创建一个新列，该列在R中的新列中具有唯一值的总数

发布于 2025-02-05 02:25:42 字数 1243 浏览 0 评论 0原文

我想创建一个新列，其中包含另一列唯一实例的总数。

x <- c("1", "1", "1", "1", "2", "2", "2", "3", "3", "3", "4", "4", "5", "6", "6", "6")
y <- c("Y", "Y", "Y", "Y", "N", "N", "Y", "Y", "Y", "Y", "Y", "Y", "Y", "N", "Y", "Y")
df <- data.frame(x, y)

我想要的是以下内容：

#    x     y         z
#
#    1     Y         4
#    1     Y         4
#    1     Y         4
#    1     Y         4
#    2     N         3
#    2     N         3
#    2     Y         3
#    3     Y         3
#    3     Y         3
#    3     Y         3
#    4     Y         2
#    4     Y         2
#    5     Y         1
#    6     N         3
#    6     Y         3
#    6     Y         3

我完成了以下脚本，但它被糊涂了。

library(plyr)
library(dplyr)
library(purrr)
library(tidyverse)
library(ggtext)
library(stringr)
x <- c("1", "1", "1", "1", "2", "2", "2", "3", "3", "3", "4", "4", "5", "6", "6", "6")
y <- c("Y", "Y", "Y", "Y", "N", "N", "Y", "Y", "Y", "Y", "Y", "Y", "Y", "N", "Y", "Y")
df <- data.frame(x, y) 
unique_count <- as.data.frame(table(df$x))
colnames(unique_count)[1] <- "x"
colnames(unique_count)[2] <- "z"
df <- purrr::reduce(list(df,unique_count), dplyr::left_join, by = 'x')

原文

I want to create a new column, which contains the totals count of a unique instance of another column.

x <- c("1", "1", "1", "1", "2", "2", "2", "3", "3", "3", "4", "4", "5", "6", "6", "6")
y <- c("Y", "Y", "Y", "Y", "N", "N", "Y", "Y", "Y", "Y", "Y", "Y", "Y", "N", "Y", "Y")
df <- data.frame(x, y)

What I want is the following:

#    x     y         z
#
#    1     Y         4
#    1     Y         4
#    1     Y         4
#    1     Y         4
#    2     N         3
#    2     N         3
#    2     Y         3
#    3     Y         3
#    3     Y         3
#    3     Y         3
#    4     Y         2
#    4     Y         2
#    5     Y         1
#    6     N         3
#    6     Y         3
#    6     Y         3

I have done the following script but it is convuluted.

library(plyr)
library(dplyr)
library(purrr)
library(tidyverse)
library(ggtext)
library(stringr)
x <- c("1", "1", "1", "1", "2", "2", "2", "3", "3", "3", "4", "4", "5", "6", "6", "6")
y <- c("Y", "Y", "Y", "Y", "N", "N", "Y", "Y", "Y", "Y", "Y", "Y", "Y", "N", "Y", "Y")
df <- data.frame(x, y) 
unique_count <- as.data.frame(table(df$x))
colnames(unique_count)[1] <- "x"
colnames(unique_count)[2] <- "z"
df <- purrr::reduce(list(df,unique_count), dplyr::left_join, by = 'x')

分享到QQ

分享到微博

如果你对这篇内容有疑问，欢迎到本站社区发帖提问参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。

发布评论

需要登录才能够评论，你可以免费注册一个本站的账号。

滥情稳全场 2025-02-12 02:25:42

一个可能的解决方案：

library(dplyr)

df %>% 
  add_count(x, name = "z")

#>    x y z
#> 1  1 Y 4
#> 2  1 Y 4
#> 3  1 Y 4
#> 4  1 Y 4
#> 5  2 N 3
#> 6  2 N 3
#> 7  2 Y 3
#> 8  3 Y 3
#> 9  3 Y 3
#> 10 3 Y 3
#> 11 4 Y 2
#> 12 4 Y 2
#> 13 5 Y 1
#> 14 6 N 3
#> 15 6 Y 3
#> 16 6 Y 3

A possible solution:

library(dplyr)

df %>% 
  add_count(x, name = "z")

