R: Separate data into combinations of two columns - r

I have some data where each id is measured by different types which can be have different values type_val. The measured value is val. A small dummy data is like this:
df <- data.frame(id=rep(letters[1:2],6),
type=c(rep('t1',6), rep('t2',6)),
type_val=rep(c(1,1,2,2,3,3),2),
val=1:12)
Then df is:
id type type_val val
1 a t1 1 1
2 b t1 1 2
3 a t1 2 3
4 b t1 2 4
5 a t1 3 5
6 b t1 3 6
7 a t2 1 7
8 b t2 1 8
9 a t2 2 9
10 b t2 2 10
11 a t2 3 11
12 b t2 3 12
I need to spread/cast data so that all combinations of type and type_val for each id are row-wise. I think this must be a job for pkgs reshape2 or tidyr but I have completely failed to generate anything other than errors.
The outcome data structure - somewhat redundant - would be something like this (hope I got it right!) where pairs of type (as given by combinations of the type_val) are columns type_t1 and type_t2 , and their associated values (val in df) are val_t1 and val_t2 - columns names are of cause arbitrary :
id type_t1 type_t2 val_t1 val_t2
1 a 1 1 1 7
2 a 1 2 1 9
3 a 1 3 1 11
4 a 2 1 3 7
5 a 2 2 3 9
6 a 2 3 3 11
7 a 3 1 5 7
8 a 3 2 5 9
9 a 3 3 5 11
10 b 1 1 2 8
11 b 1 2 2 10
12 b 1 3 2 12
13 b 2 1 4 8
14 b 2 2 4 10
15 b 2 3 4 12
16 b 3 1 6 8
17 b 3 2 6 10
18 b 3 3 6 12
UPDATE
Note that (#Sotos)
> spread(df, type, val)
id type_val t1 t2
1 a 1 1 7
2 a 2 3 9
3 a 3 5 11
4 b 1 2 8
5 b 2 4 10
6 b 3 6 12
is not the desired output - it fails to deliver the wide format defined by combinations of type and type_val in df.

how about this:
df1=df[df$type=="t1",]
df2=df[df$type=="t2",]
DF=merge(df1,df2,by="id")
DF=DF[,-c(2,5)]
colnames(DF)<-c("id", "type_t1", "val_t1","type_t2", "val_t2")

Here is something more generic that will work with an arbitrary number of unique type:
library(dplyr)
# This function takes a list of dataframes (.data) and merges them by ID
reduce_merge <- function(.data, ID) {
return(Reduce(function(x, y) merge(x, y, by = ID), .data))
}
# This function renames the cols columns in .data by appending _identifier
batch_rename <- function(.data, cols, identifier, sep = '_') {
return(plyr::rename(.data, sapply(cols, function(x){
x = paste(x, .data[1, identifier], sep = sep)
})))
}
# This function creates a list of subsetted dataframes
# (subsetted by values of key),
# uses batch_rename() to give each dataframe more informative column names,
# merges them together, and returns the columns you'd like in a sensible order
multi_spread <- function(.data, grp, key, vals) {
.data %>%
plyr::dlply(key, subset) %>%
lapply(batch_rename, vals, key) %>%
reduce_merge(grp) %>%
select(-starts_with(paste0(key, '.'))) %>%
select(id, sort(setdiff(colnames(.), c(grp, key, vals))))
}
# Your example
df <- data.frame(id=rep(letters[1:2],6),
type=c(rep('t1',6), rep('t2',6)),
type_val=rep(c(1,1,2,2,3,3),2),
val=1:12)
df %>% multi_spread('id', 'type', c('type_val', 'val'))
id type_val_t1 type_val_t2 val_t1 val_t2
1 a 1 1 1 7
2 a 1 2 1 9
3 a 1 3 1 11
4 a 2 1 3 7
5 a 2 2 3 9
6 a 2 3 3 11
7 a 3 1 5 7
8 a 3 2 5 9
9 a 3 3 5 11
10 b 1 1 2 8
11 b 1 2 2 10
12 b 1 3 2 12
13 b 2 1 4 8
14 b 2 2 4 10
15 b 2 3 4 12
16 b 3 1 6 8
17 b 3 2 6 10
18 b 3 3 6 12
# An example with three unique values of 'type'
df <- data.frame(id = rep(letters[1:2], 9),
type = c(rep('t1', 6), rep('t2', 6), rep('t3', 6)),
type_val = rep(c(1, 1, 2, 2, 3, 3), 3),
val = 1:18)
df %>% multi_spread('id', 'type', c('type_val', 'val'))
id type_val_t1 type_val_t2 type_val_t3 val_t1 val_t2 val_t3
1 a 1 1 1 1 7 13
2 a 1 1 2 1 7 15
3 a 1 1 3 1 7 17
4 a 1 2 1 1 9 13
5 a 1 2 2 1 9 15
6 a 1 2 3 1 9 17
7 a 1 3 1 1 11 13
8 a 1 3 2 1 11 15
9 a 1 3 3 1 11 17
10 a 2 1 1 3 7 13
11 a 2 1 2 3 7 15
12 a 2 1 3 3 7 17
13 a 2 2 1 3 9 13
14 a 2 2 2 3 9 15
15 a 2 2 3 3 9 17
16 a 2 3 1 3 11 13
17 a 2 3 2 3 11 15
18 a 2 3 3 3 11 17
19 a 3 1 1 5 7 13
20 a 3 1 2 5 7 15
21 a 3 1 3 5 7 17
22 a 3 2 1 5 9 13
23 a 3 2 2 5 9 15
24 a 3 2 3 5 9 17
25 a 3 3 1 5 11 13
26 a 3 3 2 5 11 15
27 a 3 3 3 5 11 17
28 b 1 1 1 2 8 14
29 b 1 1 2 2 8 16
30 b 1 1 3 2 8 18
31 b 1 2 1 2 10 14
32 b 1 2 2 2 10 16
33 b 1 2 3 2 10 18
34 b 1 3 1 2 12 14
35 b 1 3 2 2 12 16
36 b 1 3 3 2 12 18
37 b 2 1 1 4 8 14
38 b 2 1 2 4 8 16
39 b 2 1 3 4 8 18
40 b 2 2 1 4 10 14
41 b 2 2 2 4 10 16
42 b 2 2 3 4 10 18
43 b 2 3 1 4 12 14
44 b 2 3 2 4 12 16
45 b 2 3 3 4 12 18
46 b 3 1 1 6 8 14
47 b 3 1 2 6 8 16
48 b 3 1 3 6 8 18
49 b 3 2 1 6 10 14
50 b 3 2 2 6 10 16
51 b 3 2 3 6 10 18
52 b 3 3 1 6 12 14
53 b 3 3 2 6 12 16
54 b 3 3 3 6 12 18

