x y
1 1 1
2 3 2
3 2 3
4 3 4
5 2 5
6 4 6
7 5 7
8 2 8
9 1 9
10 1 10
11 3 11
12 4 12
The above is part of the input.
Let's suppose that it also has a bunch of other columns
I want to:
group_by x
summarise y by sum
And for all other columns, I want to summarise_all by just taking the first value
Here's an approach that breaks it into two problems and combines them:
library(dplyr)
left_join(
# Here we want to treat column y specially
df %>%
group_by(x) %>%
summarize(sum_y = sum(y)),
# Here we exclude y and use a different summation for all the remaining columns
df %>%
group_by(x) %>%
select(-y) %>%
summarise_all(first)
)
# A tibble: 5 x 3
x sum_y z
<int> <int> <int>
1 1 20 1
2 2 16 3
3 3 17 2
4 4 18 2
5 5 7 3
Sample data:
df <- read.table(
header = T,
stringsAsFactors = F,
text="x y z
1 1 1
3 2 2
2 3 3
3 4 4
2 5 1
4 6 2
5 7 3
2 8 4
1 9 1
1 10 2
3 11 3
4 12 4")
library(dplyr)
df1 %>%
group_by(x) %>%
summarise_each(list(avg = mean), -y) %>%
bind_cols(.,{df1 %>%
group_by(x) %>%
summarise_at(vars(y), funs(sum)) %>%
select(-x)
})
#> # A tibble: 5 x 4
#> x r_avg r.1_avg y
#> <int> <dbl> <dbl> <int>
#> 1 1 6.67 6.67 20
#> 2 2 5.33 5.33 16
#> 3 3 5.67 5.67 17
#> 4 4 9 9 18
#> 5 5 7 7 7
Created on 2019-06-20 by the reprex package (v0.3.0)
Data:
df1 <- read.table(text="
r x y
1 1 1
2 3 2
3 2 3
4 3 4
5 2 5
6 4 6
7 5 7
8 2 8
9 1 9
10 1 10
11 3 11
12 4 12", header=T)
df1 <- df1[,c(2,3,1,1)]
library(tidyverse)
df <- tribble(~x, ~y, # making a sample data frame
1, 1,
3, 2,
2, 3,
3, 4,
2, 5,
4, 6,
5, 7,
2, 8,
1, 9,
1, 10,
3, 11,
4, 12)
df <- df %>%
add_column(z = sample(1:nrow(df))) #add another column for the example
df
# If there is only one additional column and you need the first value
df %>%
group_by(x) %>%
summarise(sum_y = sum(y), z_1st = z[1])
# otherwise use summarise_at to address all the other columns
f <- function(x){x[1]} # function to extract the first value
df %>%
group_by(x) %>%
summarise_at(.vars = vars(-c('y')), .funs = f) # exclude column y from the calculations
Related
I have long data, and I am trying to make a new variable (consistent) that is the value for a given column (VALUE), for each person (ID), at TIME = 2. I used the code below to do this, but I am getting tripped up on NA's. If the VALUE for TIME = 2 is NA, then I want it to grab the VALUE at TIME = 1 instead. That part I'm not sure how to do. So, in the example below, I want the new variable (consistent) should be 10 instead of NA.
ID = c("A", "A", "B", "B", "C", "C", "D", "D")
TIME = c(1, 2, 1, 2, 1, 2, 1, 2)
VALUE = c(8, 9, 10, NA, 12, 13, 14, 9)
df = data.frame(ID, TIME, VALUE)
df <- df %>%
group_by(ID) %>%
mutate(consistent = VALUE[TIME == 2]) %>% ungroup
df
If we want to use the same code, then coalesce with the 'VALUE' where 'TIME' is 1 (assuming there is a single observation of 'TIME' for each 'ID')
library(dplyr)
df %>%
group_by(ID) %>%
mutate(consistent = coalesce(VALUE[TIME == 2], VALUE[TIME == 1])) %>%
ungroup
-output
# A tibble: 8 × 4
ID TIME VALUE consistent
<chr> <dbl> <dbl> <dbl>
1 A 1 8 9
2 A 2 9 9
3 B 1 10 10
4 B 2 NA 10
5 C 1 12 13
6 C 2 13 13
7 D 1 14 9
8 D 2 9 9
Or another option is to arrange before doing the group_by and get the first element of 'VALUE' (assuming no replicating for 'TIME')
df %>%
arrange(ID, is.na(VALUE), desc(TIME)) %>%
group_by(ID) %>%
mutate(consistent = first(VALUE)) %>%
ungroup
-output
# A tibble: 8 × 4
ID TIME VALUE consistent
<chr> <dbl> <dbl> <dbl>
1 A 2 9 9
2 A 1 8 9
3 B 1 10 10
4 B 2 NA 10
5 C 2 13 13
6 C 1 12 13
7 D 2 9 9
8 D 1 14 9
Another possible solution, using tidyr::fill:
library(tidyverse)
df %>%
group_by(ID) %>%
mutate(consistent = VALUE) %>% fill(consistent) %>% ungroup
#> # A tibble: 8 × 4
#> ID TIME VALUE consistent
#> <chr> <dbl> <dbl> <dbl>
#> 1 A 1 8 8
#> 2 A 2 9 9
#> 3 B 1 10 10
#> 4 B 2 NA 10
#> 5 C 1 12 12
#> 6 C 2 13 13
#> 7 D 1 14 14
#> 8 D 2 9 9
You can also use ifelse with your condition. TIME is guaranteed to be 1 in this scenario if there are only 2 group member each with TIME 1 and 2.
