randomly insert sequence of missing data (NAs) [duplicate] - r

I have a complete dataframe. I want to 20% of the values in the dataframe to be replaced by NAs to simulate random missing data.
A <- c(1:10)
B <- c(11:20)
C <- c(21:30)
df<- data.frame(A,B,C)
Can anyone suggest a quick way of doing that?

df <- data.frame(A = 1:10, B = 11:20, c = 21:30)
head(df)
## A B c
## 1 1 11 21
## 2 2 12 22
## 3 3 13 23
## 4 4 14 24
## 5 5 15 25
## 6 6 16 26
as.data.frame(lapply(df, function(cc) cc[ sample(c(TRUE, NA), prob = c(0.85, 0.15), size = length(cc), replace = TRUE) ]))
## A B c
## 1 1 11 21
## 2 2 12 22
## 3 3 13 23
## 4 4 14 24
## 5 5 NA 25
## 6 6 16 26
## 7 NA 17 27
## 8 8 18 28
## 9 9 19 29
## 10 10 20 30
It's a random process, so it might not give 15% every time.

You can unlist the data.frame and then take a random sample, then put back in a data.frame.
df <- unlist(df)
n <- length(df) * 0.15
df[sample(df, n)] <- NA
as.data.frame(matrix(df, ncol=3))
It can be done a bunch of different ways using sample().

If you are in the mood to use purrr instead of lapply, you can also do it like this:
> library(purrr)
> df <- data.frame(A = 1:10, B = 11:20, C = 21:30)
> df
A B C
1 1 11 21
2 2 12 22
3 3 13 23
4 4 14 24
5 5 15 25
6 6 16 26
7 7 17 27
8 8 18 28
9 9 19 29
10 10 20 30
> map_df(df, function(x) {x[sample(c(TRUE, NA), prob = c(0.8, 0.2), size = length(x), replace = TRUE)]})
# A tibble: 10 x 3
A B C
<int> <int> <int>
1 1 11 21
2 2 12 22
3 NA 13 NA
4 4 14 NA
5 5 15 25
6 6 16 26
7 7 17 27
8 8 NA 28
9 9 19 29
10 10 20 30

Same result, using binomial distribution:
dd=dim(df)
nna=20/100 #overall
df1<-df
df1[matrix(rbinom(prod(dd), size=1,prob=nna)==1,nrow=dd[1])]<-NA
df1

May i suggest a first function (ggNAadd) designed to do this, and improve it with a second function providing graphical distribution of the NAs created (ggNA)
What is neat is the possibility to input either a proportion of a fixed number of NAs.
ggNAadd = function(data, amount, plot=F){
temp <- data
amount2 <- ifelse(amount<1, round(prod(dim(data))*amount), amount)
if (amount2 >= prod(dim(data))) stop("exceeded data size")
for (i in 1:amount2) temp[sample.int(nrow(temp), 1), sample.int(ncol(temp), 1)] <- NA
if (plot) print(ggNA(temp))
return(temp)
}
And the plotting function:
ggNA = function(data, alpha=0.5){
require(ggplot2)
DF <- data
if (!is.matrix(data)) DF <- as.matrix(DF)
to.plot <- cbind.data.frame('y'=rep(1:nrow(DF), each=ncol(DF)),
'x'=as.logical(t(is.na(DF)))*rep(1:ncol(DF), nrow(DF)))
size <- 20 / log( prod(dim(DF)) ) # size of point depend on size of table
g <- ggplot(data=to.plot) + aes(x,y) +
geom_point(size=size, color="red", alpha=alpha) +
scale_y_reverse() + xlim(1,ncol(DF)) +
ggtitle("location of NAs in the data frame") +
xlab("columns") + ylab("lines")
pc <- round(sum(is.na(DF))/prod(dim(DF))*100, 2) # % NA
print(paste("percentage of NA data: ", pc))
return(g)
}
Which gives (using ggplot2 as graphical output):
ggNAadd(df, amount=0.20, plot=TRUE)
## [1] "percentage of NA data: 20"
## A B c
## 1 1 11 21
## 2 2 12 22
## 3 3 13 23
## 4 4 NA 24
## ..
Of course, as mentioned earlier, if you ask too many NAs the actual percentage will drop because of repetitions.