Related

Exclude rows where value used in another row

Imagine you have the following data set:
df = data.frame(ID = c(1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20), gender= c(1,2,1,2,2,2,2,1,1,2,1,2,1,2,2,2,2,1,1,2),
PID = c(1,1,2,2,3,3,4,4,5,5,6,6,7,7,8,8,9,9,10,10))
how can I write a code that removes the rows in the df whose gender and PID are the same (see picture). Please imagine that the code is over 1000 rows long (so it should be a solution that automatically searches for the right values to exclude).
base R
df[ave(rep(TRUE, nrow(df)), df[,c("gender","paar")], FUN = function(z) !any(duplicated(z))),]
# ID gender paar
# 1 1 1 1
# 2 2 2 1
# 3 3 1 2
# 4 4 2 2
# 7 7 2 4
# 8 8 1 4
# 9 9 1 5
# 10 10 2 5
# 11 11 1 6
# 12 12 2 6
# 13 13 1 7
# 14 14 2 7
# 17 17 2 9
# 18 18 1 9
# 19 19 1 10
# 20 20 2 10
dplyr
library(dplyr)
df %>%
group_by(gender, paar) %>%
filter(!any(duplicated(cbind(gender, paar)))) %>%
ungroup()
In base R, we may use subset after removing the observations where the group count for 'gender' and 'paar' are not 1
subset(df, ave(seq_along(gender), gender, paar, FUN = length) == 1)
Or with duplicated
df[!(duplicated(df[-1])|duplicated(df[-1], fromLast = TRUE)),]
-output
ID gender paar
1 1 1 1
2 2 2 1
3 3 1 2
4 4 2 2
7 7 2 4
8 8 1 4
9 9 1 5
10 10 2 5
11 11 1 6
12 12 2 6
13 13 1 7
14 14 2 7
17 17 2 9
18 18 1 9
19 19 1 10
20 20 2 10
Here is one more: :-)
library(dplyr)
df %>%
group_by(gender, PID) %>%
filter(is.na(ifelse(n()>1, 1, NA)))
ID gender PID
<dbl> <dbl> <dbl>
1 1 1 1
2 2 2 1
3 3 1 2
4 4 2 2
5 7 2 4
6 8 1 4
7 9 1 5
8 10 2 5
9 11 1 6
10 12 2 6
11 13 1 7
12 14 2 7
13 17 2 9
14 18 1 9
15 19 1 10
16 20 2 10
Another dplyr option could be:
df %>%
filter(with(rle(paste0(gender, PID)), rep(lengths == 1, lengths)))
ID gender PID
1 1 1 1
2 2 2 1
3 3 1 2
4 4 2 2
5 7 2 4
6 8 1 4
7 9 1 5
8 10 2 5
9 11 1 6
10 12 2 6
11 13 1 7
12 14 2 7
13 17 2 9
14 18 1 9
15 19 1 10
16 20 2 10
If the duplicated values can occur also between non-consecutive rows:
df %>%
arrange(gender, PID) %>%
filter(with(rle(paste0(gender, PID)), rep(lengths == 1, lengths)))
Using aggregate
na.omit(aggregate(. ~ gender + PID, df, function(x)
ifelse(length(x) == 1, x, NA)))
gender PID ID
1 1 1 1
2 2 1 2
3 1 2 3
4 2 2 4
6 1 4 8
7 2 4 7
8 1 5 9
9 2 5 10
10 1 6 11
11 2 6 12
12 1 7 13
13 2 7 14
15 1 9 18
16 2 9 17
17 1 10 19
18 2 10 20
With dplyr
library(dplyr)
df %>%
group_by(gender, PID) %>%
filter(n() == 1) %>%
ungroup()
# A tibble: 16 × 3
ID gender PID
<dbl> <dbl> <dbl>
1 1 1 1
2 2 2 1
3 3 1 2
4 4 2 2
5 7 2 4
6 8 1 4
7 9 1 5
8 10 2 5
9 11 1 6
10 12 2 6
11 13 1 7
12 14 2 7
13 17 2 9
14 18 1 9
15 19 1 10
16 20 2 10

