## title: “Data visualization with ggplot2” **

author: “Vikash R. Satyal”

date: “3/29/2020”

output: pdf_document

• body, td, is for normal text
• code.r is for r code
• pre is for output of knitr chunks

{r setup, include=TRUE}
knitr::opts_chunk$set(echo = TRUE)

R Markdown

dmtcars<-data.frame(mtcars)


#install.packages("ggplot2")
library(ggplot2)
#   generates a blank sheet
d<-ggplot(data=mtcars, aes(x=wt, y=mpg)) 
d

#fill the blank sheet
d+geom_point()  #scatter diagram

# change point color by  value of 3ed variable  
d+geom_point(aes(color=cyl))

d+geom_point(aes(color=cyl))+scale_color_gradientn(colours = rainbow(5))

#Add point identifying text 
d+geom_point()+geom_text(label=rownames(mtcars), size=2.5)

## Warning: package 'car' was built under R version 3.6.3

## Loading required package: carData

# adding line of best fit & LOWESS fit
d+geom_point()+geom_smooth(method=lm, levels=90) 

## Warning: Ignoring unknown parameters: levels

d+geom_point()+geom_smooth() 

## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

#change plot point size by 3rd variable
ggplot(mtcars, aes(x=wt, y=mpg, size=disp)) +
  geom_point(shape=21, color="black", fill="blue")

#Facet plot for Male & Female
ggplot(Salaries, aes(x=yrs.since.phd, y=salary, color=rank,
shape=rank)) + geom_point() + facet_grid(.~sex)

# type of stack bar & Position of graph label
m<-ggplot(Salaries, aes(x=rank, fill=sex)) 
m+geom_bar(position="stack") + labs(title='position="stack"')

m+geom_bar(position="dodge") + labs(title='position="dodge"')

m+geom_bar(position="fill") + labs(title='position="fill"')

#bar plots of data diamond
ggplot(data = diamonds) +
  geom_bar(mapping = aes(x = cut))

ggplot(data = diamonds) +
  geom_bar(mapping = aes(x = cut, color = cut))

ggplot(data = diamonds) +
  geom_bar(mapping = aes(x = cut, fill = cut))

#time series plot
t <- ggplot(data = economics, aes(x = date, y = unemploy))
t <- t + geom_line()
t

t1 <- t + geom_smooth(method = loess, span=1)
t1

data(singer, package="lattice")
ggplot(singer, aes(x=height))+ geom_histogram()+geom_density(colour="black", adjust=4)

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

#  PLOTS
ggplot(singer, aes(x=voice.part, y=height)) + geom_boxplot()

boxplot(mpg~ gear*am, data=mtcars)

#install.packages("car")
library(car)
ggplot(data=Salaries, aes(x=salary, fill=rank)) +
geom_density(alpha=.3)

#multiple grapgs in one page
g1<-ggplot(data=Salaries, aes(x=rank))+geom_bar()+coord_flip() 
g2<-ggplot(data=Salaries, aes(x=sex))+geom_bar()
g3<-ggplot(data=Salaries,aes(x=yrs.since.phd,y=salary))+geom_point()
g4<-ggplot(data=Salaries,aes(x=rank,y=salary))+
  geom_boxplot()
library(gridExtra)
grid<-grid.arrange(g1,g2,g3,g4,top=("Grid plot of salaries"))

grid

## TableGrob (3 x 2) "arrange": 5 grobs
##   z     cells    name                 grob
## 1 1 (2-2,1-1) arrange       gtable[layout]
## 2 2 (2-2,2-2) arrange       gtable[layout]
## 3 3 (3-3,1-1) arrange       gtable[layout]
## 4 4 (3-3,2-2) arrange       gtable[layout]
## 5 5 (1-1,1-2) arrange text[GRID.text.1608]

#Saving the previous graph 
ggsave("mygrid.pdf", grid, width = 4, height = 5)
# is saved in my 'document' folder

```r
# One ellipse arround all points
ggplot(faithful, aes(waiting, eruptions))+
  geom_point()+
  stat_ellipse()

# Ellipse by groups
p <- ggplot(faithful, aes(waiting, eruptions, color = eruptions > 3))+
  geom_point()
p + stat_ellipse()

# Change the type of ellipses: possible values are "t", "norm", "euclid"
p + stat_ellipse(type = "norm")