翻看简书的时候偶尔发现一篇关于tidyverse管道操作的技术贴：节省tidyverse中的管道 %>% ，还挺实用，实际演练学习下。
示例数据
library(tidyverse)
data("penguins",package = "palmerpenguins")
penguins <- na.omit(penguins)
1. rename()
1.1 select()里用rename()
penguins %>%
select(penguins_species = species, #直接进行重命名
island)
## # A tibble: 333 x 2
## penguins_species island
## <fct> <fct>
## 1 Adelie Torgersen
## 2 Adelie Torgersen
## 3 Adelie Torgersen
## 4 Adelie Torgersen
## 5 Adelie Torgersen
## 6 Adelie Torgersen
## 7 Adelie Torgersen
## 8 Adelie Torgersen
## 9 Adelie Torgersen
## 10 Adelie Torgersen
## # ... with 323 more rows
1.2 count()里面用rename()
penguins %>%
count(species, name = "total") #计数后直接赋值
## # A tibble: 3 x 2
## species total
## <fct> <int>
## 1 Adelie 146
## 2 Chinstrap 68
## 3 Gentoo 119
赋值后再计数
penguins %>%
count(penguins_species = species, name = "total")
## # A tibble: 3 x 2
## penguins_species total
## <fct> <int>
## 1 Adelie 146
## 2 Chinstrap 68
## 3 Gentoo 119
注意： 此处传递给name参数的新名称必须用引号引起来，但选定列的新名称不必用引号引起来。
2. count()内部mutate()
penguins %>%
count(long_beak=bill_length_mm > 50)
## # A tibble: 2 x 2
## long_beak n
## <lgl> <int>
## 1 FALSE 281
## 2 TRUE 52
也可以指定多个变量
penguins %>%
count(long_beak = bill_length_mm > 50,
is_adelie = species == "Adelie")
## # A tibble: 3 x 3
## long_beak is_adelie n
## <lgl> <lgl> <int>
## 1 FALSE FALSE 135
## 2 FALSE TRUE 146
## 3 TRUE FALSE 52
3.transmute()+select()
实际上，transmute()就像select()继承未修改的列一样，当然可以在执行操作时对其“重命名”
penguins %>%
transmute(penguins_species = species,
island,
body_mass_kg = body_mass_g/1000)
## # A tibble: 333 x 3
## penguins_species island body_mass_kg
## <fct> <fct> <dbl>
## 1 Adelie Torgersen 3.75
## 2 Adelie Torgersen 3.8
## 3 Adelie Torgersen 3.25
## 4 Adelie Torgersen 3.45
## 5 Adelie Torgersen 3.65
## 6 Adelie Torgersen 3.62
## 7 Adelie Torgersen 4.68
## 8 Adelie Torgersen 3.2
## 9 Adelie Torgersen 3.8
## 10 Adelie Torgersen 4.4
## # ... with 323 more rows
4. summarize()+ungroup()
summarize(.groups="drop"):删除分组变量
penguins %>%
group_by(island, species) %>%
summarize(mean_mass = mean(body_mass_g, na.rm = T),.groups = "drop")
