knitr::opts_chunk$set(echo = TRUE, cache = TRUE)
if echo = false, then no code will show in output
Packages
Loading required packages:
library(ggplot2)
library(dplyr)
library(ggthemes)
Setting global theme
theme_set(theme_bw())
Loading excel data
Student <- readxl::read_excel("student_dataset-1.xlsx")
Scatter plot
ggplot( data = iris) +
aes(x = Sepal.Length ,y = Sepal.Width ) +
geom_point()
For species wise scatter plot
ggplot(data= iris) +
geom_point(aes(x = Sepal.Length ,y = Sepal.Width )) +
facet_wrap(~Species)
For geom_point design
ggplot(data= iris, aes(x=Sepal.Length, y=Sepal.Width)) +
geom_point(col= "red", size= 3, shape= 16)
For speices wise color change
ggplot(data= iris, aes(x=Sepal.Length, y=Sepal.Width, col = Species)) +
geom_point() +
labs( x= "Sepal Length", y= "Sepal Width", col = "Species Legend",
title = "Scatter Plot of Sepal Length vs Width")
Histogram
binwidth
ggplot(iris, aes(x= Sepal.Length)) +
geom_histogram(binwidth = .1, fill= "blue", col= "black")
bins number
ggplot(iris, aes(x= Sepal.Length)) +
geom_histogram(bins = 15, fill= "blue", col= "black")
Species wise color change
ggplot(data= iris) +
geom_histogram(aes(x= Sepal.Length, fill = Species), bins = 10, col= "black", alpha= .3)
Reduce gap between plot and axis============
ggplot(data = iris)+
geom_histogram(aes(x= Sepal.Length, fill = Species),
bins = 10, col= "white", alpha= .5) +
coord_cartesian(expand = FALSE)
ggplot(data = iris)+
geom_histogram(aes(x=Sepal.Length, fill = Species),
bins = 10, col= "black", alpha= .6)+
scale_y_continuous(
breaks = seq(0, 40, by= 5),
expand = expansion(
mult = c(0, 0), #expand upper portion of the plot
add = c(0, 0) #increase gap at the bottom portion
)
)
ggplot(data = iris)+
geom_histogram(aes(x=Sepal.Length, fill = Species),
bins = 10, col= "white", alpha= .6)+
scale_y_continuous(expand = expansion(add = c(0, 5)))+
scale_x_continuous(expand = expansion(add = c(0, 0)))
Facet
facet_wrap
ggplot(data=iris)+
geom_histogram(aes(x=Sepal.Length, fill = Species),
bins = 10, col= "black", alpha =.6)+
facet_wrap(vars(Species), ncol= 1)
ggplot(data = iris)+
geom_histogram(aes(x=Sepal.Length, fill = Species),
bins = 10, col= "black", alpha= .6)+
facet_wrap(vars(Species), ncol=1, scale= "free" )
ggplot(data = iris)+
geom_histogram(aes(x=Sepal.Length, fill = Species),
bins = 10, col="black", alpha= 0.6)+
facet_wrap(vars(Species), ncol=3, scale= "free_x")
Facet_grid
ggplot(data = iris)+
geom_histogram(aes(x=Sepal.Length, fill = Species),
bins = 10, col= "black", alpha= .6)+
facet_grid(rows= vars(Species))
ggplot(data = Student)+
geom_histogram(aes(x=GPA, fill = Employment),
bins = 10, col= "black", alpha= .6)+
facet_grid(rows= vars(Employment), cols= vars(Gender))
ggplot(data = Student)+
geom_histogram(aes(x=GPA, fill = Employment),
bins = 10, col= "black", alpha= .6)+
facet_grid(rows= vars(Employment), cols= vars(Class))
Student %>%
mutate(Class= factor(Class, levels = c("Freshman", "Sophomore", "Junior", "Senior"))) %>%
summary()
## ID Gender Age Class
## Min. : 1.00 Length:132 Min. :18.00 Freshman : 4
## 1st Qu.: 33.75 Class :character 1st Qu.:20.00 Sophomore:29
## Median : 66.50 Mode :character Median :22.00 Junior :24
## Mean : 66.50 Mean :21.84 Senior :75
## 3rd Qu.: 99.25 3rd Qu.:24.00
## Max. :132.00 Max. :30.00
## Major Grad Intention GPA Employment
## Length:132 Length:132 Min. :2.340 Length:132
## Class :character Class :character 1st Qu.:2.950 Class :character
## Mode :character Mode :character Median :3.000 Mode :character
## Mean :3.016
## 3rd Qu.:3.300
## Max. :3.680
## Salary Social Networking Satisfaction Spending
## Min. :30.00 Min. : 0.000 Min. :1.000 Min. : 700.0
## 1st Qu.:50.00 1st Qu.: 0.000 1st Qu.:3.000 1st Qu.: 800.0
## Median :60.00 Median : 6.500 Median :4.000 Median : 900.0
## Mean :57.89 Mean : 4.902 Mean :3.523 Mean : 952.3
## 3rd Qu.:65.00 3rd Qu.: 8.000 3rd Qu.:4.000 3rd Qu.:1100.0
## Max. :85.00 Max. :12.000 Max. :6.000 Max. :1200.0
## Computer Text Messages Wealth
## Length:132 Min. : 0.0 Min. : 0.100
## Class :character 1st Qu.: 40.0 1st Qu.: 0.200
## Mode :character Median :300.0 Median : 1.500
## Mean :267.6 Mean : 6.825
## 3rd Qu.:500.0 3rd Qu.: 10.000
## Max. :600.0 Max. :100.000
Theme======
Build in Theme
ggplot(data=iris)+
geom_histogram(aes(x=Sepal.Length, fill = Species),
bins = 10, col= "black", alpha =.6)+
facet_wrap(vars(Species), ncol= 1)+
theme_minimal()
Other pre-build theme (ggthemes)
ggplot(data=iris)+
geom_histogram(aes(x=Sepal.Length, fill = Species),
bins = 10, col= "black", alpha =.6)+
facet_wrap(vars(Species), ncol= 1)+
theme_calc()
ggthemeAssist
p1 <- ggplot(data=iris)+
geom_histogram(aes(x=Sepal.Length, fill = Species),
bins = 10, col= "black", alpha =.6)+
facet_wrap(vars(Species), ncol= 1)+
labs(
title = "Histogram of Sepal Length by Species",
x = "Sepal Length",
y = "Frequency",
fill = "Species Legend",
subtitle = "Using Facet and other customizations",
caption = "Data : Iris"
)
Manually changing color
ggplot(data=iris)+
geom_histogram(aes(x=Sepal.Length, fill = Species),
bins = 10, col= "black", alpha =.6)+
facet_wrap(vars(Species), ncol= 1)+
scale_fill_manual(values = c("setosa"= "tomato", "versicolor"="black", "virginica" ="skyblue"))
ggplot(data=iris)+
geom_histogram(aes(x=Sepal.Length, fill = Species),
bins = 10, col= "black", alpha =1)+
facet_wrap(vars(Species), ncol= 1)+
scale_fill_brewer(palette = "Set1")