A mutate_all approach:
df %>%
dplyr::mutate_all(~ifelse(sample(c(TRUE, FALSE), size = length(.), replace = TRUE, prob = c(0.8, 0.2)),
as.character(.), NA))

Related

Replace values in one dataframe with another thats not NA

I have two dataframes A and B, that share have the same column names and the same first column (Location)
A <- data.frame("Location" = 1:3, "X" = c(21,15, 7), "Y" = c(41,5, 5), "Z" = c(12,103, 88))
B <- data.frame("Location" = 1:3, "X" = c(NA,NA, 14), "Y" = c(50,8, NA), "Z" = c(NA,14, 12))
How do i replace the values in dataframe A with the values from B if the value in B is not NA?
Thanks.
We can use coalesce
library(dplyr)
A %>%
mutate(across(-Location, ~ coalesce(B[[cur_column()]], .)))
-output
# Location X Y Z
#1 1 21 50 12
#2 2 15 8 14
#3 3 14 5 12
Here's an answer in base R:
i <- which(!is.na(B),arr.ind = T)
A[i] <- B[i]
A
Location X Y Z
1 1 21 50 12
2 2 15 8 14
3 3 14 5 12
One option with fcoalesce from data.table pakcage
list2DF(Map(data.table::fcoalesce,B,A))
gives
Location X Y Z
1 1 21 50 12
2 2 15 8 14
3 3 14 5 12

Adding Proportionate Na's in a column [duplicate]

I have a complete dataframe. I want to 20% of the values in the dataframe to be replaced by NAs to simulate random missing data.
A <- c(1:10)
B <- c(11:20)
C <- c(21:30)
df<- data.frame(A,B,C)
Can anyone suggest a quick way of doing that?
df <- data.frame(A = 1:10, B = 11:20, c = 21:30)
head(df)
## A B c
## 1 1 11 21
## 2 2 12 22
## 3 3 13 23
## 4 4 14 24
## 5 5 15 25
## 6 6 16 26
as.data.frame(lapply(df, function(cc) cc[ sample(c(TRUE, NA), prob = c(0.85, 0.15), size = length(cc), replace = TRUE) ]))
## A B c
## 1 1 11 21
## 2 2 12 22
## 3 3 13 23
## 4 4 14 24
## 5 5 NA 25
## 6 6 16 26
## 7 NA 17 27
## 8 8 18 28
## 9 9 19 29
## 10 10 20 30
It's a random process, so it might not give 15% every time.
You can unlist the data.frame and then take a random sample, then put back in a data.frame.
df <- unlist(df)
n <- length(df) * 0.15
df[sample(df, n)] <- NA
as.data.frame(matrix(df, ncol=3))
It can be done a bunch of different ways using sample().
If you are in the mood to use purrr instead of lapply, you can also do it like this:
> library(purrr)
> df <- data.frame(A = 1:10, B = 11:20, C = 21:30)
> df
A B C
1 1 11 21
2 2 12 22
3 3 13 23
4 4 14 24
5 5 15 25
6 6 16 26
7 7 17 27
8 8 18 28
9 9 19 29
10 10 20 30
> map_df(df, function(x) {x[sample(c(TRUE, NA), prob = c(0.8, 0.2), size = length(x), replace = TRUE)]})
# A tibble: 10 x 3
A B C
<int> <int> <int>
1 1 11 21
2 2 12 22
3 NA 13 NA
4 4 14 NA
5 5 15 25
6 6 16 26
7 7 17 27
8 8 NA 28
9 9 19 29
10 10 20 30
Same result, using binomial distribution:
dd=dim(df)
nna=20/100 #overall
df1<-df
df1[matrix(rbinom(prod(dd), size=1,prob=nna)==1,nrow=dd[1])]<-NA
df1
May i suggest a first function (ggNAadd) designed to do this, and improve it with a second function providing graphical distribution of the NAs created (ggNA)
What is neat is the possibility to input either a proportion of a fixed number of NAs.
ggNAadd = function(data, amount, plot=F){
temp <- data
amount2 <- ifelse(amount<1, round(prod(dim(data))*amount), amount)
if (amount2 >= prod(dim(data))) stop("exceeded data size")
for (i in 1:amount2) temp[sample.int(nrow(temp), 1), sample.int(ncol(temp), 1)] <- NA
if (plot) print(ggNA(temp))
return(temp)
}
And the plotting function:
ggNA = function(data, alpha=0.5){
require(ggplot2)
DF <- data
if (!is.matrix(data)) DF <- as.matrix(DF)
to.plot <- cbind.data.frame('y'=rep(1:nrow(DF), each=ncol(DF)),
'x'=as.logical(t(is.na(DF)))*rep(1:ncol(DF), nrow(DF)))
size <- 20 / log( prod(dim(DF)) ) # size of point depend on size of table
g <- ggplot(data=to.plot) + aes(x,y) +
geom_point(size=size, color="red", alpha=alpha) +
scale_y_reverse() + xlim(1,ncol(DF)) +
ggtitle("location of NAs in the data frame") +
xlab("columns") + ylab("lines")
pc <- round(sum(is.na(DF))/prod(dim(DF))*100, 2) # % NA
print(paste("percentage of NA data: ", pc))
return(g)
}
Which gives (using ggplot2 as graphical output):
ggNAadd(df, amount=0.20, plot=TRUE)
## [1] "percentage of NA data: 20"
## A B c
## 1 1 11 21
## 2 2 12 22
## 3 3 13 23
## 4 4 NA 24
## ..
Of course, as mentioned earlier, if you ask too many NAs the actual percentage will drop because of repetitions.
A mutate_all approach:
df %>%
dplyr::mutate_all(~ifelse(sample(c(TRUE, FALSE), size = length(.), replace = TRUE, prob = c(0.8, 0.2)),
as.character(.), NA))