df %>%
group_by(ID) %>%
arrange(TIME, .by_group=T) %>%
mutate(consistent=ifelse(is.na(VALUE)&TIME==2, lag(VALUE), VALUE)) %>%
ungroup()
# A tibble: 8 × 4
ID TIME VALUE consistent
<chr> <dbl> <dbl> <dbl>
1 A 1 8 8
2 A 2 9 9
3 B 1 10 10
4 B 2 NA 10
5 C 1 12 12
6 C 2 13 13
7 D 1 14 14
8 D 2 9 9
This question already has answers here:
Create counter within consecutive runs of values
(3 answers)
Closed 1 year ago.
Unfortunately, I can't wrap my head around this but I'm sure there is a straightforward solution. I've a data.frame that looks like this:
set.seed(1)
mydf <- data.frame(group=sample(c("a", "b"), 20, replace=T))
I'd like to create a new variable that counts from top to bottom, how many times the group occured in a row. Hence, within the example from above it should look like this:
mydf$question <- c(1, 2, 1, 2, 1, 1, 2, 3, 4, 1, 2, 3, 1, 1, 1, 1, 1, 2, 1, 1)
> mydf[1:10,]
group question
1 a 1
2 a 2
3 b 1
4 b 2
5 a 1
6 b 1
7 b 2
8 b 3
9 b 4
10 a 1
Thanks for help.
Using data.table::rleid and dplyr you could do:
set.seed(1)
mydf <- data.frame(group=sample(c("a", "b"), 20, replace=T))
library(dplyr)
library(data.table)
mydf %>%
mutate(id = data.table::rleid(group)) %>%
group_by(id) %>%
mutate(question = row_number()) %>%
ungroup()
#> # A tibble: 20 × 3
#> group id question
#> <chr> <int> <int>
#> 1 a 1 1
#> 2 b 2 1
#> 3 a 3 1
#> 4 a 3 2
#> 5 b 4 1
#> 6 a 5 1
#> 7 a 5 2
#> 8 a 5 3
#> 9 b 6 1
#> 10 b 6 2
#> 11 a 7 1
#> 12 a 7 2
#> 13 a 7 3
#> 14 a 7 4
#> 15 a 7 5
#> 16 b 8 1
#> 17 b 8 2
#> 18 b 8 3
#> 19 b 8 4
#> 20 a 9 1
Update: Most is the same as stefan but without data.table package:
library(dplyr)
mydf %>%
mutate(myrleid = with(rle(group), rep(seq_along(lengths), lengths))) %>%
group_by(myrleid) %>%
mutate(question = row_number()) %>%
ungroup()
group myrleid question
<chr> <int> <int>
1 a 1 1
2 b 2 1
3 a 3 1
4 a 3 2
5 b 4 1
6 a 5 1
7 a 5 2
8 a 5 3
9 b 6 1
10 b 6 2
11 a 7 1
12 a 7 2
13 a 7 3
14 a 7 4
15 a 7 5
16 b 8 1
17 b 8 2
18 b 8 3
19 b 8 4
20 a 9 1
I am using the combn function in R to get all the combinations of the values of variable y taking each time 2 values, grouping by the values of x. My expected final result is the tibble c.
