Related
I am trying to change values in the following list:
A 0.702
B 0.868
C 3.467
D 2.152
If the second column is less than 0.5 I would like to change to -2, between 0.5-1 to -1, between 1-1.5 to 1 and if > 1.5 then to 2.
When I try the following:
awk '$2<0.9 || $2>2' | awk '{if ($2 < 0.5) print $1,-2;}{if($2>0.5 || $2<1) print $1,-1;}{if($2>1 || $2<1.5) print $1,1;}{if($2>2) print $1,2;}'
I get the following:
A -1
A 1
B -1
B 1
C 1
C 2
D 1
D 2
I know I am missing something but for the life of me I can't figure out what - any help gratefully recieved.
If you have multiple if statements and the current value can match multiple statements, you can print multiple outputs.
If you only want to print the output of the first match, you would have to prevent running the if statements that follow.
You can use a single awk and define non overlapping matches with greater than and && lower than.
Note that using only > and < you will not for example 0.5
awk '{
if($2 < 0.5) print($1, -2)
if($2 > 0.5 && $2<1) print($1,-1)
if($2 > 1 && $2<1.5) print($1, 1)
if($2 > 1.5) print($1 ,2)
}
' file
Output
A -1
B -1
C 2
D 2
With your shown samples only. Adding one more solution with using ternary operators for condition checking(for Fun :) ).
awk '{print (NF?($2>1.5?($1 OFS 2):($2>1?($1 OFS 1):($2>0.5?($1 OFS "-1"):($1 OFS "-2")))):"")}' Input_file
Better readable form of above awk code. Since its a one-liner so breaking it up into multi form for better readability here.
awk '
{
print \
(\
NF\
?\
($2>1.5\
?\
($1 OFS 2)\
:\
($2>1\
?\
($1 OFS 1)\
:\
($2>0.5\
?\
($1 OFS "-1")\
:\
($1 OFS "-2")\
)\
)\
)\
:\
""\
)
}
' Input_file
Explanation: Simple explanation would be using ternary operators to perform conditions and accordingly printing values(since its happening in print function).
Another. Replace <s with <=s where needed:
$ awk '{
if($2<0.5) # from low to higher sets the lower limit
$2=-2
else if($2<1) # so only upper limit needs to be tested
$2=-1
else if($2<1.5)
$2=1
else
$2=2
}1' file
Output:
A -1
B -1
C 2
D 2
Probably overkill for your needs but here's a data-driven approach using GNU awk for arrays of arrays and +/-inf:
$ cat tst.awk
BEGIN {
range["-inf"][0.5] = -2
range[0.5][1] = -1
range[1][1.5] = 1
range[1.5]["+inf"] = 2
}
{
val = ""
for ( beg in range ) {
for ( end in range[beg] ) {
if ( (beg+0 < $2) && ($2 <= end+0) ) {
val = range[beg][end]
}
}
}
print $1, val
}
$ awk -f tst.awk file
A -1
B -1
C 2
D 2
I'm assuming above that "between" excludes the start of the range but includes the end of it. You could make it slightly more efficient with:
for ( beg in range ) {
if ( beg+0 < $2 ) {
for ( end in range[beg] ) {
if ( $2 <= end+0 ) {
val = range[beg][end]
}
}
}
}
but I just like having the range comparison all on 1 line and there's only 1 end for every begin so it doesn't make much difference.
