Adding sequence of numbers to the data - r

Hi I have a data frame like this
df <-data.frame(x=rep(rep(seq(0,3),each=2),2 ),gr=gl(2,8))
x gr
1 0 1
2 0 1
3 1 1
4 1 1
5 2 1
6 2 1
7 3 1
8 3 1
9 0 2
10 0 2
11 1 2
12 1 2
13 2 2
14 2 2
15 3 2
16 3 2
I want to add a new column numbering sequence of numbers when the x value ==0
I tried
library(dplyr)
df%>%
group_by(gr)%>%
mutate(numbering=seq(2,8,2))
Error in mutate_impl(.data, dots) :
Column `numbering` must be length 8 (the group size) or one, not 4
?
Just for side note mutate(numbering=rep(seq(2,8,2),each=2)) would work for this minimal example but for the general case its better to look x value change from 0!
the expected output
x gr numbering
1 0 1 2
2 0 1 2
3 1 1 4
4 1 1 4
5 2 1 6
6 2 1 6
7 3 1 8
8 3 1 8
9 0 2 2
10 0 2 2
11 1 2 4
12 1 2 4
13 2 2 6
14 2 2 6
15 3 2 8
16 3 2 8

Do you mean something like this?
library(tidyverse);
df %>%
group_by(gr) %>%
mutate(numbering = cumsum(c(1, diff(x) != 0)))
## A tibble: 16 x 3
## Groups: gr [2]
# x gr numbering
# <int> <fct> <dbl>
# 1 0 1 1.
# 2 0 1 1.
# 3 1 1 2.
# 4 1 1 2.
# 5 2 1 3.
# 6 2 1 3.
# 7 3 1 4.
# 8 3 1 4.
# 9 0 2 1.
#10 0 2 1.
#11 1 2 2.
#12 1 2 2.
#13 2 2 3.
#14 2 2 3.
#15 3 2 4.
#16 3 2 4.
Or if you must have a numbering sequence 2,4,6,... instead of 1,2,3,... you can do
df %>%
group_by(gr) %>%
mutate(numering = 2 * cumsum(c(1, diff(x) != 0)));
## A tibble: 16 x 3
## Groups: gr [2]
# x gr numering
# <int> <fct> <dbl>
# 1 0 1 2.
# 2 0 1 2.
# 3 1 1 4.
# 4 1 1 4.
# 5 2 1 6.
# 6 2 1 6.
# 7 3 1 8.
# 8 3 1 8.
# 9 0 2 2.
#10 0 2 2.
#11 1 2 4.
#12 1 2 4.
#13 2 2 6.
#14 2 2 6.
#15 3 2 8.
#16 3 2 8.

Here is an option using match to get the index and then pass on the seq values to fill
df %>%
group_by(gr) %>%
mutate(numbering = seq(2, length.out = n()/2, by = 2)[match(x, unique(x))])
# A tibble: 16 x 3
# Groups: gr [2]
# x gr numbering
# <int> <fct> <dbl>
# 1 0 1 2
# 2 0 1 2
# 3 1 1 4
# 4 1 1 4
# 5 2 1 6
# 6 2 1 6
# 7 3 1 8
# 8 3 1 8
# 9 0 2 2
#10 0 2 2
#11 1 2 4
#12 1 2 4
#13 2 2 6
#14 2 2 6
#15 3 2 8
#16 3 2 8

