Warning message: NAs introduced by coercion

df4 <- read.csv(file = "mydata.csv", header = TRUE)
require(SNPRelate)
library(gdsfmt)
myd <- df4
myd <- df4
names(myd)[-1]

myd[,1]

sample.id <- names(myd)[-1]
snp.id <- myd[,1]
snp.position <- 1:length(snp.id) # not needed for ibs
snp.chromosome <- rep(1, each=length(snp.id)) # not needed for ibs
snp.allele <- rep("A/G", length(snp.id)) # not needed for ibs

genod <- myd[,-1]
genod[is.na(genod)] <- 3
genod[genod=="0"] <- 0
genod[genod=="1"] <- 2
genod2 <- as.matrix(genod)
head(genod2)

class(genod2) <- "numeric"

head(genod2)

class(genod2) <- "numeric"
class(genod2)

filn <-"simTunesian.gds"
snpgdsCreateGeno(filn, genmat = genod,

Dear Meriam

Your csv file did not come through as attachments are stripped unless of
certain types and you post is very hard to read since you are posting in
HTML. Try renaming the file to ????.txt and set your mailer to send
plain text then people may be able to help you better.

Michael

On 08/01/2019 15:35, N Meriam wrote:

I see...
Here's a portion of what my data looks like (csv file attached).
I run again and here are the results:

df4 <- read.csv(file = "mydata.csv", header = TRUE)

require(SNPRelate)> library(gdsfmt)> myd <- df4> myd <- df4> names(myd)[-1][1] "marker" "X88"    "X9"     "X17"    "X25"

myd[,1][1]  3  4  5  6  8 10

# the data must be 0,1,2 with 3 as missing so you have r> sample.id <- names(myd)[-1]> snp.id <- myd[,1]> snp.position <- 1:length(snp.id) # not needed for ibs> snp.chromosome <- rep(1, each=length(snp.id)) # not needed for ibs> snp.allele <- rep("A/G", length(snp.id)) # not needed for ibs> # genotype data must have - in 3> genod <- myd[,-1]> genod[is.na(genod)] <- 3> genod[genod=="0"] <- 0> genod[genod=="1"] <- 2

genod2 <- as.matrix(genod)> head(genod2)     marker                        X88 X9  X17 X25

[1,] "100023173|F|0-47:G>A-47:G>A" "0" "3" "3" "3"
[2,] "1043336|F|0-7:A>G-7:A>G"     "2" "0" "3" "0"
[3,] "1212218|F|0-49:A>G-49:A>G"   "0" "0" "0" "0"
[4,] "1019554|F|0-14:T>C-14:T>C"   "0" "0" "3" "0"
[5,] "100024550|F|0-16:G>A-16:G>A" "3" "3" "3" "3"
[6,] "1106702|F|0-8:C>A-8:C>A"     "0" "0" "0" "0"

class(genod2) <- "numeric"Warning message:In class(genod2) <- "numeric" : NAs introduced by coercion> head(genod2)

  marker X88 X9 X17 X25
[1,]     NA   0  3   3   3
[2,]     NA   2  0   3   0
[3,]     NA   0  0   0   0
[4,]     NA   0  0   3   0
[5,]     NA   3  3   3   3
[6,]     NA   0  0   0   0

class(genod2) <- "numeric"> class(genod2)[1] "matrix"

# read data > filn <-"simTunesian.gds"> snpgdsCreateGeno(filn, genmat = genod,+                  sample.id = sample.id, snp.id = snp.id,+                  snp.chromosome = snp.chromosome,+                  snp.position = snp.position,+                  snp.allele = snp.allele, snpfirstdim=TRUE)Error in snpgdsCreateGeno(filn, genmat = genod, sample.id = sample.id,  :

   is.matrix(genmat) is not TRUE

Thanks,
Meriam

On Tue, Jan 8, 2019 at 9:02 AM PIKAL Petr <petr.pikal at precheza.cz> wrote:

Hi

see in line

-----Original Message-----
From: R-help <r-help-bounces at r-project.org> On Behalf Of N Meriam
Sent: Tuesday, January 8, 2019 3:08 PM
To: r-help at r-project.org
Subject: [R] Warning message: NAs introduced by coercion

Dear all,

I have a .csv file called df4. (15752 obs. of 264 variables).
I apply this code but couldn't continue further other analyses, a warning
message keeps coming up. Then, I want to determine max and min
similarity values,
heat map plot, cluster...etc

require(SNPRelate)
library(gdsfmt)
myd <- read.csv(file = "df4.csv", header = TRUE)
names(myd)[-1]

myd[,1]

myd[1:10, 1:10]

  # the data must be 0,1,2 with 3 as missing so you have r

sample.id <- names(myd)[-1]
snp.id <- myd[,1]
snp.position <- 1:length(snp.id) # not needed for ibs
snp.chromosome <- rep(1, each=length(snp.id)) # not needed for ibs
snp.allele <- rep("A/G", length(snp.id)) # not needed for ibs

# genotype data must have - in 3

genod <- myd[,-1]
genod[is.na(genod)] <- 3
genod[genod=="0"] <- 0
genod[genod=="1"] <- 2
genod[1:10,1:10]
genod <- as.matrix(genod)

matrix can have only one type of data so you probaly changed it to
character by such construction.

class(genod) <- "numeric"

This tries to change all "numeric" values to numbers but if it cannot it
sets it to NA.

something like

head(iris)

   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
1          5.1         3.5          1.4         0.2  setosa
2          4.9         3.0          1.4         0.2  setosa
3          4.7         3.2          1.3         0.2  setosa
4          4.6         3.1          1.5         0.2  setosa
5          5.0         3.6          1.4         0.2  setosa
6          5.4         3.9          1.7         0.4  setosa

ir <-head(iris)
irm <- as.matrix(ir)
head(irm)

   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
1 "5.1"        "3.5"       "1.4"        "0.2"       "setosa"
2 "4.9"        "3.0"       "1.4"        "0.2"       "setosa"
3 "4.7"        "3.2"       "1.3"        "0.2"       "setosa"
4 "4.6"        "3.1"       "1.5"        "0.2"       "setosa"
5 "5.0"        "3.6"       "1.4"        "0.2"       "setosa"
6 "5.4"        "3.9"       "1.7"        "0.4"       "setosa"

class(irm) <- "numeric"

Warning message:
In class(irm) <- "numeric" : NAs introduced by coercion

head(irm)

   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
1          5.1         3.5          1.4         0.2      NA
2          4.9         3.0          1.4         0.2      NA
3          4.7         3.2          1.3         0.2      NA
4          4.6         3.1          1.5         0.2      NA
5          5.0         3.6          1.4         0.2      NA
6          5.4         3.9          1.7         0.4      NA

Cheers
Petr

*Warning message:In class(genod) <- "numeric" : NAs introduced by

coercion*

Maybe I could illustrate more with details so I can be more specific?
Please, let me know.

I would appreciate your help.
Thanks,
Meriam

[[alternative HTML version deleted]]

--
Michael
http://www.dewey.myzen.co.uk/home.html