ggplot2 - line diagram

---

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

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

Creating sample data set -

> date <- seq(from=as.Date("1/1/2020", format("%d/%m/%y")), 
+             by = "year", 
+             length.out = 20)
> set.seed(99)
> prod <- round(abs(rnorm(20)*100))
> df <- data.frame(date, prod)
> df

         date prod
1  2020-01-01   21
2  2021-01-01   48
3  2022-01-01    9
4  2023-01-01   44
5  2024-01-01   36
6  2025-01-01   12
7  2026-01-01   86
8  2027-01-01   49
9  2028-01-01   36
10 2029-01-01  129
11 2030-01-01   75
12 2031-01-01   92
13 2032-01-01   75
14 2033-01-01  251
15 2034-01-01  304
16 2035-01-01    0
17 2036-01-01   39
18 2037-01-01  175
19 2038-01-01   50
20 2039-01-01   27

Create a line graph using geom_line() -

> ggplot(data=df, aes(x=date, y=prod)) +
+   geom_line()

Add points to the line -

> ggplot(data=df, aes(x=date, y=prod)) +
+   geom_line() +
+   geom_point()

---

Line type

The different line types available in R software are : “blank”, “solid”, “dashed”, “dotted”, “dotdash”, “longdash”, “twodash”. Example of a dashed line -

> ggplot(data=df, aes(x=date, y=prod)) +
+   geom_line(linetype="dashed") +
+   geom_point()

Example of a twodash line -

> ggplot(data=df, aes(x=date, y=prod)) +
+   geom_line(linetype="twodash") +
+   geom_point()

---

Line Size

To change the size of the line the argument size can be used -

> ggplot(data=df, aes(x=date, y=prod)) +
+   geom_line(size=2) +
+   geom_point()

---

Line Transparency

To change the transparency of the line the argument alpha can be used -

> ggplot(data=df, aes(x=date, y=prod)) +
+   geom_line(size = 2, alpha=0.2) +
+   geom_point()

---

Line Color

Specify the color name in the color argument -

> ggplot(data=df, aes(x=date, y=prod)) +
+   geom_line(color="red") +
+   geom_point()

---

Title and axis names

Using labs() -

> ggplot(data=df, aes(x=date, y=prod)) +
+   geom_line(color="red") +
+   geom_point()+
+   labs(title="Example of a line chart",
+        x="X axis title",
+        y="Y axis title")

Using ggtitle, xlab and ylab -

> ggplot(data=df, aes(x=date, y=prod)) +
+   geom_line(color="red") +
+   geom_point()+
+   ggtitle("Example of a line chart")+
+   xlab("X axis title")+
+   ylab("Y axis title")

---

Fitting a line

A line can be fitted on the points using geom_smooth() -

> ggplot(data=df, aes(x=date, y=prod)) +
+   geom_smooth() +
+   geom_point()

To hide the standard error area around the line set the argument se=F inside geom_smooth() -

> ggplot(data=df, aes(x=date, y=prod)) +
+   geom_smooth(se=F) +
+   geom_point()

---

Stairs Line

Using geom_step() instead of geom_line -

> ggplot(data=df, aes(x=date, y=prod)) +
+   geom_step() +
+   geom_point()

---

Area plot

To change the transparency of the line the argument alpha can be used -

> ggplot(data=df, aes(x=date, y=prod)) +
+   geom_area(fill="#E69F00", alpha=0.2) +
+   geom_point()

---

Multiple Line

For this we are using the built in economics data set -

> head(economics) 

# A tibble: 6 x 6
  date         pce    pop psavert uempmed unemploy
  <date>     <dbl>  <dbl>   <dbl>   <dbl>    <dbl>
1 1967-07-01  507. 198712    12.6     4.5     2944
2 1967-08-01  510. 198911    12.6     4.7     2945
3 1967-09-01  516. 199113    11.9     4.6     2958
4 1967-10-01  512. 199311    12.9     4.9     3143
5 1967-11-01  517. 199498    12.8     4.7     3066
6 1967-12-01  525. 199657    11.8     4.8     3018

> ls.str(economics)

date :  Date[1:574], format: "1967-07-01" "1967-08-01" "1967-09-01" "1967-10-01" "1967-11-01" ...
pce :  num [1:574] 507 510 516 512 517 ...
pop :  num [1:574] 198712 198911 199113 199311 199498 ...
psavert :  num [1:574] 12.6 12.6 11.9 12.9 12.8 11.8 11.7 12.3 11.7 12.3 ...
uempmed :  num [1:574] 4.5 4.7 4.6 4.9 4.7 4.8 5.1 4.5 4.1 4.6 ...
unemploy :  num [1:574] 2944 2945 2958 3143 3066 ...

Here is a plot with date on X axis and personal saving rate (psavert) on Y axis -

> ggplot(economics, aes(x=date)) + 
+   geom_line(aes(y = psavert), color = "red") 

Let’s add another line to the plot -

> ggplot(economics, aes(x=date)) + 
+   geom_line(aes(y = psavert), color = "darkred") + 
+   geom_line(aes(y = uempmed), color="steelblue") +
+   xlab("Date") + ylab("Values")

---

Adding legend

Let’s assume we have two data sets of production and sales over time -

> date <- seq(from=as.Date("1/1/2020", format("%d/%m/%y")), by = "year", length.out = 20)
> set.seed(99)
> prod <- round(abs(rnorm(20)*100))
> sale <- round(abs(rnorm(20)*100))
> dprod <- data.frame(date, prod)
> dsale <- data.frame(date, sale)

We need to do some data wrangling to prepare the data for the visualization-

> df <- dprod %>% 
+   mutate(date, prod, Sector="Production") %>% 
+   rename(Values = prod) %>% 
+   bind_rows(dsale %>% 
+           mutate(date, sale, Sector="Sale") %>% 
+           rename(Values = sale))
> ls.str(df)

date :  Date[1:40], format: "2020-01-01" "2021-01-01" "2022-01-01" "2023-01-01" "2024-01-01" ...
Sector :  chr [1:40] "Production" "Production" "Production" "Production" ...
Values :  num [1:40] 21 48 9 44 36 12 86 49 36 129 ...

Now use color/linetype to use different line for different group and a legend will be generated -

> ggplot(df, aes(x = date, y = Values, color = Sector)) + 
+   geom_line() +
+   ggtitle("Multiple Line Example")

Using line type -

> ggplot(df, aes(x = date, y = Values, linetype = Sector, color = Sector)) + 
+   geom_line() +
+   ggtitle("Multiple Line Example") + 
+   geom_point()

Expert solutions to R Studio statistics assignments.