问题
My question is very similar to Applying group_by and summarise on data while keeping all the columns' info but I would like to keep columns which get excluded because they conflict after grouping.
Label <- c("203c","203c","204a","204a","204a","204a","204a","204a","204a","204a")
Type <- c("wholefish","flesh","flesh","fleshdelip","formula","formuladelip",
"formula","formuladelip","wholefish", "wholefishdelip")
Proportion <- c(1,1,0.67714,0.67714,0.32285,0.32285,0.32285,
0.32285, 0.67714,0.67714)
N <- (1:10)
C <- (1:10)
Code <- c("c","a","a","b","a","b","c","d","c","d")
df <- data.frame(Label,Type, Proportion, N, C, Code)
df
Label Type Proportion N C Code
1 203c wholefish 1.0000 1 1 c
2 203c flesh 1.0000 2 2 a
3 204a flesh 0.6771 3 3 a
4 204a fleshdelip 0.6771 4 4 b
5 204a formula 0.3228 5 5 a
6 204a formuladelip 0.3228 6 6 b
7 204a formula 0.3228 7 7 c
8 204a formuladelip 0.3228 8 8 d
9 204a wholefish 0.6771 9 9 c
10 204a wholefishdelip 0.6771 10 10 d
total <- df %>%
#where the Label and Code are the same the Proportion, N and C
#should be added together respectively
group_by(Label, Code) %>%
#total proportion should add up to 1
#my way of checking that the correct task has been completed
summarise_if(is.numeric, sum)
# A tibble: 6 x 5
# Groups: Label [?]
Label Code Proportion N C
<fctr> <fctr> <dbl> <int> <int>
1 203c a 1.00000 2 2
2 203c c 1.00000 1 1
3 204a a 0.99999 8 8
4 204a b 0.99999 10 10
5 204a c 0.99999 16 16
6 204a d 0.99999 18 18
Up until here I get what I want. Now I would like to include the column Type though it is excluded because values are conflicting. this is the result I would like to obtain
# A tibble: 6 x 5
# Groups: Label [?]
Label Code Proportion N C Type
<fctr> <fctr> <dbl> <int> <int> <fctr>
1 203c a 1.00000 2 2 wholefish
2 203c c 1.00000 1 1 flesh
3 204a a 0.99999 8 8 flesh_formula
4 204a b 0.99999 10 10 fleshdelip_formuladelip
5 204a c 0.99999 16 16 wholefish_formula
6 204a d 0.99999 18 18 wholefishdelip_formuladelip
I have tried ungroup() and some variations of mutate and unite but to no avail, any suggestions would be greatly appreciated
回答1:
Here's the data.table solution, I'm assuming you want the mean() of Proportion, since these grouped proportions are likely not additive.
setDT(df)
df[, .(Type =paste(Type,collapse="_"),
Proportion=mean(Proportion),N= sum(N),C=sum(C)), by=.(Label,Code)]
[order(Label)]
Label Code Type Proportion N C
1: 203c c wholefish 1.000000 1 1
2: 203c a flesh 1.000000 2 2
3: 204a a flesh_formula 0.499995 8 8
4: 204a b fleshdelip_formuladelip 0.499995 10 10
5: 204a c formula_wholefish 0.499995 16 16
6: 204a d formuladelip_wholefishdelip 0.499995 18 18
I'm not sure this is the cleanest dplyr solution, but it works:
df %>% group_by(Label, Code) %>%
mutate(Type = paste(Type,collapse="_")) %>%
group_by(Label,Type,Code) %>%
summarise(N=sum(N),C=sum(C),Proportion=mean(Proportion))
Note the key here is to re-group once you create the combined Type column.
