问题
I'm using a particular program that would require me to examine pairs of variables in a text file by specifying the pairs using indices.
For example:
gcta --reml-bivar 1 2 --grm test --pheno test.phen --out test
Where 1 and 2 would correspond to values from the first two columns in a text file. If I had 50 columns and wanted to examine each pair without repetition (1&2, 2&3, 1&3 ... 50), what would be the best way to automate this by looping through this? So essentially the script would be executing the same command but taking in pairs of indices like:
gcta --reml-bivar 1 3 --grm test --pheno test.phen --out test
gcta --reml-bivar 1 4 --grm test --pheno test.phen --out test
... so on and so forth. Thanks!
回答1:
Since you haven't shown us any sample input we're just guessing but if your input is list of numbers (extracted from a file or otherwise) then here's an approach:
$ cat combinations.awk
###################
# Calculate all combinations of a set of strings, see
# https://rosettacode.org/wiki/Combinations#AWK
###################
function get_combs(A,B, i,n,comb) {
## Default value for r is to choose 2 from pool of all elements in A.
## Can alternatively be set on the command line:-
## awk -v r=<number of items being chosen> -f <scriptname>
n = length(A)
if (r=="") r = 2
comb = ""
for (i=1; i <= r; i++) { ## First combination of items:
indices[i] = i
comb = (i>1 ? comb OFS : "") A[indices[i]]
}
B[comb]
## While 1st item is less than its maximum permitted value...
while (indices[1] < n - r + 1) {
## loop backwards through all items in the previous
## combination of items until an item is found that is
## less than its maximum permitted value:
for (i = r; i >= 1; i--) {
## If the equivalently positioned item in the
## previous combination of items is less than its
## maximum permitted value...
if (indices[i] < n - r + i) {
## increment the current item by 1:
indices[i]++
## Save the current position-index for use
## outside this "for" loop:
p = i
break}}
## Put consecutive numbers in the remainder of the array,
## counting up from position-index p.
for (i = p + 1; i <= r; i++) indices[i] = indices[i - 1] + 1
## Print the current combination of items:
comb = ""
for (i=1; i <= r; i++) {
comb = (i>1 ? comb OFS : "") A[indices[i]]
}
B[comb]
}
}
# Input should be a list of strings
{
split($0,A)
delete B
get_combs(A,B)
PROCINFO["sorted_in"] = "@ind_str_asc"
for (comb in B) {
print comb
}
}
.
$ awk -f combinations.awk <<< '1 2 3 4'
1 2
1 3
1 4
2 3
2 4
3 4
.
$ while read -r a b; do
echo gcta --reml-bivar "$a" "$b" --grm test --pheno test.phen --out test
done < <(awk -f combinations.awk <<< '1 2 3 4')
gcta --reml-bivar 1 2 --grm test --pheno test.phen --out test
gcta --reml-bivar 1 3 --grm test --pheno test.phen --out test
gcta --reml-bivar 1 4 --grm test --pheno test.phen --out test
gcta --reml-bivar 2 3 --grm test --pheno test.phen --out test
gcta --reml-bivar 2 4 --grm test --pheno test.phen --out test
gcta --reml-bivar 3 4 --grm test --pheno test.phen --out test
Remove the echo when you're done testing and happy with the output.
In case anyone's reading this and wants permutations instead of combinations:
$ cat permutations.awk
###################
# Calculate all permutations of a set of strings, see
# https://en.wikipedia.org/wiki/Heap%27s_algorithm
function get_perm(A, i, lgth, sep, str) {
lgth = length(A)
for (i=1; i<=lgth; i++) {
str = str sep A[i]
sep = " "
}
return str
}
function swap(A, x, y, tmp) {
tmp = A[x]
A[x] = A[y]
A[y] = tmp
}
function generate(n, A, B, i) {
if (n == 1) {
B[get_perm(A)]
}
else {
for (i=1; i <= n; i++) {
generate(n - 1, A, B)
if ((n%2) == 0) {
swap(A, 1, n)
}
else {
swap(A, i, n)
}
}
}
}
function get_perms(A,B) {
generate(length(A), A, B)
}
###################
# Input should be a list of strings
{
split($0,A)
delete B
get_perms(A,B)
PROCINFO["sorted_in"] = "@ind_str_asc"
for (perm in B) {
print perm
}
}
.