Related

identify whenever values repeat in r

I have a dataframe like this.
data <- data.frame(Condition = c(1,1,2,3,1,1,2,2,2,3,1,1,2,3,3))
I want to populate a new variable Sequence which identifies whenever Condition starts again from 1.
So the new dataframe would look like this.
Thanks in advance for the help!
data <- data.frame(Condition = c(1,1,2,3,1,1,2,2,2,3,1,1,2,3,3),
Sequence = c(1,1,1,1,2,2,2,2,2,2,3,3,3,3,3))
base R
data$Sequence2 <- cumsum(c(TRUE, data$Condition[-1] == 1 & data$Condition[-nrow(data)] != 1))
data
# Condition Sequence Sequence2
# 1 1 1 1
# 2 1 1 1
# 3 2 1 1
# 4 3 1 1
# 5 1 2 2
# 6 1 2 2
# 7 2 2 2
# 8 2 2 2
# 9 2 2 2
# 10 3 2 2
# 11 1 3 3
# 12 1 3 3
# 13 2 3 3
# 14 3 3 3
# 15 3 3 3
dplyr
library(dplyr)
data %>%
mutate(
Sequence2 = cumsum(Condition == 1 & lag(Condition != 1, default = TRUE))
)
# Condition Sequence Sequence2
# 1 1 1 1
# 2 1 1 1
# 3 2 1 1
# 4 3 1 1
# 5 1 2 2
# 6 1 2 2
# 7 2 2 2
# 8 2 2 2
# 9 2 2 2
# 10 3 2 2
# 11 1 3 3
# 12 1 3 3
# 13 2 3 3
# 14 3 3 3
# 15 3 3 3
This took a while. Finally I find this solution:
library(dplyr)
data %>%
group_by(Sequnce = cumsum(
ifelse(Condition==1, lead(Condition)+1, Condition)
- Condition==1)
)
Condition Sequnce
<dbl> <int>
1 1 1
2 1 1
3 2 1
4 3 1
5 1 2
6 1 2
7 2 2
8 2 2
9 2 2
10 3 2
11 1 3
12 1 3
13 2 3
14 3 3
15 3 3

Apply same function to several data replicates in R

Consider the following data simulation mechanism:
set.seed(1)
simulW <- function(G)
{
# Let G be the number of groups
n<-2*G #Assume 2 individuals per group
i<-rep(1:G, rep(2,G)) # Group index
j<-rep (1:n)
Y<-rbinom(n, 1, 0.5) # binary
data.frame(id=1:n, i,Y)
}
r<-5 #5 replicates
dat1 <- replicate(r, simulW(G = 10 ), simplify=FALSE)
#For example the first data replicate will be
> dat1[[1]]
id i Y
1 1 1 0
2 2 1 1
3 3 2 0
4 4 2 0
5 5 3 0
6 6 3 0
7 7 4 0
8 8 4 1
9 9 5 1
10 10 5 0
The code below can perform group wise (i is the group) sum of Y but by default considers only the first replicate i.e dat1[[1]].
Di<-aggregate( Y, by=list ( i ),FUN=sum) #Sum per group for the first dataset
e<-colSums(Di [ 2 ] ) #Total sum of Y for all groups for dataset 1
> e
x
8
di<-Di [ 2 ] # Groupwise sum for replicate 1
> di
x
1 2
2 2
3 2
4 0
5 2
How can I use the same function to perform the group wise sum for the other replicates.
Maybe something like:
for (m in 1:r )
{
Di[m]<-
e[m]<-
di[m]<-
}
You may use aggregate in lapply -
result <- lapply(dat1, function(x) aggregate(Y~i, x, sum))
result
#[[1]]
# i Y
#1 1 1
#2 2 1
#3 3 0
#4 4 0
#5 5 1
#6 6 1
#7 7 0
#8 8 2
#9 9 1
#10 10 1
#[[2]]
# i Y
#1 1 2
#2 2 2
#3 3 2
#4 4 0
#5 5 2
#6 6 1
#7 7 0
#8 8 0
#9 9 1
#10 10 1
#...
#...
We may use tidyverse
library(purrr)
library(dplyr)
map(dat1, ~ .x %>%
group_by(i) %>%
summarise(Y = sum(Y)))
-output
[[1]]
# A tibble: 10 × 2
i Y
<int> <int>
1 1 0
2 2 2
3 3 1
4 4 2
5 5 1
6 6 0
7 7 1
8 8 1
9 9 2
10 10 1
[[2]]
# A tibble: 10 × 2
i Y
<int> <int>
1 1 1
2 2 1
3 3 0
4 4 0
5 5 1
6 6 1
7 7 0
8 8 2
9 9 1
10 10 1
[[3]]
# A tibble: 10 × 2
i Y
<int> <int>
1 1 2
2 2 2
3 3 2
4 4 0
5 5 2
6 6 1
7 7 0
8 8 0
9 9 1
10 10 1
[[4]]
# A tibble: 10 × 2
i Y
<int> <int>
1 1 1
2 2 0
3 3 1
4 4 1
5 5 1
6 6 1
7 7 0
8 8 1
9 9 1
10 10 2
[[5]]
# A tibble: 10 × 2
i Y
<int> <int>
1 1 1
2 2 0
3 3 1
4 4 1
5 5 0
6 6 0
7 7 2
8 8 2
9 9 0
10 10 2

