geom_bar two datasets together in R - r

Question

I have two dataframes with two columns each, that I would like to plot together as a barplot using ggplot in R as shown below:
How can I do this using dplyr in R?
Sample Data:
DF1
Code Count_2020
A 1
B 2
C 3
D 4
E 5
F 6
DF2
Code Count_2021
A 4
B 8
C 6
D 8
E 10
F 12
So, I first thought of merging the two dataframes into one using dplyr::inner_join, and I got a new dataframe as shown below:
Code Count_2021 Count_2020
A 4 1
B 8 2
C 6 3
D 8 4
E 10 5
F 12 6
Next I thought of using dplyr::gather to plot the count data from both years together as Type and Value, but this messed up the gathered dataframe as the output changed to:
Type Value
Code A
Code B
Code C
Code D
Code E
Code F
Code I tried
library(tidyverse)
# Merge DF1 and DF2
DF = inner_join(DF1, DF2)
# Gather data for plotting
Gathered_DF= DF%>% dplyr::select(Code, Count_2020, Count_2021) %>%
gather(key = Type, value = Value) # Output not as expected, stuck!!

Answer 1

We can reshape to 'long' format with pivot_longer after the join and then use geom_col in ggplot2 with position specified as 'dodge' and fill as 'Year`
library(dplyr)
library(tidyr)
library(ggplot2)
inner_join(DF1, DF2) %>%
pivot_longer(cols = -Code, names_to = 'Year', names_prefix = 'Count_') %>%
ggplot(aes(x = Code, y = value, fill = Year)) +
geom_col(position = 'dodge') +
theme_bw()
-output
data
DF1 <- structure(list(Code = c("A", "B", "C", "D", "E", "F"),
Count_2020 = 1:6), class = "data.frame", row.names = c(NA,
-6L))
DF2 <- structure(list(Code = c("A", "B", "C", "D", "E", "F"), Count_2021 = c(4L,
8L, 6L, 8L, 10L, 12L)), class = "data.frame", row.names = c(NA,
-6L))

Answer 2

You can use pivot_longer instead of gather as it is superseded in tidyr 1.1.3
library(tidyverse)
df1 <- data.frame(Code = c("A", "B", "C", "D", "E", "F"),
Count_2020 = c(1,2,3,4,5,6))
df2 <- data.frame(Code = c("A", "B", "C", "D", "E", "F"),
Count_2021 = c(4, 8, 6, 8, 10, 12))
df_joined <- df1 %>%
inner_join(df2, by = "Code") %>%
pivot_longer(cols = !Code, names_to = "Year", names_prefix = "Count_", values_to = "Count")
df_joined
#> # A tibble: 12 x 3
#> Code Year Count
#> <fct> <chr> <dbl>
#> 1 A 2020 1
#> 2 A 2021 4
#> 3 B 2020 2
#> 4 B 2021 8
#> 5 C 2020 3
#> 6 C 2021 6
#> 7 D 2020 4
#> 8 D 2021 8
#> 9 E 2020 5
#> 10 E 2021 10
#> 11 F 2020 6
#> 12 F 2021 12
ggplot(df_joined, aes(x = Code, y = Count, fill = Year)) +
geom_bar(stat = "identity", position = "dodge")
In the code above, the argument inside pivot_longer are:
cols = !Code it means the column to be pivoted that is all column except Code
names_to = "Year" it means the name of column to be created for grouping
names_prefix = "Count_" is used to remove the string "Count_" from the created column "Year"
values_to = "Count" it means the name of column to created for stored value from each group.
You can learn more about this function by simply call ?pivot_longer

Answer 3

Use pivot_longer() to reshape your data then plot using ggplot.
Bonus: to add text on the bars, use geom_bar_text from the ggfittext package
library(tidyverse)
DF1 <- read.table(text = "Code Count_2020
A 1
B 2
C 3
D 4
E 5
F 6", header = TRUE)
DF2 <- read.table(text = "Code Count_2021
A 4
B 8
C 6
D 8
E 10
F 12", header = TRUE)
DF <- left_join(DF1, DF2, by = "Code")
DF_long <- DF %>%
pivot_longer(-Code,
names_to = c("tmp", "Year"),
names_sep = "\\_",
values_to = "Count") %>%
select(-tmp)
DF_long
#> # A tibble: 12 x 3
#> Code Year Count
#> <chr> <chr> <int>
#> 1 A 2020 1
#> 2 A 2021 4
#> 3 B 2020 2
#> 4 B 2021 8
#> 5 C 2020 3
#> 6 C 2021 6
#> 7 D 2020 4
#> 8 D 2021 8
#> 9 E 2020 5
#> 10 E 2021 10
#> 11 F 2020 6
#> 12 F 2021 12
plt <- ggplot(DF_long, aes(x = Code,
y = Count,
fill = Year)) +
geom_col(position = position_dodge(width = 0.9)) +
theme_minimal()
plt
library(ggfittext)
plt +
geom_bar_text(position = "dodge", reflow = TRUE)
Created on 2021-08-05 by the reprex package (v2.0.1)

Answer 4

I also found another way of doing it:
library(tidyverse)
DF1 = data.frame(Code = c("A", "B", "C", "D", "E", "F"),
Count_2020 = c(1,2,3,4,5,6))
DF2 = data.frame(Code = c("A", "B", "C", "D", "E", "F"),
Count_2021 = c(4, 8, 6, 8, 10, 12))
DF_Merged =
inner_join(DF1, DF2)
DFF_Merged = DF_Merged %>% dplyr::select(Code, Count_2020, Count_2021) %>%
gather(key = Type, value = Value, -Code) %>%
mutate(Type = ifelse(Type == "Count_2020", "2020", "2021"))
DFF_Merged %>%
ggplot(aes(x = reorder(Code,Value), y = Value, fill = Type,
text = paste("Count:", Value,
"<br>", "Offense Code:", Code,
"<br>", "Year:", Type))) +
geom_col(position = "dodge", show.legend = FALSE) +
xlab("Offense Code") +
ylab("Count") +
ggtitle("Arrest Counts for Group 1 in Year 2020 and 2021") +
theme(axis.text=element_text(size=8))
Result