repeat the nth element every other n in a sequence

the original vector x:
x = 1:20
and what i look for is a vector y that repeats the n-th element in x every other n, for instance, when n=4:
n = 4
y = c(1,2,3,4,4,5,6,7,8,8,9,10,11,12,12,13,14,15,16,16,17,18,19,20,20)
i'm actually doing it for matrices and i think it relates to the use of apply here when margin=2 but couldn't figure it out right off the bat,
could anyone kindly show me a quick solution?
We can also use
v1 <- rep(1, length(x))
v1[c(FALSE, FALSE, FALSE, TRUE)] <- 2
rep(x, v1)
#[1] 1 2 3 4 4 5 6 7 8 8 9 10 11 12 12 13 14 15 16 16 17 18 19 20 20
Or as #MichaelChirico commented, the 2nd line of code can be made more general with
v1[seq_along(v1) %% n == 0L] = 2
Or in a one-liner with ifelse (from #JonathanCarroll's comments)
rep(x, ifelse(seq_along(x) %% n, 1, 2))
Indeed matrices are the way to go
duplast = function(M) rbind(M, M[nrow(M), ])
c(duplast(matrix(x, nrow = 4L)))
# [1] 1 2 3 4 4 5 6 7 8 8 9 10 11 12 12 13 14 15 16 16 17 18 19 20
# [25] 20
If you wanted to use apply:
c(apply(matrix(x, nrow = 4L), 2L, function(C) c(C, C[length(C)])))

R data frame manipulation

Suppose I have a data frame that looks like this.
# start end motif
# 2 6 a
# 10 15 b
# 30 35 c
How would I create a data frame that fills in the remaining start and end locations like so up to a certain number Max_end:
Max_end <- 33
# start end motif
# 0 2 na # <- 0-2 are filled in because it is not in the original data frame
# 2 6 a # <- 2-6 are in the original
# 6 10 na # <- 6-10 is not
# 10 15 b # <- 10-15 is
# 15 30 na # and so on
# 30 33 c
And further, calculates the distance between the start and end locations and creates a one column data frame.
# Length motif
# 2 na
# 4 a
# 4 na
# 5 b
# 15 na
# 3 c
Currently this is how i am doing it: It is very inefficient
library(data.table)
library(stringi)
f <- fread('ABC.txt',header=F,skip=1)$V1
f <- paste(f, collapse = "")
motifs = c('GATC', 'CTGCAG', 'ACCACC', 'CC(A|T)GG', 'CCAC.{8}TGA(C|T)')
v <- na.omit(data.frame(do.call(rbind, lapply(stri_locate_all_regex(f, motifs), unlist))))
v <- v[order(v[,1]),]
v2difference <- "blah"
for(i in 2:nrow(v)){
if(v[i,1] > v[i-1,2]+2){v2difference[i] <- v[i,1]-v[i-1,2]-2}
}
v2difference[1] <- v[1,1]
v2 <- data.frame(Order=seq(1, 2*nrow(v), 2),Lengths=matrix(v2difference, ncol = 1),Motifs="na")
v1 <- data.frame(Order=seq(2, 2*nrow(v), 2),Lengths=(v$end-v$start+1),Motifs=na.omit(unlist(stri_extract_all_regex(f,motifs))))
V <- data.frame(Track=1,rbind(v1,v2))
V <- V[order(V$Order),]
B <- V[,!(names(V) %in% "Order")]
Max_end <- 33
breaks <- c(0, t(as.matrix(dat[,1:2])), Max_end) # get endpoints
breaks <- breaks[breaks <= Max_end]
merge(dat, data.frame(start=breaks[-length(breaks)], end=breaks[-1]), all=T)
# start end motif
# 1 0 2 <NA>
# 2 2 6 a
# 3 6 10 <NA>
# 4 10 15 b
# 5 15 30 <NA>
# 6 30 33 <NA>
# 7 30 35 c
To specify a start and endpoint, you could do
Max_end <- 33
Max_start <- 10
breaks <- unique(c(Max_start, t(as.matrix(dat[,1:2])), Max_end))
breaks <- breaks[breaks <= Max_end & breaks >= Max_start]
merge(dat, data.frame(start=breaks[-length(breaks)], end=breaks[-1]), all.y=T)
# start end motif
# 1 10 15 b
# 2 15 30 <NA>
# 3 30 33 <NA>
Note: this doesn't include "c" in the shortened final interval, you would need to decide if that values gets included or not when the interval changes.