UPDATE 1 : new equation should cover nearly all scenarios :
1st half equation handles the sign +/-
2nd half handles the magnitude of the binning
mawk '$NF = (-++_)^(+(__=$NF)<_) * ++_^(int(__+_--^-_)!=_--)'
X -1.25 -2
X -1.00 -2
X -0.75 -2
X -0.50 -2
X -0.25 -2
X 0.00 -2
X 0.25 -2
X 0.50 -1
X 0.75 -1
X 1.00 1
X 1.25 1
X 1.50 2
X 1.75 2
X 2.00 2
X 2.25 2
X 2.50 2
==============================
this may not cover every possible scenario, but if u want a single liner to cover the samples shown :
mawk '$NF = 4 < (_=int(2*$NF)-2)^2 ? 1+(-3)^(_<-_) :_'
A -1
B -1
C 2
D 2
I have the following file called in.txt:
2020-01-01 fruit banana 3.4
2020-03-02 alcohol smirnov 26.99
2020-03-10 fruit orange 4.20
2020-04-03 fruit orange 4.20
2021-09-01 alcohol beer 6.00
2021-08-03 fruit mango 6.99
2022-01-01 fruit orange 4.30
2022-03-04 alcohol beer 6.00
2022-03-03 alcohol beer 6.00
2022-04-01 fruit mango 7.20
I want to transform the file so it reads something like this:
2020-01-01 2021-01-01 2022-01-01
-2020-12-31 -2021-12-31 -2022-12-31
fruit banana 3.40 0.00 0.00
orange 8.40 0.00 4.30
mango 0.00 6.99 7.20
Subt 11.80 6.99 11.50
alcohol beer 0.00 6.00 12.00
smirnov 26.99 0.00 0.00
Subt 26.99 6.00 12.00
Total 38.59 12.99 23.50
I have started writing the following script but am stuck on how to approach this. How can I display totals columns side by side. The other problem is that this is just dummy data. I have many different categories other than fruit and alcohol and it seems wrong to write if statements and for-loops for each one. Also how can I print fruit and alcohol out just once rather than for every iteration of column 3 and bring the date range to the top. Help is much appreciated.
#!/usr/bin/env bash
awk '
BEGIN{
FS=OFS="\t";
}
{
if ($2 ~ fruit && $1 >= "2020-01-01" && $1 <= "2020-12-31") {
a[$3]+=$4;
sa+=$4;
}
}
END {
PROCINFO["sorted_in"]="#ind_str_asc";
for (i in a) {
print "fruit", i, a[i]
}
}
' "${#:--}"
Would you please try the following:
#!/bin/bash
awk '
{
year = substr($1, 1, 4) # extract year
if (from == "" || from > year) from = year # first (smallest) year
if (to == "" || to < year) to = year # last (largest) year
if ($3 in category == 0) {
category[$3] = $2 # map item to category
list[$2] = list[$2] fs[$2] $3 # csv of items
fs[$2] = "," # delimiter for csv
}
sum[$3,year] += $4 # sum of the item in the year
subt[$2,year] += $4 # sum of the category in the year
ttl[year] += $4 # sum in the year
}
END {
format1 = "%-10s%-10s" # format for the left cells
format2 = "%-16s" # format for the header
format3 = "%-16.2f" # format for the amounts
# print upper header
printf(format1, "", "")
for (y = from; y <= to; y++) {
printf(format2, y "-01-01")
}
print ""
# print second header
printf(format1, "", "")
for (y = from; y <= to; y++) {
printf(format2, "-" y "-12-31")
}
print ""
for (cat in list) { # loop over the categories ("fruit" and "alcohol")
n = split(list[cat], item, ",") # split into items
for (i = 1; i <= n; i++) { # loop over the items
printf(format1, i == 1 ? cat : "", item[i])
for (y = from; y <= to; y++) { # loop over years
printf(format3, sum[item[i],y]) # append the sum of the year
}
print "" # finally break the line
}
print "" # insert blank line
printf(format1, "Subt", "")
for (y = from; y <= to; y++) {
printf(format3, subt[cat,y]) # append the subtotal
}
print "\n"
}
printf(format1, "Total", "")
for (y = from; y <= to; y++) {
printf(format3, ttl[y]) # append the total amount
}
print ""
}
' in.txt
Output with the provided input:
2020-01-01 2021-01-01 2022-01-01
-2020-12-31 -2021-12-31 -2022-12-31
alcohol smirnov 26.99 0.00 0.00
beer 0.00 6.00 12.00
Subt 26.99 6.00 12.00
fruit banana 3.40 0.00 0.00
orange 8.40 0.00 4.30
mango 0.00 6.99 7.20
Subt 11.80 6.99 11.50
Total 38.79 12.99 23.50
Please forgive me the order of items are not same as the OP's.
