Tidyverse学习笔记

Tidyverse

作者

Qingyao Zhang

发布于

2025年11月10日

library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
library(tibble)
# 使用Keng中的depress数据进行演示
data("depress", package = "Keng")

1 %>% versus |>

对于R语言4.1之前的版本，tidyverse依赖magrittr中的管道操作符%>%。对于R语言4.1及以后的版本，R base中包含自己的管道运算符|>。然而，%>%与|>的功能不同。

1.1 |>的用法

R base中的|>的功能比较简单，运行?'|>'查看|>的文档。|>的用法有以下几种：

  1. 常规用法，将|>左侧对象传递给右侧函数的第一个参数。
# simple uses:
# same as pull(depress, gender)
depress |> 
  pull(gender) 
##  [1] 0 1 1 0 1 0 1 0 1 1 0 0 1 0 1 1 1 0 1 0 1 0 0 1 1 1 1 0 1 1 0 1 0 0 1 0 1 0
## [39] 1 0 0 1 0 1 0 1 1 1 1 1 1 0 0 0 1 1 1 0 1 1 1 1 0 1 1 0 0 0 0 1 0 1 1 1 1 0
## [77] 1 0 1 0 0 1 0 1 0 1 0 1 0 0 1 1 1 0
# same as nrow(subset(depress, gender == 0))
depress |> 
  subset(gender == 0) |> 
  nrow()  
## [1] 41
  1. 将|>左侧对象传递给右侧函数的其他参数。
  1. 使用_ 占位符指代|>左侧对象
注记_占位符的使用规则
  1. _默认内隐地传递给|>右侧函数的第一个参数；当_以外显的方式传递时，_的默认传递将被取消
  2. 只能使用参数名传递_
  3. 只能使用一个_
  4. 不能在嵌套函数中使用_
# valid use
depress |> 
  subset(class == 3) |> 
  t.test(anx ~ gender, data = _)
## 
##  Welch Two Sample t-test
## 
## data:  anx by gender
## t = 1.3118, df = 19.977, p-value = 0.2045
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
##  -0.2922643  1.2824604
## sample estimates:
## mean in group 0 mean in group 1 
##        2.083333        1.588235

下面的用法不可行：

depress |> 
  summary(select(.data = _, gender))
  1. 使用匿名函数
depress |> 
  subset(class == 3) |> 
  (function(d) t.test(dm1 ~ gender, data = d))()
## 
##  Welch Two Sample t-test
## 
## data:  dm1 by gender
## t = -0.89829, df = 26.676, p-value = 0.3771
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
##  -0.4163176  0.1628862
## sample estimates:
## mean in group 0 mean in group 1 
##        1.729167        1.855882
depress |> 
  subset(class == 9) |> 
  (\(d) t.test(dm1 ~ gender, data = d))()
## 
##  Welch Two Sample t-test
## 
## data:  dm1 by gender
## t = 0.89103, df = 12.351, p-value = 0.3899
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
##  -0.2704022  0.6465927
## sample estimates:
## mean in group 0 mean in group 1 
##        2.171429        1.983333
  1. |>右侧函数使用参数名传递参数值，从而跳过目标参数之前的参数
depress |> 
  subset(class == 3) |> 
  t.test(formula = dm1 ~ gender)
## 
##  One Sample t-test
## 
## data:  subset(depress, class == 3)
## t = 5.5043, df = 6785, p-value = 3.841e-08
## alternative hypothesis: true mean is not equal to 0
## 95 percent confidence interval:
##   84.56869 178.12434
## sample estimates:
## mean of x 
##  131.3465
  1. |>结合使用_占位符提取数据子集
depress |> 
  _$gender
##  [1] 0 1 1 0 1 0 1 0 1 1 0 0 1 0 1 1 1 0 1 0 1 0 0 1 1 1 1 0 1 1 0 1 0 0 1 0 1 0
## [39] 1 0 0 1 0 1 0 1 1 1 1 1 1 0 0 0 1 1 1 0 1 1 1 1 0 1 1 0 0 0 0 1 0 1 1 1 1 0
## [77] 1 0 1 0 0 1 0 1 0 1 0 1 0 0 1 1 1 0
depress |> 
  _[["gender"]]
##  [1] 0 1 1 0 1 0 1 0 1 1 0 0 1 0 1 1 1 0 1 0 1 0 0 1 1 1 1 0 1 1 0 1 0 0 1 0 1 0
## [39] 1 0 0 1 0 1 0 1 1 1 1 1 1 0 0 0 1 1 1 0 1 1 1 1 0 1 1 0 0 0 0 1 0 1 1 1 1 0
## [77] 1 0 1 0 0 1 0 1 0 1 0 1 0 0 1 1 1 0
  1. 使用|>转换代码
quote(depress |> subset(class == 3) |> nrow())
## nrow(subset(depress, class == 3))

