Table of content

ggplot2 - scatter plot

---

Install library using install.packages("ggplot2")
Import ggplot2 and dplyr library:

> library("ggplot2")
> library("dplyr")

Loading the data set and do some changes to make it usable -

> college <- read.csv('Data/college.csv')
> college <- college %>%
+   mutate(state=as.factor(state), region=as.factor(region),
+          highest_degree=as.factor(highest_degree),
+          control=as.factor(control), gender=as.factor(gender),
+          loan_default_rate=as.numeric(loan_default_rate))

---

Calling ggplot() alone just creates a blank plot -

> ggplot()

Tell ggplot what data to use -

> ggplot(data=college) +
+   geom_point(mapping = aes(x=tuition, y=sat_avg))

The same scatter plot can also be made using qplot which stands for quick plot -

> qplot(data= college, x=tuition, y=sat_avg)

---

Shape

Let’s try representing a different dimension. What if we want to differentiate public vs. private schools? We can do this using the shape attribute -

> ggplot(data=college) +
+   geom_point(mapping=aes(x=tuition, y=sat_avg, 
+                          shape=control))

Using qplot -

> qplot(data = college, x = tuition, y = sat_avg, 
+       shape = control)

---

Color

What if we try color instead of shape to view different categories?

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control))

Using qplot -

> qplot(data = college, x = tuition, y = sat_avg, 
+       color = control)

Using RStudio Addin for coloring

View this link for details on how to install and use this.

> CPCOLS <- c("#8B0A50", "#9A32CD")
> 
> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control))+
+ scale_color_manual(values=CPCOLS)

---

Point size

Let’s alter the size of pointers in accordance to the number of undergraduates in each points -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads))

Using qplot -

> qplot(data = college, x = tuition, y = sat_avg, 
+       color = control, size = undergrads)

---

Alpha - transparency

To add some transparency so we can see through those points -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35)

Using qplot -

> qplot(data = college, x = tuition, y = sat_avg, 
+       color = control, size = undergrads,alpha=I(0.35)) # manually setting alpha = I(n) -- 0<n<1

---

Title and Subtitle

Add title and subtitle using the ggtitle -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   ggtitle("SAT Average score VS Tuition Fee",
+           subtitle = "A comparison study")

Alternatively -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(title = "SAT Average score VS Tuition Fee",
+           subtitle = "A comparison study")

---

Axis labels

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   xlab("Tuition Fees")+
+   ylab("SAT Average Score")

Alternatively using labs -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee",
+        subtitle = "A comparison study")

To plot the title in middle -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee",
+        subtitle = "A comparison study") +
+   theme(plot.title = element_text(hjust = 0.5))

---

Axis limit

Using xlim and ylim -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee",
+        subtitle = "A comparison study")+
+   xlim(0,55000)+ylim(500,1800)

expand_limits doesn’t cut values from the plot -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee",
+        subtitle = "A comparison study")+
+   expand_limits(x=c(0,55000),y=c(1500,2000))

---

Caption

The caption appears in the bottom-right, and is often used for sources, notes or copyright -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee",
+        caption = "Source: U.S. Department of Education")

---

Tag

The plot tag appears at the top-left, and is typically used for labelling a subplot with a letter -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee",
+        subtitle = "A comparison study",
+        caption = "Source: U.S. Department of Education",
+        tag = "A")

---

Changing background color

plot.background changes the color of background of plot and panel.backgrund changes the color of background of panel-

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee",
+        subtitle = "A comparison study",
+        caption = "Source: U.S. Department of Education",
+        tag = "A")+
+   theme(plot.background = element_rect(fill='darkseagreen'))

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee",
+        subtitle = "A comparison study",
+        caption = "Source: U.S. Department of Education",
+        tag = "A")+
+   theme(panel.background = element_rect(fill='azure1'))

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee",
+        subtitle = "A comparison study",
+        caption = "Source: U.S. Department of Education",
+        tag = "A")+
+   theme(panel.background = element_rect(fill='azure1'),
+         plot.background = element_rect(fill='azure1'))

Use element_blank() to remove all grids and colors from background -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee")+
+   theme(panel.background = element_blank())

---

Using Predefined Themes

List of themes: * theme_bw() * theme_minimal() * theme_linedraw() * theme_light() * theme_dark() * theme_classic() * theme_void() * theme_test()

Using classic theme -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee") +
+   theme_classic()

Using minimal theme -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee") +
+   theme_minimal()

Using dark theme -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee") +
+   theme_dark()

More themes can be found from the package ggthemes. Load the package -

> library(ggthemes)

Details on the themes can be found here.

Using the theme solarized -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee") +
+   theme_solarized()

---

Axis grids

Showing both grids in a single color using panel.grid.major -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee")+
+   theme(panel.background = element_blank(),
+         panel.grid.major = element_line("grey"))

Showing only X axis grid using panel.grid.major.x-

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee")+
+   theme(panel.background = element_blank(),
+         panel.grid.major.x = element_line("grey"))

Similarly Y axis grid -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee")+
+   theme(panel.background = element_blank(),
+         panel.grid.major.y = element_line("grey"))

To hide grids use element_blank() -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee")+
+   theme(panel.background = element_blank(),
+         panel.grid.major = element_blank())

---

Legend Customization

Changing Legend Titles

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", 
+        y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee",
+        size="No. of students",
+        color="Institution Type")

Legend position

Can take values - right, left, bottom, top, none.
Example -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", 
+        y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee")+
+   theme(legend.position = "left")

legend.position = "none" to hide the legend-

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", 
+        y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee")+
+   theme(legend.position = "none")

Legend title

To hide the legend title -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", 
+        y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee")+
+   theme(legend.title = element_blank())

Legend Direction

Layout of items in legends (“horizontal” or “vertical”)

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", 
+        y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee")+
+   theme(legend.direction = "vertical",
+         legend.position = "top")

Legend Box Positioning

Using legend.box -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", 
+        y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee")+
+   theme(legend.position = "top",
+           legend.box = "vertical")

To alight the legend box to left, right or center use legend.box.just -

> ggplot(data = college) +
+   geom_point(mapping = aes(x = tuition, y = sat_avg, 
+                          color = control, size = undergrads), 
+              alpha = 0.35) +
+   labs(x = "Tuition Fees", 
+        y = "SAT Average Score",
+        title = "SAT Average score VS Tuition Fee")+
+   theme(legend.position = "top",
+         legend.box = "vertical",
+         legend.box.just = "right")

---

Special thanks to Mike Chappel for his course in Lynda on ggplot2.

Check out https://www.homeworkhelponline.net for R Studio Programming assignment help.