# Hello
# I have a question regarding pairwise calculations of a matrix using a
"for-loop."
# Below I have a matrix "X" with 8 columns. These are genotypic data so
Column1 & Column2 is
# a unit, Column3 & Column4 is a unit, Column5 & Column6 is a unit, and
Coulmn7 & 8 is a unit.
# I have a loop designed to calculate the number of times an individual in
Column"i" & Column"j"
# has the same value and the same individual has two values that are the
same in Column"k" & Column"l" .
# I have another seires of code that adds a 2 in the poper location of a
data frame called "result.df".
# I have written a loop that accomplishes this "pair of columns" pairwise
comparison, but it also compares
# some of the "pairs of Columns" to themselves. Is there a way to get around
this?
# creation of the data matrix
c1<- c(1,4,3,2,4,1,3,2,4,3)
c2<- c(2,4,3,4,4,3,4,1,3,2)
c3<- c(1,3,2,4,4,3,4,4,2,2)
c4<- c(2,3,2,3,1,3,2,4,4,3)
c5<- c(1,2,1,1,2,2,2,3,2,1)
c6<- c(3,2,4,3,1,1,2,3,3,4)
c7<- c(1,2,1,2,3,2,3,2,1,2)
c8<- c(1,2,2,3,2,3,3,4,1,2)
X<-cbind(c1,c2,c3,c4,c5,c6,c7,c8)
X
## Creation of the result dataframe
result<- matrix(0,16,2)
result.df<-data.frame(result)
result.df[,1] <- c(1,1,1,1,2,2,2,2,3,3,3,3,4,4,4,4)
result.df[,2] <- c(1,2,3,4,1,2,3,4,1,2,3,4,1,2,3,4)
names(result.df)[1]<-"L(A)a(i)"
names(result.df)[2]<-"L(B)a(j)"
result.df
### The loop written to find Double Homozygotes
for (a in seq(1,(ncol(X)-3), by=2)){
for (b in seq(3,(ncol(X)-1), by=2)){
for (i in a){
j <- a+1
for (k in b){
l <- b+1
match.rows <- ((X [,i] == X [, j] ) & ( X [,k] == X [, l]))
double_homo_i <- X [match.rows, i]
double_homo_k <- X [match.rows, k]
double_homo<- cbind( double_homo_i, double_homo_k)
double_homo.df<-data.frame(double_homo,Counts=2)
names(double_homo.df)[1]<-"L(A)a(i)"
names(double_homo.df)[2]<- "L(B)a(j)"
# Below takes each round throught he loop and puts in the result.dfdataframe.
count<-double_homo.df
almost.df<-aggregate(count$Counts, list(count[,1],count[,2]),
FUN=sum)
temp<-order(almost.df$Group.1)
final.df<-almost.df[temp,]
names(final.df)[1]<-"L(A)a(i)"
names(final.df)[2]<-"L(B)a(j)"
result.df<-merge(result.df,final.df,by=c("L(A)a(i)","L(B)a(j)"), all.x=T)
}
}
}
}
# here is the result I get
result.df
# L(A)a(i) L(B)a(j) C1C2~C3C4 C1C2~C5C6 C1C2~C7C8 C3C4~C3C4 C3C4~C5C6
C3C4~C7C8 C5C6~C3C4 C5C6~C5C6 C5C6~C7C8
# 1 1 1 NA NA NA
NA NA NA NA
NA NA
# 2 1 2 NA NA
NA NA NA NA
NA NA NA
# 3 1 3 NA NA
NA NA NA NA
NA NA NA
# 4 1 4 NA NA
NA NA NA NA
NA NA NA
# 5 2 1 NA NA
NA NA NA NA
NA NA NA
# 6 2 2 NA NA
NA 2 NA NA
NA 4 2
# 7 2 3 NA NA
NA NA NA NA
2 NA 2
# 8 2 4 NA NA
NA NA NA NA
NA NA NA
# 9 3 1 NA NA
NA NA NA NA NA
NA NA
# 10 3 2 2 NA NA
NA 2 2
NA NA NA
# 11 3 3 NA NA
NA 4 NA NA
NA 2 NA
# 12 3 4 NA NA
NA NA NA NA
2 NA NA
# 13 4 1 NA NA
NA NA NA NA
NA NA NA
# 14 4 2 NA 2
2 NA NA NA
NA NA NA
# 15 4 3 2 NA
NA NA 2 NA
NA NA NA
# 16 4 4 NA NA
NA 2 NA NA
NA NA NA
# Here is the Result I am looking for.
L(A)a(i) L(B)a(j) C1C2~C3C4 C1C2~C5C6 C1C2~C7C8 C3C4~C5C6 C3C4~C7C8
C5C6~C7C8
# 1 1 1 NA NA NA
NA NA NA
# 2 1 2 NA NA
NA NA NA NA
# 3 1 3 NA NA
NA NA NA NA
# 4 1 4 NA NA
NA NA NA NA
# 5 2 1 NA NA
NA NA NA NA
# 6 2 2 NA NA
NA NA NA 2
# 7 2 3 NA NA
NA NA NA 2
# 8 2 4 NA NA
NA NA NA NA
# 9 3 1 NA NA NA
NA NA NA
# 10 3 2 2 NA
NA 2 2 NA
# 11 3 3 NA NA
NA NA NA NA
# 12 3 4 NA NA
NA NA NA NA
# 13 4 1 NA NA
NA NA NA NA
# 14 4 2 NA 2 2
NA NA NA
# 15 4 3 2 NA
NA 2 NA NA
# 16 4 4 NA NA
NA NA NA NA
# Any help or ideas would be greatly appreciated
# Thanks in advance
# Luke Neraas
# [EMAIL PROTECTED]
# University of Alaska Fairbanks
# School of Fisheries and Ocean Sciences
# 11120 Glacier Highway
# UAF Fisheries Division
# Juneau, AK 99801
[[alternative HTML version deleted]]
______________________________________________
[email protected] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