How to add a column with repeating but changing sequence?

I'm trying to add a column with repeating sequence but one that changes for each group. In the example data, the group is the id column.
data <- tibble::expand_grid(id = 1:12, condition = c("a", "b", "c"))
data
id condition
1 a
1 b
1 c
2 a
2 b
2 c
3 a
3 b
3 c
... and so on
I'd like to add a column called order to repeat various combinations like 1 2 3 2 3 1 3 1 2 1 3 2 2 1 3 3 2 1 for each id.
In the end, the desired output will look like this
id condition order
1 a 1
1 b 2
1 c 3
2 a 2
2 b 3
2 c 1
3 a 3
3 b 1
3 c 2
... and so on
I'm looking for a simple mutate solution or base R solution. I tried generating a list of combinations but I'm not sure how to create a variable from that.
You can use perms from package pracma to generate all permutations, e.g.,
data %>%
cbind(order = c(t(pracma::perms(1:3))))
which gives
id condition order
1 1 a 3
2 1 b 2
3 1 c 1
4 2 a 3
5 2 b 1
6 2 c 2
7 3 a 2
8 3 b 3
9 3 c 1
10 4 a 2
11 4 b 1
12 4 c 3
13 5 a 1
14 5 b 2
15 5 c 3
16 6 a 1
17 6 b 3
18 6 c 2
19 7 a 3
20 7 b 2
21 7 c 1
22 8 a 3
23 8 b 1
24 8 c 2
25 9 a 2
26 9 b 3
27 9 c 1
28 10 a 2
29 10 b 1
30 10 c 3
31 11 a 1
32 11 b 2
33 11 c 3
34 12 a 1
35 12 b 3
36 12 c 2

How to create an increasing index based on a certain condition?

Suppose I have this dataframe:
df <- data.frame(co11 = c(rep(1, 5), 5, 6, rep(1, 3), 2, 3, 4, 5, 8, rep(1, 2), rep(2, 2), 8, 10))
I would like to create another column (col2) with increasing group index whenever a value in a row is at least 5. To illustrate, here is the resulting df that I would like to get:
co11 col2
1 1 1
2 1 1
3 1 1
4 1 1
5 1 1
6 5 2
7 6 3
8 1 3
9 1 3
10 1 3
11 2 3
12 3 3
13 4 3
14 5 4
15 8 5
16 1 5
17 1 5
18 2 5
19 2 5
20 8 6
21 10 7
Is there an available function in dplyr that can do this?
Waldi's answer is very good, here is a slightly modified version:
library(dplyr)
df %>%
group_by(col2 =cumsum(co11 >= 5)+1)
co11 col2
1 1 1
2 1 1
3 1 1
4 1 1
5 1 1
6 5 2
7 6 3
8 1 3
9 1 3
10 1 3
11 2 3
12 3 3
13 4 3
14 5 4
15 8 5
16 1 5
17 1 5
18 2 5
19 2 5
20 8 6
21 10 7
You could use pmax to find maximum value of each row, and cumsum to sum occurences above 5 :
df %>% mutate(newcol=cumsum(do.call(pmax,select(.,everything()))>=5)+1)
co11 newcol
1 1 1
2 1 1
3 1 1
4 1 1
5 1 1
6 5 2
7 6 3
8 1 3
9 1 3
10 1 3
11 2 3
12 3 3
13 4 3
14 5 4
15 8 5
16 1 5
17 1 5
18 2 5
19 2 5
20 8 6
21 10 7