1.2 %>%的用法

  1. 常规用法，将⁠%>%左侧对象传递给右侧函数的第一个参数。
# 同pull(depress, gender)
depress %>% 
  pull(gender) 
##  [1] 0 1 1 0 1 0 1 0 1 1 0 0 1 0 1 1 1 0 1 0 1 0 0 1 1 1 1 0 1 1 0 1 0 0 1 0 1 0
## [39] 1 0 0 1 0 1 0 1 1 1 1 1 1 0 0 0 1 1 1 0 1 1 1 1 0 1 1 0 0 0 0 1 0 1 1 1 1 0
## [77] 1 0 1 0 0 1 0 1 0 1 0 1 0 0 1 1 1 0
# 同nrow(subset(depress, gender == 0))
depress %>% 
  subset(gender == 0) %>% 
  nrow()  
## [1] 41
  1. 将%>%左侧对象传递给右侧函数的其他参数。
  1. 使用. 占位符指代%>%左侧对象
注记.占位符的使用规则
  1. .总是默认以内隐的方式传递给%>%右侧函数的第一个参数，这一行为可以用{}取消
  2. 可以使用位置传递.
  3. %>%右侧函数可以使用多个.
  4. 可以在嵌套函数中使用.
# 有效用法
depress %>%
  mutate(.,
         depr1_mean = rowMeans(select(., starts_with("depr1")))) %>%
  pull(depr1_mean)
##  [1] 1.55 1.55 1.90 1.35 1.30 1.95 1.60 1.45 2.70 1.75 2.10 1.90 1.75 1.85 1.65
## [16] 1.90 1.50 1.55 1.80 1.70 1.85 1.35 2.45 2.10 2.15 2.95 1.50 1.55 1.60 1.75
## [31] 1.50 1.80 1.80 1.50 1.95 2.45 1.50 1.85 1.45 2.30 2.70 1.45 2.25 2.15 2.10
## [46] 2.00 2.20 2.05 1.60 1.75 2.00 2.20 1.35 2.40 1.95 1.20 2.20 2.35 1.95 2.15
## [61] 1.60 2.05 1.55 1.65 2.85 2.95 2.40 1.85 2.05 2.00 2.05 2.50 1.65 2.00 1.15
## [76] 1.95 1.90 1.65 1.90 1.80 2.20 2.30 2.45 2.25 2.00 2.15 1.45 2.35 1.80 1.75
## [91] 1.85 1.95 1.70 1.45
# `.`总会传递给%>%右侧函数第一个参数
depress %>%
  slice_head(n = 5) %>%
  pull(dm1) %>%
  c(length(.))
## [1] 1.55 1.55 1.90 1.35 1.30 5.00
# 在`{}`内，`.`不会传递给第一个参数
depress %>%
  slice_head(n = 5) %>%
  pull(dm1) %>%
  {c(length(.))}
## [1] 5
  1. 使用匿名函数
depress %>%
  subset(class == 3) %>% 
  (function(d) t.test(dm1 ~ gender, data = d))
## 
##  Welch Two Sample t-test
## 
## data:  dm1 by gender
## t = -0.89829, df = 26.676, p-value = 0.3771
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
##  -0.4163176  0.1628862
## sample estimates:
## mean in group 0 mean in group 1 
##        1.729167        1.855882
depress %>%
  subset(class == 5) %>% 
  t.test(dm1 ~ gender, data = .)
## 
##  Welch Two Sample t-test
## 
## data:  dm1 by gender
## t = 1.4493, df = 17.276, p-value = 0.1652
## alternative hypothesis: true difference in means between group 0 and group 1 is not equal to 0
## 95 percent confidence interval:
##  -0.09295787  0.50248168
## sample estimates:
## mean in group 0 mean in group 1 
##        2.033333        1.828571
# 当`%>%`右侧有多个语句时，使用`{}`将这些语句括起来，
# 在`{}`中`.`不会传递给第一个参数
depress %>%
  subset(class == 9) %>% 
  {
    ncol(.)
    nrow(.)
  }
## [1] 19
  1. %>%结合使用.占位符提取数据子集
depress %>% 
  .$gender
##  [1] 0 1 1 0 1 0 1 0 1 1 0 0 1 0 1 1 1 0 1 0 1 0 0 1 1 1 1 0 1 1 0 1 0 0 1 0 1 0
## [39] 1 0 0 1 0 1 0 1 1 1 1 1 1 0 0 0 1 1 1 0 1 1 1 1 0 1 1 0 0 0 0 1 0 1 1 1 1 0
## [77] 1 0 1 0 0 1 0 1 0 1 0 1 0 0 1 1 1 0
depress %>% 
  .[["gender"]]
##  [1] 0 1 1 0 1 0 1 0 1 1 0 0 1 0 1 1 1 0 1 0 1 0 0 1 1 1 1 0 1 1 0 1 0 0 1 0 1 0
## [39] 1 0 0 1 0 1 0 1 1 1 1 1 1 0 0 0 1 1 1 0 1 1 1 1 0 1 1 0 0 0 0 1 0 1 1 1 1 0
## [77] 1 0 1 0 0 1 0 1 0 1 0 1 0 0 1 1 1 0
  1. 使用%>%与.创建函数
quote(depress %>% subset(class == 3) %>% nrow())
## depress %>% subset(class == 3) %>% nrow()
# 当`.`出现在`%>%`左侧，它们将创建一个函数
subset_nrow <- . %>% subset(class == 3) %>% nrow()
subset_nrow(depress)
## [1] 29