Using GNU awk for arrays of arrays:
$ cat tst.awk
BEGIN { OFS="\t" }
{
sub(/-.*/,"",$1)
minYear = ( NR==1 || $1 < minYear ? $1 : minYear )
maxYear = ( NR==1 || $1 > maxYear ? $1 : maxYear )
items[$2][$3]
vals[$1][$2][$3] += $4
typeTots[$1][$2] += $4
yearTots[$1] += $4
}
END {
printf "%s", OFS
for ( year=minYear; year<=maxYear; year++ ) {
printf "%s%s", OFS, year
}
print ""
for ( type in items ) {
itemCnt = 0
for ( item in items[type] ) {
printf "%s%s%s", (itemCnt++ ? "" : type), OFS, item
for ( year=minYear; year<=maxYear; year++ ) {
printf "%s%0.2f", OFS, vals[year][type][item]
}
print ""
}
printf "Subt%s", OFS
for ( year=minYear; year<=maxYear; year++ ) {
printf "%s%0.2f", OFS, typeTots[year][type]
}
print ORS
}
printf "Total%s", OFS
for ( year=minYear; year<=maxYear; year++ ) {
printf "%s%0.2f", OFS, yearTots[year]
}
print ""
}
$ awk -f tst.awk in.txt
2020 2021 2022
alcohol beer 0.00 6.00 12.00
smirnov 26.99 0.00 0.00
Subt 26.99 6.00 12.00
fruit orange 8.40 0.00 4.30
mango 0.00 6.99 7.20
banana 3.40 0.00 0.00
Subt 11.80 6.99 11.50
Total 38.79 12.99 23.50
or if you really want specific date ranges instead of just the year in the header:
$ cat tst.awk
BEGIN { OFS="\t" }
{
sub(/-.*/,"",$1)
minYear = ( NR==1 || $1 < minYear ? $1 : minYear )
maxYear = ( NR==1 || $1 > maxYear ? $1 : maxYear )
items[$2][$3]
vals[$1][$2][$3] += $4
typeTots[$1][$2] += $4
yearTots[$1] += $4
}
END {
printf "%s", OFS
for ( year=minYear; year<=maxYear; year++ ) {
printf "%s%s-01-01", OFS, year
}
print ""
printf "%s", OFS
for ( year=minYear; year<=maxYear; year++ ) {
printf "%s-%s-12-31", OFS, year
}
print ""
for ( type in items ) {
itemCnt = 0
for ( item in items[type] ) {
printf "%s%s%s", (itemCnt++ ? "" : type), OFS, item
for ( year=minYear; year<=maxYear; year++ ) {
printf "%s%0.2f", OFS, vals[year][type][item]
}
print ""
}
printf "Subt%s", OFS
for ( year=minYear; year<=maxYear; year++ ) {
printf "%s%0.2f", OFS, typeTots[year][type]
}
print ORS
}
printf "Total%s", OFS
for ( year=minYear; year<=maxYear; year++ ) {
printf "%s%0.2f", OFS, yearTots[year]
}
print ""
}
$ awk -f tst.awk in.txt | column -s$'\t' -t
2020-01-01 2021-01-01 2022-01-01
-2020-12-31 -2021-12-31 -2022-12-31
alcohol beer 0.00 6.00 12.00
smirnov 26.99 0.00 0.00
Subt 26.99 6.00 12.00
fruit orange 8.40 0.00 4.30
mango 0.00 6.99 7.20
banana 3.40 0.00 0.00
Subt 11.80 6.99 11.50
Total 38.79 12.99 23.50
I believe the following piece of awk code is a good start. The remaining part to do is just some cleanup and some extra code for the sums.
