geom_bar 两个数据集一起在 R

Question

我有两个dataframes，每个都有two 列，我想在R 中使用ggplot 将together 绘制为barplot，如下所示：

如何在 R 中使用 dplyr 来做到这一点？

样本数据：

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

所以，我首先想到的是使用dplyr::inner_join 将两个dataframes 合并为一个，然后得到一个新的dataframe，如下所示：

Code Count_2021 Count_2020
 A          4          1
 B          8          2
 C          6          3
 D          8          4
 E         10          5
 F         12          6 

接下来我想使用dplyr::gather 将这两年的计数数据一起绘制为Type 和Value，但是当输出变为：

Type Value
Code A 
Code B
Code C
Code D
Code E
Code F

我尝试过的代码

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

我还找到了另一种方法：

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)) 

结果

Answer 2

使用pivot_longer() 重塑您的数据，然后使用ggplot 绘图。 奖励：要在条上添加文本，请使用 ggfittext 包中的 geom_bar_text

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)

^{由reprex package (v2.0.1) 于 2021-08-05 创建}

Answer 3

您可以使用pivot_longer 代替gather，因为它已被tidyr 1.1.3 取代

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")

在上面的代码中，pivot_longer 里面的参数是：

• cols = !Code 表示要旋转的列是除Code 之外的所有列
• names_to = "Year" 表示要为分组创建的列的名称
• names_prefix = "Count_" 用于从创建的列"Year" 中删除字符串"Count_"
• values_to = "Count" 表示为每个组的存储值创建的列的名称。

您可以通过拨打?pivot_longer了解更多有关此功能的信息

Answer 4

我们可以在加入后使用pivot_longer 重塑为'long'格式，然后在ggplot2 中使用geom_col，position 指定为'dodge'，fill 指定为'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()

-输出

数据

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))