But when I try to do it in tidyverse something is (very) wrong.
library(tidyverse)
df <- tibble(x = c(1, 1, 1, 2, 2, 2, 2),
y = c(8, 9, 7, 3, 5, 2, 1))
# This is what I want
a <- combn(df$y[df$x == 1], 2)
a <- rbind(a, rep(1, ncol(a)))
b <- combn(df$y[df$x == 2], 2)
b <- rbind(b, rep(2, ncol(b)))
c <- cbind(a, b)
c <- tibble(c)
c <- t(c)
# but using tidyverse it does not work
df %>% group_by(x) %>% mutate(z = combn(y, 2))
#> Error: Problem with `mutate()` input `z`.
#> x Input `z` can't be recycled to size 3.
#> i Input `z` is `combn(y, 2)`.
#> i Input `z` must be size 3 or 1, not 2.
#> i The error occurred in group 1: x = 1.
Created on 2020-11-18 by the reprex package (v0.3.0)
Try with combn
out = df %>% group_by(x) %>% do(data.frame(t(combn(.$y, 2))))
# A tibble: 9 x 3
# Groups: x [2]
x X1 X2
<dbl> <dbl> <dbl>
1 1 8 9
2 1 8 7
3 1 9 7
4 2 3 5
5 2 3 2
6 2 3 1
7 2 5 2
8 2 5 1
9 2 2 1
If you have dplyr v1.0.2, you can do this
df %>% group_by(x) %>% group_modify(~as_tibble(t(combn(.$y, 2L))))
Output
# A tibble: 9 x 3
# Groups: x [2]
x V1 V2
<dbl> <dbl> <dbl>
1 1 8 9
2 1 8 7
3 1 9 7
4 2 3 5
5 2 3 2
6 2 3 1
7 2 5 2
8 2 5 1
9 2 2 1
An option with summarise and unnest
library(dplyr)
library(tidyr)
df %>%
group_by(x) %>%
summarise(y = list(as.data.frame(t(combn(y, 2)))), .groups = 'drop') %>%
unnest(c(y))
# A tibble: 9 x 3
# x V1 V2
# <dbl> <dbl> <dbl>
#1 1 8 9
#2 1 8 7
#3 1 9 7
#4 2 3 5
#5 2 3 2
#6 2 3 1
#7 2 5 2
#8 2 5 1
#9 2 2 1
I am having troubles restructuring the data as I need to.
My df looks like this:
id <- (1:20)
author <- c("A","A","A","A","A","B","B","B","A","A","A","B","B","B","B"
,"B","B","B","A","A")
df <- data.frame(id, author)
> print(df)
id author
1 1 A
2 2 A
3 3 A
4 4 A
5 5 A
6 6 B
7 7 B
8 8 B
9 9 A
10 10 A
11 11 A
12 12 B
13 13 B
14 14 B
15 15 B
16 16 B
17 17 B
18 18 B
19 19 A
20 20 A
And I'm trying to get a data structure where the columns are the authors and the rwos indicate the first and last id values of each sequence of A or B values. So in this case the first row with author A is id = 1, and the last one of that series is id 5, and so forth.
Something like this:
A <- c(1, 5, 9, 11, 19,20)
B <- c(6, 8, 12, 18, NA, NA)
df.desired <- data.frame(A, B)
print(df.desired)
A B
1 1 6
2 5 8
3 9 12
4 11 18
5 19 NA
6 20 NA
Any ideas?
Thanks a lot!
We can create groups using data.table rleid, select 1st and last row in each group and get data in wide format.
library(dplyr)
df %>%
group_by(grp = data.table::rleid(author)) %>%
slice(1L, n()) %>%
group_by(author) %>%
mutate(grp = row_number()) %>%
tidyr::pivot_wider(names_from = author, values_from = id) %>%
select(-grp)
# A tibble: 6 x 2
# A B
# <int> <int>
#1 1 6
#2 5 8
#3 9 12
#4 11 18
#5 19 NA
#6 20 NA
For the updated request in comments we can do :
df %>%
group_by(grp = data.table::rleid(author)) %>%
slice(1L, n()) %>%
mutate(author = row_number()) %>%
tidyr::pivot_wider(names_from = row, values_from = id) %>%
ungroup %>%
select(-grp)
# A tibble: 5 x 2
# `1` `2`
# <int> <int>
#1 1 5
#2 6 8
#3 9 11
#4 12 18
#5 19 20
Here is a base R option
z <- rle(df$author)
lst <- split(df,findInterval(1:nrow(df),cumsum(z$lengths), left.open = TRUE))
u <- lapply(lst,function(v) range(v$id))
idx <- split(seq_along(z$values),z$values)
x <- lapply(idx,function(v) unlist(u[v],use.names = FALSE))
df.desired <- as.data.frame(lapply(x,`length<-`,max(lengths(x))))
which gives
> df.desired
A B
1 1 6
2 5 8
3 9 12
4 11 18
5 19 NA
6 20 NA
An option using data.table:
library(data.table)
dcast(
setDT(df)[, ri := rleid(author)][, id[c(1L, .N)], .(author, ri)],
rowid(author) ~ author, value.var="V1")
output:
author A B
1: 1 1 6
2: 2 5 8
3: 3 9 12
4: 4 11 18
5: 5 19 NA
6: 6 20 NA
If there is a possibility of an author having a single row, you will need unique(c(1L, .N))
I have a dataframe with several columns containing list columns that I want to unnest (or unchop). BUT, they are different lengths, so the resulting error is Error: No common size for...