If a value appears in the row, all subsequent rows should take this value (with dplyr)

I'm just starting to learn R and I'm already facing the first bigger problem.
Let's take the following panel dataset as an example:
N=5
T=3
time<-rep(1:T, times=N)
id<- rep(1:N,each=T)
dummy<- c(0,0,1,1,0,0,0,1,0,0,0,1,0,1,0)
df<-as.data.frame(cbind(id, time,dummy))
id time dummy
1 1 1 0
2 1 2 0
3 1 3 1
4 2 1 1
5 2 2 0
6 2 3 0
7 3 1 0
8 3 2 1
9 3 3 0
10 4 1 0
11 4 2 0
12 4 3 1
13 5 1 0
14 5 2 1
15 5 3 0
I now want the dummy variable for all rows of a cross section to take the value 1 after the 1 for this cross section appears for the first time. So, what I want is:
id time dummy
1 1 1 0
2 1 2 0
3 1 3 1
4 2 1 1
5 2 2 1
6 2 3 1
7 3 1 0
8 3 2 1
9 3 3 1
10 4 1 0
11 4 2 0
12 4 3 1
13 5 1 0
14 5 2 1
15 5 3 1
So I guess I need something like:
df_new<-df %>%
group_by(id) %>%
???
I already tried to set all zeros to NA and use the na.locf function, but it didn't really work.
Anybody got an idea?
Thanks!
Use cummax
df %>%
group_by(id) %>%
mutate(dummy = cummax(dummy))
# A tibble: 15 x 3
# Groups: id [5]
# id time dummy
# <dbl> <dbl> <dbl>
# 1 1 1 0
# 2 1 2 0
# 3 1 3 1
# 4 2 1 1
# 5 2 2 1
# 6 2 3 1
# 7 3 1 0
# 8 3 2 1
# 9 3 3 1
#10 4 1 0
#11 4 2 0
#12 4 3 1
#13 5 1 0
#14 5 2 1
#15 5 3 1
Without additional packages you could do
transform(df, dummy = ave(dummy, id, FUN = cummax))

Grouping rows with mutliple conditions across columns, incl. a sorting, in R/dplyr