#>    x y z
#> 1  1 Y 4
#> 2  1 Y 4
#> 3  1 Y 4
#> 4  1 Y 4
#> 5  2 N 3
#> 6  2 N 3
#> 7  2 Y 3
#> 8  3 Y 3
#> 9  3 Y 3
#> 10 3 Y 3
#> 11 4 Y 2
#> 12 4 Y 2
#> 13 5 Y 1
#> 14 6 N 3
#> 15 6 Y 3
#> 16 6 Y 3

回复收藏 0 原文

北方。的韩爷 2025-02-12 02:25:42

这与@pauls的答案完全相同，但仅与其他单词和一行相同！

library(dplyr)

df %>% 
  group_by(x) %>% 
  mutate(z = n())

   x     y         z
   <chr> <chr> <int>
 1 1     Y         4
 2 1     Y         4
 3 1     Y         4
 4 1     Y         4
 5 2     N         3
 6 2     N         3
 7 2     Y         3
 8 3     Y         3
 9 3     Y         3
10 3     Y         3
11 4     Y         2
12 4     Y         2
13 5     Y         1
14 6     N         3
15 6     Y         3
16 6     Y         3

This is exactly the same as @Pauls answer, but just with other words and one line more!

library(dplyr)

df %>% 
  group_by(x) %>% 
  mutate(z = n())

   x     y         z
   <chr> <chr> <int>
 1 1     Y         4
 2 1     Y         4
 3 1     Y         4
 4 1     Y         4
 5 2     N         3
 6 2     N         3
 7 2     Y         3
 8 3     Y         3
 9 3     Y         3
10 3     Y         3
11 4     Y         2
12 4     Y         2
13 5     Y         1
14 6     N         3
15 6     Y         3
16 6     Y         3

回复收藏 0 原文

烂柯人 2025-02-12 02:25:42

这可以通过以下文章来回答： dplyr：将计数放入新的可变<< /a>

您需要按变量x和y对数据进行分组，并计算这些组合的发生。使用Dplyr A解决方案将是：

library(dplyr)

x <- c("1", "1", "1", "1", "2", "2", "2", "3", "3", "3", "4", "4", "5", "6", "6", "6")
y <- c("Y", "Y", "Y", "Y", "N", "N", "Y", "Y", "Y", "Y", "Y", "Y", "Y", "N", "Y", "Y")
df <- data.frame(x, y)

df %>% group_by(x,y) %>% mutate(z = n())

输出：

# A tibble: 16 × 3
# Groups:   x, y [8]
   x     y     z
   <chr> <chr> <int>
 1 1     Y         4
 2 1     Y         4
 3 1     Y         4
 4 1     Y         4
 5 2     N         2
 6 2     N         2
 7 2     Y         1
 8 3     Y         3
 9 3     Y         3
10 3     Y         3
11 4     Y         2
12 4     Y         2
13 5     Y         1
14 6     N         1
15 6     Y         2
16 6     Y         2

This can be answered by the following post: dplyr: put count occurrences into new variable

You need to group your data by variable x and y and count the occurences of these combinations. With dplyr a solution would then be:

library(dplyr)

x <- c("1", "1", "1", "1", "2", "2", "2", "3", "3", "3", "4", "4", "5", "6", "6", "6")
y <- c("Y", "Y", "Y", "Y", "N", "N", "Y", "Y", "Y", "Y", "Y", "Y", "Y", "N", "Y", "Y")
df <- data.frame(x, y)

df %>% group_by(x,y) %>% mutate(z = n())

Output:

# A tibble: 16 × 3
# Groups:   x, y [8]
   x     y     z
   <chr> <chr> <int>
 1 1     Y         4
 2 1     Y         4
 3 1     Y         4
 4 1     Y         4
 5 2     N         2
 6 2     N         2
 7 2     Y         1
 8 3     Y         3
 9 3     Y         3
10 3     Y         3
11 4     Y         2
12 4     Y         2
13 5     Y         1
14 6     N         1
15 6     Y         2
16 6     Y         2

回复收藏 0 原文

~没有更多了~