Replace row value in a data frame group by the smallest value in that group

I have the following data set:
time <- c(0,1,2,3,4,5,0,1,2,3,4,5,0,1,2,3,4,5)
value <- c(10,8,6,5,3,2,12,10,6,5,4,2,20,15,16,9,2,2)
group <- c(1,1,1,1,1,1,2,2,2,2,2,2,3,3,3,3,3,3)
data <- data.frame(time, value, group)
I want to create a new column called data$diff that is equal to data$value minus the value of data$value when data$time == 0 within each group.
I am beginning with the following code
for(i in 1:nrow(data)){
for(n in 1:max(data$group)){
if(data$group[i] == n) {
data$diff[i] <- ???????
}
}
}
But cannot figure out what to put in place of the question marks. The desired output would be this table: https://i.stack.imgur.com/1bAKj.png
Any thoughts are appreciated.
Since in your example data$time == 0 is always the first element of the group, you can use this data.table approach.
library(data.table)
setDT(data)
data[, diff := value[1] - value, by = group]
In case that data$time == 0 is not the first element in each group you can use this:
data[, diff := value[time==0] - value, by = group]
Output:
> data
time value group diff
1: 0 10 1 0
2: 1 8 1 2
3: 2 6 1 4
4: 3 5 1 5
5: 4 3 1 7
6: 5 2 1 8
7: 0 12 2 0
8: 1 10 2 2
9: 2 6 2 6
10: 3 5 2 7
11: 4 4 2 8
12: 5 2 2 10
13: 0 20 3 0
14: 1 15 3 5
15: 2 16 3 4
16: 3 9 3 11
17: 4 2 3 18
18: 5 2 3 18
Here is a base R approach.
within(data, diff <- ave(
seq_along(value), group,
FUN = \(i) value[i][time[i] == 0] - value[i]
))
Output
time value group diff
1 0 10 1 0
2 1 8 1 2
3 2 6 1 4
4 3 5 1 5
5 4 3 1 7
6 5 2 1 8
7 0 12 2 0
8 1 10 2 2
9 2 6 2 6
10 3 5 2 7
11 4 4 2 8
12 5 2 2 10
13 0 20 3 0
14 1 15 3 5
15 2 16 3 4
16 3 9 3 11
17 4 2 3 18
18 5 2 3 18
Here is a short way to do it with dplyr.
library(dplyr)
data %>%
group_by(group) %>%
mutate(diff = value[which(time == 0)] - value)
Which gives
# Groups: group [3]
time value group diff
<dbl> <dbl> <dbl> <dbl>
1 0 10 1 0
2 1 8 1 2
3 2 6 1 4
4 3 5 1 5
5 4 3 1 7
6 5 2 1 8
7 0 12 2 0
8 1 10 2 2
9 2 6 2 6
10 3 5 2 7
11 4 4 2 8
12 5 2 2 10
13 0 20 3 0
14 1 15 3 5
15 2 16 3 4
16 3 9 3 11
17 4 2 3 18
18 5 2 3 18
library(dplyr)
vals2use <- data %>%
group_by(group) %>%
filter(time==0) %>%
select(c(2,3)) %>%
rename(value4diff=value)
dataNew <- merge(data, vals2use, all=T)
dataNew$diff <- dataNew$value4diff-dataNew$value
dataNew <- dataNew[,c(1,2,3,5)]
dataNew
group time value diff
1 1 0 10 0
2 1 1 8 2
3 1 2 6 4
4 1 3 5 5
5 1 4 3 7
6 1 5 2 8
7 2 0 12 0
8 2 1 10 2
9 2 2 6 6
10 2 3 5 7
11 2 4 4 8
12 2 5 2 10
13 3 0 20 0
14 3 1 15 5
15 3 2 16 4
16 3 3 9 11
17 3 4 2 18
18 3 5 2 18

How to define rows numbering depending on a group and a value in group's first rows?