BEGIN{
# how many divisions per year
n=1
# initialisation of some variables
tmax=0;tmin=999999; ymax=qmax=0;ymin=9999;qmin=99
}
# convert date to quarter,trim,half
{ y=$1+0; q=(substr($1,6,7)+0)%n}
# compute min max time
(y*100+q < tmin) { ymin=y;qmin=q;tmin=y*100+q }
(y*100+q > tmax) { ymax=y;qmax=q;tmax=y*100+q }
# Create arrays that keep track of everything
# a : prices by year,q,category and element
# b : just a list of categories, eg fruit
# c : just a list of elements and the category it belongs to.
{ a[y,q,$2,$3]=$4; b[$2]; c[$3]=$2 }
END{
# loop over categories (eg fruit)
for(i in b) {
# loop over elemnts
for(j in c) {
# exclude elements that do not belong to category
if (i!=c[j]) continue
s=i OFS j;
# loop over the time
for (y=ymin;y<=ymax;y++) {
for (q=0;q<n;++q) {
if (y*100+q < tmin) continue
if (y*100+q > tmax) continue
s=s OFS a[y,q,i,j]+0
}
}
print s
}
}
}
This currently outputs:
alcohol beer 0 6 6
alcohol smirnov 26.99 0 0
fruit orange 4.2 0 4.3
fruit mango 0 6.99 7.2
fruit banana 3.4 0 0
Sample input
12.0000 0.6000000 0.05
13.0000 1.6000000 0.05
14.0000 2.6000000 0.05
15.0000 3.0000000 0.05
15.0000 3.2000000 0.05
15.0000 3.4000000 0.05
15.0000 3.6000000 0.10
15.0000 3.8000000 0.10
15.0000 4.0000000 0.10
15.0000 4.2000000 0.11
15.0000 4.4000000 0.12
15.0000 4.6000000 0.13
15.0000 4.8000000 0.14
15.0000 5.0000000 0.15
15.0000 5.2000000 0.14
15.0000 5.4000000 0.13
15.0000 5.6000000 0.12
15.0000 5.8000000 0.11
15.0000 6.0000000 0.10
15.0000 6.2000000 0.10
15.0000 6.4000000 0.10
15.0000 6.6000000 0.05
15.0000 6.8000000 0.05
15.0000 7.0000000 0.05
Goal
Print line 1 in output as 0 0
For $2 = 5.000000, $3 = 0.15.
Print line 2 in output as 1 0.15
For $2 = 4.800000 through $2 = 5.200000, sum+=$3 for each line (i.e. 0.14 + 0.15 + 0.14 = 0.43).
Print line 3 in output as 2 0.43.
For $2 = 4.600000 through $2 = 5.400000, sum+=$3 for each line (i.e. 0.13 + 0.14 + 0.15 + 0.14 + 0.13 = 0.69).
Print line 4 in output as 3 0.69
Continue this pattern until $2 = 5.000000 +- 1.6 (9 lines total, plus line 1 as 0 0 = 10 total lines in output)
Desired Output
0 0
1 0.15
2 0.43
3 0.69
4 0.93
5 1.15
6 1.35
7 1.55
8 1.75
9 1.85
Attempt
Script 1
#!/bin/bash
for (( i=0; i<=8; i++ )); do
awk '$2 >= 5.0000000-'$i'*0.2 {sum+=$3}
$2 == 5.0000000+'$i'*0.2 {print '$i', sum; exit
}' test.dat
done > test.out
produces
0 0.15
1 0.43
2 0.69
3 0.93
4 1.15
5 1.35
6 1.55
7 1.75
8 1.85
This is very close. However, the output is missing 0 0 for line 1, and because of this, lines 2 through 10 have $1 and $2 mismatched by 1 line.
Script 2
#!/bin/bash
for (( i=0; i<=8; i++ )); do
awk ''$i'==0 {sum=0}
'$i'>0 && $2 > 5.0000000-'$i'*0.2 {sum+=$3}
$2 == 5.0000000+'$i'*0.2 - ('$i' ? 0.2 : 0) {print '$i', sum; exit
}' test.dat
done > test.out
which produces
0 0
1 0.15
2 0.43
4 0.93
5 1.15
6 1.35
7 1.55
$1 and $2 are now correctly matched. However, I am missing the lines with $1=3, $1=8, and $1=9 completely. Adding the ternary operator causes my code to skip these iterations in the loop somehow.