Label Type Code N C Proportion
<fctr> <chr> <fctr> <int> <int> <dbl>
1 203c flesh a 2 2 1.000000
2 203c wholefish c 1 1 1.000000
3 204a flesh_formula a 8 8 0.499995
4 204a fleshdelip_formuladelip b 10 10 0.499995
5 204a formula_wholefish c 16 16 0.499995
6 204a formuladelip_wholefishdelip d 18 18 0.499995
回答2:
Here are two other options:
1) Nest columns into one column and then customize the summary by checking the data types:
df %>%
group_by(Label, Code) %>% nest() %>%
mutate(data = map(data,
~ as.tibble(map(.x, ~ if(is.numeric(.x)) sum(.x) else paste(.x, collapse="_")))
)
) %>% unnest()
# A tibble: 6 x 6
# Label Code Type Proportion N C
# <fctr> <fctr> <chr> <dbl> <int> <int>
#1 203c c wholefish 1.00000 1 1
#2 203c a flesh 1.00000 2 2
#3 204a a flesh_formula 0.99999 8 8
#4 204a b fleshdelip_formuladelip 0.99999 10 10
#5 204a c formula_wholefish 0.99999 16 16
#6 204a d formuladelip_wholefishdelip 0.99999 18 18
2) summarize separately and then join the result:
numeric <- df %>%
group_by(Label, Code) %>%
summarise_if(is.numeric, sum)
character <- df %>%
group_by(Label, Code) %>%
summarise_if(~ is.character(.) || is.factor(.), ~ paste(., collapse="_"))
inner_join(numeric, character, by = c("Label", "Code"))
# A tibble: 6 x 6
# Groups: Label [?]
# Label Code Proportion N C Type
# <fctr> <fctr> <dbl> <int> <int> <chr>
#1 203c a 1.00000 2 2 flesh
#2 203c c 1.00000 1 1 wholefish
#3 204a a 0.99999 8 8 flesh_formula
#4 204a b 0.99999 10 10 fleshdelip_formuladelip
#5 204a c 0.99999 16 16 formula_wholefish
#6 204a d 0.99999 18 18 formuladelip_wholefishdelip
回答3:
Here's a tidyverse solution that keeps your group_by statement the same. The key is to use mutate_if for each variable type first (i.e., numeric, character), then get distinct rows.
library(tidyverse)
#> Loading tidyverse: ggplot2
#> Loading tidyverse: tibble
#> Loading tidyverse: tidyr
#> Loading tidyverse: readr
#> Loading tidyverse: purrr
#> Loading tidyverse: dplyr
#> Conflicts with tidy packages ----------------------------------------------
#> filter(): dplyr, stats
#> lag(): dplyr, stats
Label <- c("203c", "203c", "204a", "204a", "204a", "204a", "204a", "204a",
"204a", "204a")
Type <- c("wholefish", "flesh", "flesh", "fleshdelip", "formula", "formuladelip",
"formula", "formuladelip", "wholefish", "wholefishdelip")
Proportion <- c(1, 1, 0.67714, 0.67714, 0.32285, 0.32285, 0.32285, 0.32285,
0.67714, 0.67714)
N <- (1:10)
C <- (1:10)
Code <- c("c", "a", "a", "b", "a", "b", "c", "d", "c", "d")
df <- data_frame(Label, Type, Proportion, N, C, Code)
df
#> # A tibble: 10 x 6
#> Label Type Proportion N C Code
#> <chr> <chr> <dbl> <int> <int> <chr>
#> 1 203c wholefish 1.00000 1 1 c
#> 2 203c flesh 1.00000 2 2 a
#> 3 204a flesh 0.67714 3 3 a
#> 4 204a fleshdelip 0.67714 4 4 b
#> 5 204a formula 0.32285 5 5 a
#> 6 204a formuladelip 0.32285 6 6 b
#> 7 204a formula 0.32285 7 7 c
#> 8 204a formuladelip 0.32285 8 8 d
#> 9 204a wholefish 0.67714 9 9 c
#> 10 204a wholefishdelip 0.67714 10 10 d
df %>%
group_by(Label, Code) %>%
mutate_if(is.numeric, sum) %>%
mutate_if(is.character, funs(paste(unique(.), collapse = "_"))) %>%
distinct()
#> # A tibble: 6 x 6
#> # Groups: Label, Code [6]
#> Label Type Proportion N C Code
#> <chr> <chr> <dbl> <int> <int> <chr>
#> 1 203c wholefish 1.00000 1 1 c
#> 2 203c flesh 1.00000 2 2 a
#> 3 204a flesh_formula 0.99999 8 8 a
#> 4 204a fleshdelip_formuladelip 0.99999 10 10 b
#> 5 204a formula_wholefish 0.99999 16 16 c
#> 6 204a formuladelip_wholefishdelip 0.99999 18 18 d
来源：https://stackoverflow.com/questions/46553514/applying-group-by-and-summarisesum-but-keep-columns-with-non-relevant-conflict