Here is a reprex to show what works and doesn't work.
library(tidyr)
library(vctrs)
# This works as expected
df_A <- tibble(
ID = 1:3,
A = as_list_of(list(c(9, 8, 5), c(7,6), c(6, 9)))
)
unchop(df_A, cols = c(A))
# A tibble: 7 x 2
ID A
<int> <dbl>
1 1 9
2 1 8
3 1 5
4 2 7
5 2 6
6 3 6
7 3 9
# This works as expected as the lists are the same lengths
df_AB_1 <- tibble(
ID = 1:3,
A = as_list_of(list(c(9, 8, 5), c(7,6), c(6, 9))),
B = as_list_of(list(c(1, 2, 3), c(4, 5), c(7, 8)))
)
unchop(df_AB_1, cols = c(A, B))
# A tibble: 7 x 3
ID A B
<int> <dbl> <dbl>
1 1 9 1
2 1 8 2
3 1 5 3
4 2 7 4
5 2 6 5
6 3 6 7
7 3 9 8
# This does NOT work as the lists are different lengths
df_AB_2 <- tibble(
ID = 1:3,
A = as_list_of(list(c(9, 8, 5), c(7,6), c(6, 9))),
B = as_list_of(list(c(1, 2), c(4, 5, 6), c(7, 8, 9, 0)))
)
unchop(df_AB_2, cols = c(A, B))
# Error: No common size for `A`, size 3, and `B`, size 2.
The output that I would like to achieve for df_AB_2 above is as follows where each list is unchopped and missing values are filled with NA:
# A tibble: 10 x 3
ID A B
<dbl> <dbl> <dbl>
1 1 9 1
2 1 8 2
3 1 5 NA
4 2 7 4
5 2 6 5
6 2 NA 6
7 3 6 7
8 3 9 8
9 3 NA 9
10 3 NA 0
I have referenced this issue on Github and StackOverflow here.
Any ideas how to achieve the result above?
Versions
> packageVersion("tidyr")
[1] ‘1.0.0’
> packageVersion("vctrs")
[1] ‘0.2.0.9001’
Here is an idea via dplyr that you can generalise to as many columns as you want,
library(tidyverse)
df_AB_2 %>%
pivot_longer(c(A, B)) %>%
mutate(value = lapply(value, `length<-`, max(lengths(value)))) %>%
pivot_wider(names_from = name, values_from = value) %>%
unnest() %>%
filter(rowSums(is.na(.[-1])) != 2)
which gives,
# A tibble: 10 x 3
ID A B
<int> <dbl> <dbl>
1 1 9 1
2 1 8 2
3 1 5 NA
4 2 7 4
5 2 6 5
6 2 NA 6
7 3 6 7
8 3 9 8
9 3 NA 9
10 3 NA 0
Defining a helper function to update the lengths of the element and proceeding with dplyr:
foo <- function(x, len_vec) {
lapply(
seq_len(length(x)),
function(i) {
length(x[[i]]) <- len_vec[i]
x[[i]]
}
)
}
df_AB_2 %>%
mutate(maxl = pmax(lengths(A), lengths(B))) %>%
mutate(A = foo(A, maxl), B = foo(B, maxl)) %>%
unchop(cols = c(A, B)) %>%
select(-maxl)
# A tibble: 10 x 3
ID A B
<int> <dbl> <dbl>
1 1 9 1
2 1 8 2
3 1 5 NA
4 2 7 4
5 2 6 5
6 2 NA 6
7 3 6 7
8 3 9 8
9 3 NA 9
10 3 NA 0
Using data.table:
library(data.table)
setDT(df_AB_2)
df_AB_2[, maxl := pmax(lengths(A), lengths(B))]
df_AB_2[, .(unlist(A)[seq_len(maxl)], unlist(B)[seq_len(maxl)]), by = ID]