Question
Can anyone explain what's wrong with script 2, or how to achieve the desired output in one line of code? Thank you.
Solution
I used Ed Morton's solution to solve this. Both of them work for different goals. Instead of using the modulus to save array space, I constrained the array to $1 = 15.0000. I did this instead of the modulus in order to include two other "key" variables that I had wanted to also sum over at different parts of the input, into separate output files.
Furthermore, as far as I understood it, the script summed only for lines with $2 >= 5.0000000, and then multiplied the summation by 2, in order to include the lines with $2 <= 5.0000000. This works for the sample input here because I made $3 symmetric around 0.15. I modified it to sum them separately, though.
awk 'BEGIN { key=5; range=9}
$1 == 15.0000 {
a[NR] = $3
}
$2 == key { keyIdx = NR}
END {
print (0, 0) > "test.out"
sum = a[keyIdx]
for (delta=1; delta<=range; delta++) {
print (delta, sum) > "test.out"
plusIdx = (keyIdx + delta)
minusIdx = (keyIdx - delta)
sum += a[plusIdx] + a[minusIdx]
}
exit
}' test.dat
Is this what you're trying to do?
$ cat tst.awk
$2 == 5 { keyNr = NR }
{ nr2val[NR] = $3 }
END {
print 0, 0
sum = nr2val[keyNr]
for (delta=1; delta<=9; delta++) {
print delta, sum
sum += nr2val[keyNr+delta] + nr2val[keyNr-delta]
}
}
$ awk -f tst.awk file
0 0
1 0.15
2 0.43
3 0.69
4 0.93
5 1.15
6 1.35
7 1.55
8 1.75
9 1.85
We could optimize it to only store 2*(range=9) values in vals[] (using a modulus operator NR%(2*range) for the index) and do the calculation when we hit an NR that's range lines past the line where $2 == key rather than doing it after we've read the whole of the input if it's either too slow or your input file is too big to store all in memory, e.g.:
$ cat tst.awk
BEGIN { key=5; range=9 }
{
idx = NR % (2*range)
nr2val[idx] = $3
}
$2 == key { keyIdx = idx; endNr = NR+range }
NR == endNr { exit }
END {
print 0, 0
sum = nr2val[keyIdx]
for (delta=1; delta<=range; delta++) {
print delta, sum
idx = (keyIdx + delta) % (2*range)
sum += nr2val[idx] + nr2val[idx]
}
exit
}
$ awk -f tst.awk file
0 0
1 0.15
2 0.43
3 0.69
4 0.93
5 1.15
6 1.35
7 1.55
8 1.75
9 1.85
I like your problem. It is an adequate challenge.
My approach is to put all possible into the awk script. And scan the input file only once. Because I/O manipulation is slower than computation (these days).
Do as many computation (actually 9) on the relevant input line.
The required inputs are variable F1 and text file input.txt
The execution command is:
awk -v F1=95 -f script.awk input.txt
So the logic is:
1. Initialize: Compute the 9 range markers and store their values in an array.
2. Store the 3rd input value in an order array `field3`. We use this array to compute the sum.
3. On each line that has 1st field equals 15.0000.
3.1 If found begin marker then mark it.
3.2 If found end marker then compute the sum, and mark it.
4. Finalize: Output all the computed results
script.awk including few debug printout to assist in debugging
BEGIN {
itrtns = 8; # iterations count consistent all over the program.
for (i = 0; i <= itrtns; i++) { # compute range markers per iteration
F1start[i] = (F1 - 2 - i)/5 - 14; # print "F1start["i"]="F1start[i];
F1stop[i] = (F1 - 2 + i)/5 - 14; # print "F1stop["i"]="F1stop[i];
b[i] = F1start[i] + (i ? 0.2 : 0); # print "b["i"]="b[i];
}
}
{ field3[NR] = $3;} # store 3rd input field in ordered array.