## # A tibble: 5 x 3
## island species mean_mass
## <fct> <fct> <dbl>
## 1 Biscoe Adelie 3710.
## 2 Biscoe Gentoo 5092.
## 3 Dream Adelie 3701.
## 4 Dream Chinstrap 3733.
## 5 Torgersen Adelie 3709.
5. arrange()+其他功能slice()
penguins %>%
top_n(5, wt=body_mass_g) #按列排序前5行
## # A tibble: 6 x 8
## species island bill_length_mm bill_depth_mm flipper_length_~ body_mass_g sex
## <fct> <fct> <dbl> <dbl> <int> <int> <fct>
## 1 Gentoo Biscoe 49.2 15.2 221 6300 male
## 2 Gentoo Biscoe 59.6 17 230 6050 male
## 3 Gentoo Biscoe 51.1 16.3 220 6000 male
## 4 Gentoo Biscoe 45.2 16.4 223 5950 male
## 5 Gentoo Biscoe 49.8 15.9 229 5950 male
## 6 Gentoo Biscoe 48.8 16.2 222 6000 male
## # ... with 1 more variable: year <int>
penguins %>%
slice_max(order_by = body_mass_g,n=5) # slice_*的新功能
## # A tibble: 6 x 8
## species island bill_length_mm bill_depth_mm flipper_length_~ body_mass_g sex
## <fct> <fct> <dbl> <dbl> <int> <int> <fct>
## 1 Gentoo Biscoe 49.2 15.2 221 6300 male
## 2 Gentoo Biscoe 59.6 17 230 6050 male
## 3 Gentoo Biscoe 51.1 16.3 220 6000 male
## 4 Gentoo Biscoe 48.8 16.2 222 6000 male
## 5 Gentoo Biscoe 45.2 16.4 223 5950 male
## 6 Gentoo Biscoe 49.8 15.9 229 5950 male
## # ... with 1 more variable: year <int>
新slice_*()功能最大的变化是为分组数据添加了适当的行为，例如：
penguins %>%
group_by(species) %>%
slice_max(body_mass_g,prop=.05) #返回每个物种重量百分比最高的5%的企鹅
## # A tibble: 16 x 8
## # Groups: species [3]
## species island bill_length_mm bill_depth_mm flipper_length_~ body_mass_g
## <fct> <fct> <dbl> <dbl> <int> <int>
## 1 Adelie Biscoe 43.2 19 197 4775
## 2 Adelie Biscoe 41 20 203 4725
## 3 Adelie Torge~ 42.9 17.6 196 4700
## 4 Adelie Torge~ 39.2 19.6 195 4675
## 5 Adelie Dream 39.8 19.1 184 4650
## 6 Adelie Dream 39.6 18.8 190 4600
## 7 Adelie Biscoe 45.6 20.3 191 4600
## 8 Chinst~ Dream 52 20.7 210 4800
## 9 Chinst~ Dream 52.8 20 205 4550
## 10 Chinst~ Dream 53.5 19.9 205 4500
## 11 Gentoo Biscoe 49.2 15.2 221 6300
## 12 Gentoo Biscoe 59.6 17 230 6050
## 13 Gentoo Biscoe 51.1 16.3 220 6000
## 14 Gentoo Biscoe 48.8 16.2 222 6000
## 15 Gentoo Biscoe 45.2 16.4 223 5950
## 16 Gentoo Biscoe 49.8 15.9 229 5950
## # ... with 2 more variables: sex <fct>, year <int>
6. add_count()
按组计数和求和，add_count()添加一列，其中包含每组（或组的组合）的计数
penguins %>%
add_count(species, name = "count_by_species") %>%
select(-contains("mm"))
## # A tibble: 333 x 6
## species island body_mass_g sex year count_by_species
## <fct> <fct> <int> <fct> <int> <int>
## 1 Adelie Torgersen 3750 male 2007 146
## 2 Adelie Torgersen 3800 female 2007 146
## 3 Adelie Torgersen 3250 female 2007 146
## 4 Adelie Torgersen 3450 female 2007 146
## 5 Adelie Torgersen 3650 male 2007 146
## 6 Adelie Torgersen 3625 female 2007 146
## 7 Adelie Torgersen 4675 male 2007 146
## 8 Adelie Torgersen 3200 female 2007 146
## 9 Adelie Torgersen 3800 male 2007 146
## 10 Adelie Torgersen 4400 male 2007 146
## # ... with 323 more rows
也可以使用wt来按组有效的获取总和：
penguins %>%
add_count(species,wt=body_mass_g,
name = "total_weighted_by_species") %>%
select(-contains("mm"))
## # A tibble: 333 x 6
## species island body_mass_g sex year total_weighted_by_species
## <fct> <fct> <int> <fct> <int> <int>
## 1 Adelie Torgersen 3750 male 2007 541100
## 2 Adelie Torgersen 3800 female 2007 541100
## 3 Adelie Torgersen 3250 female 2007 541100
## 4 Adelie Torgersen 3450 female 2007 541100
## 5 Adelie Torgersen 3650 male 2007 541100
## 6 Adelie Torgersen 3625 female 2007 541100
## 7 Adelie Torgersen 4675 male 2007 541100
## 8 Adelie Torgersen 3200 female 2007 541100
## 9 Adelie Torgersen 3800 male 2007 541100
## 10 Adelie Torgersen 4400 male 2007 541100
## # ... with 323 more rows
默认情况下，add_tally()添加行数，此时可以使用mutate (n = n())进行处理
penguins %>%
add_count(species, wt=body_mass_g,
name = "total_weight_by_speices") %>%
add_tally(wt=body_mass_g,
name = "total_weight_of_all_species") %>%
select(1:2,last_col(0):last_col(1))
## # A tibble: 333 x 4
## species island total_weight_of_all_species total_weight_by_speices
## <fct> <fct> <int> <int>
## 1 Adelie Torgersen 1400950 541100
## 2 Adelie Torgersen 1400950 541100
## 3 Adelie Torgersen 1400950 541100
## 4 Adelie Torgersen 1400950 541100
## 5 Adelie Torgersen 1400950 541100
## 6 Adelie Torgersen 1400950 541100
## 7 Adelie Torgersen 1400950 541100
## 8 Adelie Torgersen 1400950 541100
## 9 Adelie Torgersen 1400950 541100
## 10 Adelie Torgersen 1400950 541100
## # ... with 323 more rows
参考链接：
网友评论