new_data

cl<-kmeans(new_data,3)

cl

data <- new_data

wss <- sapply(1:15,

function(k){kmeans(data, k )$tot.withinss})

wss

plot(1:15, wss,

type="b", pch = 19, frame = FALSE,

xlab="Number of clusters K",

ylab="Total within-clusters sum of squares")

install.packages("cluster")

library(cluster)

clusplot(new_data, cl$cluster, color=TRUE, shade=TRUE,

labels=2, lines=0)

cl$cluster

cl$centers

3. "agglomarative clustering "

clusters <- hclust(dist(iris[, 3:4]))

plot(clusters)

clusterCut <- cutree(clusters, 3)

table(clusterCut, iris$Species)

ggplot(iris, aes(Petal.Length, Petal.Width, color = iris$Species)) +

geom_point(alpha = 0.4, size = 3.5) + geom_point(col = clusterCut) +

scale_color_manual(values = c('black', 'red', 'green'))


clusters <- hclust(dist(iris[, 3:4]), method = 'average')

clusterCut1 <- cutree(clusters, 3)

table(clusterCut1, iris$Species)

plot(clusters)

ggplot(iris, aes(Petal.Length, Petal.Width, color = iris$Species)) +

geom_point(alpha = 0.4, size = 3.5) + geom_point(col = clusterCut1) +

scale_color_manual(values = c('black', 'red', 'green'))

4. //hypothesis//

dataf<-seq(1,20,by=1)

dataf

mean(dataf)

sd(dataf)

a<-t.test(dataf,alternative="two.sided",mu=10,conf.int=0.95)

5. //time series//

data("AirPassengers")

class(AirPassengers)

start(AirPassengers)

end(AirPassengers)

frequency(AirPassengers)

summary(AirPassengers)

plot(AirPassengers)

abline(reg=lm(AirPassengers~time(AirPassengers)))

cycle(AirPassengers)

plot(aggregate(AirPassengers,FUN=mean))

boxplot(AirPassengers~cycle(AirPassengers))
6. Linear regression

height<-c(102,117,105,141,135,115,138)

weight<-c(61,46,62,54,60,69,51)

student<-lm(weight~height)

student

predict (student,data.frame(height=119),interval="confidence)

plot(student)

7.

ftest<-read.csv(file.choose(),sep=",",header=T)

var.test(ftest$time_g1,ftest$time_g2,alternative = "two.sided")

"one way anova"

data1<-read.csv(file.choose(),sep = ",",header = T)

names(data1)

summary(data1)

head(data1)

anv<-aov(formula = satindex~dept,data=data1)

summary(anv)

8. "two way anova"

data2<-read.csv(file.choose(),sep=",",header = T)

names(data2)

summary(data2)

anv1<-aov(formula = satindex~ dept+exp+dept*exp,data = data2)

summary(anv1)
Practical No :
Aim: Implement regression in R

Code:

attach(mtcars)

plot(wt,mpg)

abline(lm(mpg~wt))

title("Regression of MPG on weight")

Output:

Practical No:
Aim:

Code

Histogram

hist(mtcars$mpg)

hist(mtcars$mpg, breaks = 20, col = "green")

Output:

DotChart

Code:
dotchart(mtcars$mpg,labels = row.names(mtcars),cex = .7,

main="Gas MIlage for Car Models",

xlab = "Miles Per Gallon")

Output:

Barplot

Code

counts<-table(mtcars$gear)

barplot(counts, main="Car Distribution",xlab = "Number of Gears")

output:
Code:

counts<-table(mtcars$gear)

barplot(counts, main="Car Distribution", horiz = TRUE,

names.arg = c("3 Gears","4 Gears", "5 Gears"))

output:

Code:

counts<-table(mtcars$vs,mtcars$gear)

barplot(counts,main = "Car distribution by Gears and VS",

xlab = "Number of gears", col =c("darkblue","red"),

legend= rownames(counts))

output:

You might also like