2 c_across()

dplyr文档中介绍到，与c()相比，（1）c_across()使用tidy select，更加便捷； （2）c_across()使用vctrs::vec_c()，给出的输出更加安全。

tidy select只有15种（见help("select")）：:，!，&，c()，everything()，last_col()，group_cols()，starts_with()，ends_with()，contains()，matches()，num_range()，all_of()，any_of()，where()。

下面的例子在data.frame中对c()与c_across()进行了比较，代码中注释了结果正确与否。

set.seed(20250927)
toy_dat <- data.frame(x1 = rnorm(10), x2 = rnorm(10), x3 = rnorm(10))
head(toy_dat)
##           x1         x2         x3
## 1 -2.7734224 -0.6661558  1.0882648
## 2 -1.1618233 -0.9076756  0.1483481
## 3 -0.3773254  0.1182323  1.0507643
## 4  0.2743375 -0.1521034  0.7412800
## 5  0.6070295  0.7295347 -0.5049492
## 6 -0.3429219 -0.1650072  2.3721901
toy_dat |>
  rowwise() |> 
  mutate(
    # correct
    y1 = mean(c(x1, x2, x3)),
    # incorrect
    y2 = mean(x1:x3),
    # incorrect
    y3 = mean(c(x1:x3)),
    # correct
    y4 = mean(c_across(x1:x3))
  ) |> 
  head()
## # A tibble: 6 × 7
## # Rowwise: 
##       x1     x2     x3     y1     y2     y3     y4
##    <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>
## 1 -2.77  -0.666  1.09  -0.784 -1.27  -1.27  -0.784
## 2 -1.16  -0.908  0.148 -0.640 -0.662 -0.662 -0.640
## 3 -0.377  0.118  1.05   0.264  0.123  0.123  0.264
## 4  0.274 -0.152  0.741  0.288  0.274  0.274  0.288
## 5  0.607  0.730 -0.505  0.277  0.107  0.107  0.277
## 6 -0.343 -0.165  2.37   0.621  0.657  0.657  0.621

下面的例子在tibble中对c()与c_across()进行了比较，代码中注释了结果正确与否。

toy_dat <- as_tibble(toy_dat)
head(toy_dat)
## # A tibble: 6 × 3
##       x1     x2     x3
##    <dbl>  <dbl>  <dbl>
## 1 -2.77  -0.666  1.09 
## 2 -1.16  -0.908  0.148
## 3 -0.377  0.118  1.05 
## 4  0.274 -0.152  0.741
## 5  0.607  0.730 -0.505
## 6 -0.343 -0.165  2.37
toy_dat |>
  rowwise() |> 
  mutate(
    # correct
    y1 = mean(c(x1, x2, x3)),
    # incorrect
    y2 = mean(x1:x3),
    # incorrect
    y3 = mean(c(x1:x3)),
    # correct
    y4 = mean(c_across(x1:x3))
  ) |> 
  head()
## # A tibble: 6 × 7
## # Rowwise: 
##       x1     x2     x3     y1     y2     y3     y4
##    <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>  <dbl>
## 1 -2.77  -0.666  1.09  -0.784 -1.27  -1.27  -0.784
## 2 -1.16  -0.908  0.148 -0.640 -0.662 -0.662 -0.640
## 3 -0.377  0.118  1.05   0.264  0.123  0.123  0.264
## 4  0.274 -0.152  0.741  0.288  0.274  0.274  0.288
## 5  0.607  0.730 -0.505  0.277  0.107  0.107  0.277
## 6 -0.343 -0.165  2.37   0.621  0.657  0.657  0.621

可见，在使用rowwise()时，必须将tidy select语法与c_across()结合使用，才能得出正确的计算结果。