In the following dataframe, I have 24 points in the 3D space (2 horizontal locations along X and Y, each with 12 vertical values along Z).
I would like to group together the points vertically if:
they have the same val value and
they follow each other along the Z axis (so two 1 separated by another value would not have the same ID).
And this should be done only for the values beyond the 3 first Z values (which automatically get ID = 1, 2 and 3 respectively, the following ones start at 4).
set.seed(50)
library(dplyr)
mydf = data.frame(X = rep(1, 24), Y = rep(1:2, each = 12),
Z = c(sample(1:12,12,replace=F), sample(4:16,12,replace=F)),
val = c(rep(1:3, 8)))
mydf = mydf %>% group_by(X,Y) %>% arrange(X,Y,Z) %>% data.frame()
# X Y Z val
# 1 1 1 1 3 # In this X-Y location, Z starts at 1
# 2 1 1 2 3
# 3 1 1 3 3
# 4 1 1 4 2
# 5 1 1 5 2
# 6 1 1 6 1
# 7 1 1 7 1
# 8 1 1 8 1
# 9 1 1 9 1
# 10 1 1 10 2
# 11 1 1 11 2
# 12 1 1 12 3
# 13 1 2 4 2 # In this X-Y location, Z starts at 4
# [etc (see below)]
Desired output (note for example that lines 4-5 and 10-11 get a different ID):
rle1 = rle(mydf[4:12,]$val)
# Run Length Encoding
# lengths: int [1:4] 2 4 2 1
# values : int [1:4] 2 1 2 3
rle2 = rle(mydf[4:12 + 12,]$val)
# Run Length Encoding
# lengths: int [1:7] 2 1 1 2 1 1 1
# values : int [1:7] 3 1 2 1 3 1 2
mydf$ID = c(1:3, rep(4:(3+length(rle1$lengths)), rle1$lengths),
1:3, rep(4:(3+length(rle2$lengths)), rle2$lengths))
# X Y Z val ID
# 1 1 1 1 3 1
# 2 1 1 2 3 2
# 3 1 1 3 3 3
# 4 1 1 4 2 4
# 5 1 1 5 2 4
# 6 1 1 6 1 5
# 7 1 1 7 1 5
# 8 1 1 8 1 5
# 9 1 1 9 1 5
# 10 1 1 10 2 6
# 11 1 1 11 2 6
# 12 1 1 12 3 7 # In this X-Y location, I have 7 groups in the end
# 13 1 2 4 2 1
# 14 1 2 5 2 2
# 15 1 2 6 3 3
# 16 1 2 7 3 4
# 17 1 2 9 3 4
# 18 1 2 10 1 5
# 19 1 2 11 2 6
# 20 1 2 12 1 7
# 21 1 2 13 1 7
# 22 1 2 14 3 8
# 23 1 2 15 1 9
# 24 1 2 16 2 10 # In this X-Y location, I have 10 groups in the end
How could I perform this more efficiently, or in one line, and why not with dplyr, supposing this applies for many (X,Y) locations and with always the 3 first Z values (which starts at a different value at each location) followed by a location-dependent number of following ID groups?
I was starting with a try to work with a vector from a conditional subset in dplyr, which is wrong:
mydf %>% group_by(X,Y) %>% arrange(X,Y,Z) %>%
mutate(dummy = mean(rle(val)$values))
Error: error in evaluating the argument 'x' in selecting a method for function 'mean': Error in rle(c(1L, 2L, 3L, 1L, 2L, 3L, 3L, 3L, 1L, 1L, 2L, 2L))$function (x, :
invalid subscript type 'closure'
Thanks!
You can use data.table::rleid on val starting from the 4th element and then add an offset of 3, this could simplify the rle calculation;
library(dplyr); library(data.table)
mydf %>%
group_by(X, Y) %>%
mutate(ID = c(1:3, rleid(val[-(1:3)]) + 3)) %>%
as.data.frame() # for print purpose only
# X Y Z val ID
#1 1 1 1 3 1
#2 1 1 2 3 2
#3 1 1 3 3 3
#4 1 1 4 2 4
#5 1 1 5 2 4
#6 1 1 6 1 5
#7 1 1 7 1 5
#8 1 1 8 1 5
#9 1 1 9 1 5
#10 1 1 10 2 6
#11 1 1 11 2 6
#12 1 1 12 3 7
#13 1 2 4 2 1
#14 1 2 5 2 2
#15 1 2 6 3 3
#16 1 2 7 3 4
#17 1 2 9 3 4
#18 1 2 10 1 5
#19 1 2 11 2 6
#20 1 2 12 1 7
#21 1 2 13 1 7
#22 1 2 14 3 8
#23 1 2 15 1 9
#24 1 2 16 2 10
Or without rleid, use cumsum + diff:
mydf %>% group_by(X, Y) %>% mutate(ID = c(1:3, cumsum(c(4, diff(val[-(1:3)]) != 0))))

