如何根据列名称中的模式计算 data.frame 中的平均值？

Question

我有一个包含 21 列的 data.frame，每三列代表一个特定的时间点。我想计算这些一式三份中每一个的平均值。

   geneName  t11  t12  t13  t21  t22  t23  t31  t32  t33  t41  t42  t43  t51 t52  t53  t61  t62  t63
gene1 gene1 3296 5133 3466 2166 1759 2099 1916 1379 1570 2533 1794 1016  800  79  648   99   60  152
gene2 gene2 4210 5505 4173 2736 2748 3052 2409 1944 2237 1158 3475 1488 4023 102  940  265  365  124
...

在上面的示例中，我想计算三个

t1

、

t2

、

t3

等的平均值

Answer 1

这是一个基本的 R 方法 -

# Column numbers to be ignored from the calculation
columns_not_included <- 1
# Keep only subset of dataset that we need
tmp <- df[-columns_not_included]

cbind.data.frame(df[columns_not_included], 
              sapply(split.default(tmp, 
               sub('\\d$', '', names(tmp))), rowMeans, na.rm =TRUE))

#  geneName       t1       t2       t3       t4       t5       t6
#1    gene1 3965.000 2008.000 1621.667 1781.000  509.000 103.6667
#2    gene2 4629.333 2845.333 2196.667 2040.333 1688.333 251.3333

sub('\\d$', '', names(tmp))

将删除列名称的最后一个数字，以便

t11

、

t12

和

t13

都将仅返回

t1

，对于传递给

split.default

的其他组也是如此，将数据拆分为基于这些组的数据框列表。对于每个组，我们使用

rowMeans

计算行均值。

Answer 2

tidyverse

解决方案：

library(tidyverse)

df %>%
  pivot_longer(-geneName, names_to = ".value", names_pattern = "(t.)") %>%
  summarise(across(everything(), mean), .by = geneName)

# # A tibble: 2 × 7
#   geneName    t1    t2    t3    t4    t5    t6
#   <chr>    <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
# 1 gene1    3965  2008  1622. 1781   509   104.
# 2 gene2    4629. 2845. 2197. 2040. 1688.  251.

Answer 3

另一种基本 R 方法：

g1 <- t(substr(names(df[-1]), 1, 2))[rep(1, nrow(df)),]
cbind(df[1], tapply(unlist(df[-1]), list(row(g1), g1), mean))

  geneName       t1       t2       t3       t4       t5       t6
1    gene1 3965.000 2008.000 1621.667 1781.000  509.000 103.6667
2    gene2 4629.333 2845.333 2196.667 2040.333 1688.333 251.3333

Answer 4

df<- read.table(text =
"geneName  t11  t12  t13  t21  t22  t23  t31  t32  t33  t41  t42  t43  t51 t52  t53  t61  t62  t63
gene1 3296 5133 3466 2166 1759 2099 1916 1379 1570 2533 1794 1016  800  79  648   99   60  152
gene2 4210 5505 4173 2736 2748 3052 2409 1944 2237 1158 3475 1488 4023 102  940  265  365  124", header = TRUE)

library(tidyverse)

df %>% 
  pivot_longer(cols = -geneName) %>% 
  mutate(name = substr(name, 1, 2)) %>%
  group_by(geneName, name) %>%
  summarise(mean = mean(value))

# A tibble: 12 × 3
# Groups:   geneName [2]
   geneName name   mean
   <chr>    <chr> <dbl>
 1 gene1    t1    3965 
 2 gene1    t2    2008 
 3 gene1    t3    1622.
 4 gene1    t4    1781 
 5 gene1    t5     509 
 6 gene1    t6     104.
 7 gene2    t1    4629.
 8 gene2    t2    2845.
 9 gene2    t3    2197.
10 gene2    t4    2040.
11 gene2    t5    1688.
12 gene2    t6     251.

Answer 5

这是另一种选择：

library(tidyverse)

test_data |>
  pivot_longer(-geneName, 
               names_to = "time", 
               names_pattern = "t(\\d+)", 
               names_transform = as.numeric) |>
  arrange(geneName, time) |>
  mutate(group = cumsum(time - lag(time, default = first(time)-1)!=1)) |>
  nest(data = -c(geneName, group)) |>
  transmute(geneName = geneName,
            time_range = map_chr(data, ~glue::glue("t{mn}-t{mx}", 
                                                mn = min(.x$time),
                                                mx = max(.x$time))),
            mean = map_dbl(data, ~mean(.x$value))) |>
  pivot_wider(names_from = time_range, values_from = mean)
#> # A tibble: 2 x 7
#>   geneName `t11-t13` `t21-t23` `t31-t33` `t41-t43` `t51-t53` `t61-t63`
#>   <chr>        <dbl>     <dbl>     <dbl>     <dbl>     <dbl>     <dbl>
#> 1 gene1        3965      2008      1622.     1781       509       104.
#> 2 gene2        4629.     2845.     2197.     2040.     1688.      251.

Answer 6

尽管我喜欢 Ronak 的巧妙答案，但我仍然更喜欢使用 tidyverse grammer 进行计算。我发现它更干净、更清晰。

但是谢谢你的帮助

test.mean <- test_data |>
group_by(gene)
dplyr::rowwise() |> 
mutate("meant1" = mean(c(t11,t12,t13))) |>
mutate("meant2" = mean(c(t21,t22,t23))) |>
mutate("meant3" = mean(c(t31,t32,t33))) |>
mutate("meant4" = mean(c(t41,t42,t43))) |>
mutate("meant5" = mean(c(t51,t52,t53))) |>
mutate("meant6" = mean(c(t61,t62,t63))) |>
select(matches("geneName|mean")) |> 
column_to_rownames("geneName") |>
as.data.frame()