A dataframe DD has some missing rows. Based on the values in 'ID_raw' column I have duplicated the rows in order to replace the missing rows. Now I have to number the rows in such way that the first value in each group (column 'File') equals the value in the same row in the column 'ID_raw'. This will be a key in joining the dataframe with another one. Below a dummy example of the DD dataframe:
DD<-data.frame(ID_raw=c(1,5,7,8,5,7,9,13,3,6),Val=c(1,2,8,15,54,23,88,77,32,2),File=c("A","A","A","A","B","B","B","B","C","C"))
ID_raw Val File
1 1 1 A
2 5 2 A
3 7 8 A
4 8 15 A
5 5 54 B
6 7 23 B
7 9 88 B
8 13 77 B
9 3 32 C
10 6 2 C
So far I've successfully duplicated the rows, however, I have a problem in numbering the rows in such way, that they start from the same value as the value in ID_raw column for each group ('File').
DD$ID_diff <- 0
DD$ID_diff[1:nrow(DD)-1] <- as.integer(diff(DD$ID_raw, 1)) #values which tell how many times a row has to be duplicated
DD$ID_diff <- sapply(DD$ID_diff, function(x) ifelse(x<0, 0, x)) #replacement the values <0 (for the first rows in each 'File' group)
DD <- DD[rep(seq(nrow(DD)), DD$ID_diff), 1:ncol(DD)] #rows duplication
Based on the code above I receive this output:
ID_raw Val File ID_diff
1 1 1 A 4
1.1 1 1 A 4
1.2 1 1 A 4
1.3 1 1 A 4
2 5 2 A 2
2.1 5 2 A 2
3 7 8 A 1
5 5 54 B 2
5.1 5 54 B 2
6 7 23 B 2
6.1 7 23 B 2
7 9 88 B 4
7.1 9 88 B 4
7.2 9 88 B 4
7.3 9 88 B 4
9 3 32 C 3
9.1 3 32 C 3
9.2 3 32 C 3
I would like to receive this:
ID_raw Val File ID_diff ID_new
1 1 1 A 4 1
1.1 1 1 A 4 2
1.2 1 1 A 4 3
1.3 1 1 A 4 4
2 5 2 A 2 5
2.1 5 2 A 2 6
3 7 8 A 1 7
5 5 54 B 2 5
5.1 5 54 B 2 6
6 7 23 B 2 7
6.1 7 23 B 2 8
7 9 88 B 4 9
7.1 9 88 B 4 10
7.2 9 88 B 4 11
7.3 9 88 B 4 12
9 3 32 C 3 3
9.1 3 32 C 3 4
9.2 3 32 C 3 5
This is one option using dplyr based on the output of your code:
df %>%
group_by(File) %>%
mutate(ID_new = seq(1, n()) + first(ID_raw) - 1)
# A tibble: 18 x 5
# Groups: File [3]
ID_raw Val File ID_diff ID_new
<int> <int> <fct> <int> <dbl>
1 1 1 A 4 1
2 1 1 A 4 2
3 1 1 A 4 3
4 1 1 A 4 4
5 5 2 A 2 5
6 5 2 A 2 6
7 7 8 A 1 7
8 5 54 B 2 5
9 5 54 B 2 6
10 7 23 B 2 7
11 7 23 B 2 8
12 9 88 B 4 9
13 9 88 B 4 10
14 9 88 B 4 11
15 9 88 B 4 12
16 3 32 C 3 3
17 3 32 C 3 4
18 3 32 C 3 5
We can do this in the chain from the beginning itself i.e. instead of creating the 'ID_diff' and using sapply, directly use diff on the 'ID_raw', then uncount, grouped by 'File', create the sequence column
library(tidyverse)
DD %>%
mutate(ID_diff = pmax(c(diff(ID_raw), 0), 0)) %>%
uncount(ID_diff, .remove = FALSE) %>%
group_by(File) %>%
mutate(ID_new = seq(first(ID_raw), length.out = n(), by = 1))
# A tibble: 18 x 5
# Groups: File [3]
# ID_raw Val File ID_diff ID_new
# <dbl> <dbl> <fct> <dbl> <dbl>
# 1 1 1 A 4 1
# 2 1 1 A 4 2
# 3 1 1 A 4 3
# 4 1 1 A 4 4
# 5 5 2 A 2 5
# 6 5 2 A 2 6
# 7 7 8 A 1 7
# 8 5 54 B 2 5
# 9 5 54 B 2 6
#10 7 23 B 2 7
#11 7 23 B 2 8
#12 9 88 B 4 9
#13 9 88 B 4 10
#14 9 88 B 4 11
#15 9 88 B 4 12
#16 3 32 C 3 3
#17 3 32 C 3 4
#18 3 32 C 3 5

Resources