Delete rows with value if not only value in group

Somewhat new to R and I find myself needing to delete rows based on multiple criteria. The data frame has 3 columns and I need to delete rows where bid=99 and there are values less than 99 grouping by rid and qid. The desired output at an rid and qid level are bid has multiple values less than 99 or bid=99.
rid qid bid
1 1 5
1 1 6
1 1 99
1 2 6
2 1 7
2 1 99
2 2 2
2 2 3
3 1 7
3 1 8
3 2 1
3 2 99
4 1 2
4 1 6
4 2 1
4 2 2
4 2 99
5 1 99
5 2 99
The expected output...
rid qid bid
1 1 5
1 1 6
1 2 6
2 1 7
2 2 2
2 2 3
3 1 7
3 1 8
3 2 1
4 1 2
4 1 6
4 2 1
4 2 2
5 1 99
5 2 99
Any assistance would be appreciated.
You can use the base R function ave to generate a dropping variable like this:
df$dropper <- with(df, ave(bid, rid, qid, FUN= function(i) i == 99 & length(i) > 1))
ave calculates a function on bid, grouping by rid and qid. The function tests if each element of the grouped bid values i is 99 and if i has a length greater than 1. Also, with is used to reduce typing.
which returns
df
rid qid bid dropper
1 1 1 5 0
2 1 1 6 0
3 1 1 99 1
4 1 2 6 0
5 2 1 7 0
6 2 1 99 1
7 2 2 2 0
8 2 2 3 0
9 3 1 7 0
10 3 1 8 0
11 3 2 1 0
12 3 2 99 1
13 4 1 2 0
14 4 1 6 0
15 4 2 1 0
16 4 2 2 0
17 4 2 99 1
18 5 1 99 0
19 5 2 99 0
then drop the undesired observations with df[dropper == 0, 1:3] which will simultaneously drop the new variable.
If you want to just delete rows where bid = 99 then use dplyr.
library(dplyr)
df <- df %>%
filter(bid != 99)
Where df is your data frame. and != means not equal to
Updated solution using dplyr
df %>%
group_by(rid, qid) %>%
mutate(tempcount = n())%>%
ungroup() %>%
mutate(DropValue =ifelse(bid == 99 & tempcount > 1, 1,0) ) %>%
filter(DropValue == 0) %>%
select(rid,qid,bid)
Here is another option with all and if condition in data.table to subset the rows after grouping by 'rid' and 'qid'
library(data.table)
setDT(df1)[, if(all(bid==99)) .SD else .SD[bid!= 99], .(rid, qid)]
# rid qid bid
# 1: 1 1 5
# 2: 1 1 6
# 3: 1 2 6
# 4: 2 1 7
# 5: 2 2 2
# 6: 2 2 3
# 7: 3 1 7
# 8: 3 1 8
# 9: 3 2 1
#10: 4 1 2
#11: 4 1 6
#12: 4 2 1
#13: 4 2 2
#14: 5 1 99
#15: 5 2 99
Or without using the if
setDT(df1)[df1[, .I[all(bid==99) | bid != 99], .(rid, qid)]$V1]
Here is a solution using dplyr, which is a very expressive framework for this kind of problems.
df <- read.table(text =
" rid qid bid
1 1 5
1 1 6
1 1 99
1 2 6
2 1 7
2 1 99
2 2 2
2 2 3
3 1 7
3 1 8
3 2 1
3 2 99
4 1 2
4 1 6
4 2 1
4 2 2
4 2 99
5 1 99
5 2 99",
header = TRUE, stringsAsFactors = FALSE)
Dplyr verbs allow to express the program in a way that is close to the very terms of your questions:
library(dplyr)
res <-
df %>%
group_by(rid, qid) %>%
filter(!(any(bid < 99) & bid == 99)) %>%
ungroup()
# # A tibble: 15 × 3
# rid qid bid
# <int> <int> <int>
# 1 1 1 5
# 2 1 1 6
# 3 1 2 6
# 4 2 1 7
# 5 2 2 2
# 6 2 2 3
# 7 3 1 7
# 8 3 1 8
# 9 3 2 1
# 10 4 1 2
# 11 4 1 6
# 12 4 2 1
# 13 4 2 2
# 14 5 1 99
# 15 5 2 99
Let's check we get the desired output:
desired_output <- read.table(text =
" rid qid bid
1 1 5
1 1 6
1 2 6
2 1 7
2 2 2
2 2 3
3 1 7
3 1 8
3 2 1
4 1 2
4 1 6
4 2 1
4 2 2
5 1 99
5 2 99",
header = TRUE, stringsAsFactors = FALSE)
identical(as.data.frame(res), desired_output)
# [1] TRUE

Resources