Randomly insert NAs into dataframe proportionaly

I have a complete dataframe. I want to 20% of the values in the dataframe to be replaced by NAs to simulate random missing data.
A <- c(1:10)
B <- c(11:20)
C <- c(21:30)
df<- data.frame(A,B,C)
Can anyone suggest a quick way of doing that?
df <- data.frame(A = 1:10, B = 11:20, c = 21:30)
head(df)
## A B c
## 1 1 11 21
## 2 2 12 22
## 3 3 13 23
## 4 4 14 24
## 5 5 15 25
## 6 6 16 26
as.data.frame(lapply(df, function(cc) cc[ sample(c(TRUE, NA), prob = c(0.85, 0.15), size = length(cc), replace = TRUE) ]))
## A B c
## 1 1 11 21
## 2 2 12 22
## 3 3 13 23
## 4 4 14 24
## 5 5 NA 25
## 6 6 16 26
## 7 NA 17 27
## 8 8 18 28
## 9 9 19 29
## 10 10 20 30
It's a random process, so it might not give 15% every time.
You can unlist the data.frame and then take a random sample, then put back in a data.frame.
df <- unlist(df)
n <- length(df) * 0.15
df[sample(df, n)] <- NA
as.data.frame(matrix(df, ncol=3))
It can be done a bunch of different ways using sample().
If you are in the mood to use purrr instead of lapply, you can also do it like this:
> library(purrr)
> df <- data.frame(A = 1:10, B = 11:20, C = 21:30)
> df
A B C
1 1 11 21
2 2 12 22
3 3 13 23
4 4 14 24
5 5 15 25
6 6 16 26
7 7 17 27
8 8 18 28
9 9 19 29
10 10 20 30
> map_df(df, function(x) {x[sample(c(TRUE, NA), prob = c(0.8, 0.2), size = length(x), replace = TRUE)]})
# A tibble: 10 x 3
A B C
<int> <int> <int>
1 1 11 21
2 2 12 22
3 NA 13 NA
4 4 14 NA
5 5 15 25
6 6 16 26
7 7 17 27
8 8 NA 28
9 9 19 29
10 10 20 30
Same result, using binomial distribution:
dd=dim(df)
nna=20/100 #overall
df1<-df
df1[matrix(rbinom(prod(dd), size=1,prob=nna)==1,nrow=dd[1])]<-NA
df1
May i suggest a first function (ggNAadd) designed to do this, and improve it with a second function providing graphical distribution of the NAs created (ggNA)
What is neat is the possibility to input either a proportion of a fixed number of NAs.
ggNAadd = function(data, amount, plot=F){
temp <- data
amount2 <- ifelse(amount<1, round(prod(dim(data))*amount), amount)
if (amount2 >= prod(dim(data))) stop("exceeded data size")
for (i in 1:amount2) temp[sample.int(nrow(temp), 1), sample.int(ncol(temp), 1)] <- NA
if (plot) print(ggNA(temp))
return(temp)
}
And the plotting function:
ggNA = function(data, alpha=0.5){
require(ggplot2)
DF <- data
if (!is.matrix(data)) DF <- as.matrix(DF)
to.plot <- cbind.data.frame('y'=rep(1:nrow(DF), each=ncol(DF)),
'x'=as.logical(t(is.na(DF)))*rep(1:ncol(DF), nrow(DF)))
size <- 20 / log( prod(dim(DF)) ) # size of point depend on size of table
g <- ggplot(data=to.plot) + aes(x,y) +
geom_point(size=size, color="red", alpha=alpha) +
scale_y_reverse() + xlim(1,ncol(DF)) +
ggtitle("location of NAs in the data frame") +
xlab("columns") + ylab("lines")
pc <- round(sum(is.na(DF))/prod(dim(DF))*100, 2) # % NA
print(paste("percentage of NA data: ", pc))
return(g)
}
Which gives (using ggplot2 as graphical output):
ggNAadd(df, amount=0.20, plot=TRUE)
## [1] "percentage of NA data: 20"
## A B c
## 1 1 11 21
## 2 2 12 22
## 3 3 13 23
## 4 4 NA 24
## ..
Of course, as mentioned earlier, if you ask too many NAs the actual percentage will drop because of repetitions.
A mutate_all approach:
df %>%
dplyr::mutate_all(~ifelse(sample(c(TRUE, FALSE), size = length(.), replace = TRUE, prob = c(0.8, 0.2)),
as.character(.), NA))

Resources