$ awk -f permutations.awk <<< '1 2 3 4'
1 2 3 4
1 2 4 3
1 3 2 4
1 3 4 2
1 4 2 3
1 4 3 2
2 1 3 4
2 1 4 3
2 3 1 4
2 3 4 1
2 4 1 3
2 4 3 1
3 1 2 4
3 1 4 2
3 2 1 4
3 2 4 1
3 4 1 2
3 4 2 1
4 1 2 3
4 1 3 2
4 2 1 3
4 2 3 1
4 3 1 2
4 3 2 1
Both of the above use GNU awk for sorted_in to sort the output. If you don't have GNU awk you can still use the scripts as-is and if you need to sort the output then pipe it to sort.
回答2:
If I understand you correctly and you don't need pairs looks like '1 1', '2 2', ... and '1 2', '2 1' ... try this script
#!/bin/bash
for i in $(seq 1 49);
do
for j in $(seq $(($i + 1)) 50);
do gcta --reml-bivar "$i $j" --grm test --pheno test.phen --out test
done;
done;
回答3:
1 and 2 would correspond to values from the first two columns in a text file.
each pair without repetition
So let's walk through this process:
- We repeat the first column from the file times the file length
- We repeat each value (each line) from the second column from the file times the file length
- We join the repeated columns -> we have all combinations
- We need to filter "repetitions", we can just join the file with the original file and filter out repeating columns
- So we get each pair without repetitions.
- Then we just read the file line by line.
The script:
# create an input file cause you didn't provide any
cat << EOF > in.txt
1 a
2 b
3 c
4 d
EOF
# get file length
inlen=$(<in.txt wc -l)
# join the columns
paste -d' ' <(
# repeat the first column inlen times
# https://askubuntu.com/questions/521465/how-can-i-repeat-the-content-of-a-file-n-times
seq "$inlen" |
xargs -I{} cut -d' ' -f1 in.txt
) <(
# repeat each line inlen times
# https://unix.stackexchange.com/questions/81904/repeat-each-line-multiple-times
awk -v IFS=' ' -v v="$inlen" '{for(i=0;i<v;i++)print $2}' in.txt
) |
# filter out repetitions - ie. filter original lines from the file
sort |
comm --output-delimiter='' -3 <(sort in.txt) - |
# read the file line by line
while read -r one two; do
echo "$one" "$two"
done
will output:
1 b
1 c
1 d
2 a
2 c
2 d
3 a
3 b
3 d
4 a
4 b
4 c
回答4:
#!/bin/bash
#set the length of the combination depending the
#user's choice
eval rg+=({1..$2})
#the code builds the script and runs it (eval)
eval `
#Character range depending on user selection
for i in ${rg[@]} ; do
echo "for c$i in {1..$1} ;do "
done ;
#Since the script is based on a code that brings
#all possible combinations even with duplicates -
#this is where the deduplication
#prevention conditioning set by (the script writes
#the conditioning code)
op1=$2
op2=$(( $2 - 1 ))
echo -n "if [ 1 == 1 ] "
while [ $op1 -gt 1 ] ; do
echo -n \&\& [ '$c'$op1 != '$c'$op2 ]' '
op2=$(( op2 -1 )
if [ $op2 == 0 ] ; then
op1=$(( op1 - 1 ))
op2=$(( op1 - 1 ))
fi
done ;
echo ' ; then'
echo -n "echo "
for i in ${rg[@]} ;
do
echo -n '$c'$i
done ;
echo \;
echo fi\;
for i in ${rg[@]} ; do
echo 'done ;'
done;`
example: range length
$ ./combs.bash '{1..2} {a..c} \$ \#' 4
12ab$
12ab#
12acb
12ac$
12ac#
12a$b
12a$c
12a$#
12a#b
12a#c
12a#$
..........
回答5:
#!/bin/bash
len=$2
eval c=($1)
per()
{
((`grep -Poi '[^" ".]'<<<$2|sort|uniq|wc -l` < $((len - ${1}))))&&{ return;}
(($1 == 0))&&{ echo $2;return;}
for i in ${c[@]} ; do
per "$((${1} - 1 ))" "$2 $i"
done
}
per "$2" ""
#example
$ ./neto '{0..3} {a..d} \# \!' 7
0 1 2 3 a b c
0 1 2 3 a b d
0 1 2 3 a b #
0 1 2 3 a b !
0 1 2 3 a c b
0 1 2 3 a c d
0 1 2 3 a c #
0 1 2 3 a c !
0 1 2 3 a d b
...
来源：https://stackoverflow.com/questions/56911991/how-would-i-loop-over-pairs-of-values-without-repetition-in-bash