$1==15.0000 { # for each input line that has 1st input field 15.0000
currVal = $2 + 0; # convert 2nd input field to numeric value
for (i = 0; i <= itrtns; i++) { # on each line scan for range markers
# print "i="i, "currVal="currVal, "b["i"]="b[i], "F1stop["i"]="F1stop[i], isZero(currVal-b[i]), isZero(currVal-F1stop[i]);
if (isZero(currVal - b[i])) { # if there is a begin marker
F1idx[i] = NR; # store the marker index postion
# print "F1idx["i"] =", F1idx[i];
}
if (isZero(currVal - F1stop[i])) { # if there is an end marker
for (s = F1idx[i]; s <= NR; s++) {sum[i] += field3[s];} # calculate its sum
F2idx[i] = NR; # store its end marker postion (for debug report)
# print "field3["NR"]=", field3[NR];
}
}
}
END { # output the computed results
for (i = 0; i <= itrtns; i++) {print i, sum[i], "rows("F1idx[i]"-"F2idx[i]")"}
}
function isZero(floatArg) { # floating point number pecision comparison
tolerance = 0.00000000001;
if (floatArg < tolerance && floatArg > -1 * tolerance )
return 1;
return 0;
}
Provided input.txt from the question.
12.0000 0.6000000 0.05
13.0000 1.6000000 0.05
14.0000 2.6000000 0.05
15.0000 3.0000000 0.05
15.0000 3.2000000 0.05
15.0000 3.4000000 0.05
15.0000 3.6000000 0.10
15.0000 3.8000000 0.10
15.0000 4.0000000 0.10
15.0000 4.2000000 0.11
15.0000 4.4000000 0.12
15.0000 4.6000000 0.13
15.0000 4.8000000 0.14
15.0000 5.0000000 0.15
15.0000 5.2000000 0.14
15.0000 5.4000000 0.13
15.0000 5.6000000 0.12
15.0000 5.8000000 0.11
15.0000 6.0000000 0.10
15.0000 6.2000000 0.10
15.0000 6.4000000 0.10
15.0000 6.6000000 0.05
15.0000 6.8000000 0.05
15.0000 7.0000000 0.05
The output for: awk -v F1=95 -f script.awk input.txt
0 0.13 rows(12-12)
1 0.27 rows(12-13)
2 0.54 rows(11-14)
3 0.79 rows(10-15)
4 1.02 rows(9-16)
5 1.24 rows(8-17)
6 1.45 rows(7-18)
7 1.6 rows(6-19)
8 1.75 rows(5-20)
The output for: awk -v F1=97 -f script.awk input.txt
0 0.15 rows(14-14)
1 0.29 rows(14-15)
2 0.56 rows(13-16)
3 0.81 rows(12-17)
4 1.04 rows(11-18)
5 1.25 rows(10-19)
6 1.45 rows(9-20)
7 1.65 rows(8-21)
8 1.8 rows(7-22)
I have a problem and thus i ask :)
i have input... something like this
48 06-Jul-16 00:04:26.850000, 0.3
1 06-Jul-16 00:04:29.200000, 0.35
60 06-Jul-16 00:04:29.250000, 0.3
1 06-Jul-16 00:04:32.190476, 0.35
11 06-Jul-16 00:04:32.238095, 0.3
1 06-Jul-16 00:04:32.761905, 0.35
20 06-Jul-16 00:04:32.809524, 0.3
1 06-Jul-16 00:04:33.800000, 0.35
14 06-Jul-16 00:04:33.850000, 0.3
1 06-Jul-16 00:04:34.550000, 0.35
4 06-Jul-16 00:04:34.600000, 0.3
1 06-Jul-16 00:04:34.800000, 0.35
28 06-Jul-16 00:04:34.850000, 0.3
2 06-Jul-16 00:04:36.238095, 0.35
12 06-Jul-16 00:04:36.333333, 0.3
1 06-Jul-16 00:04:36.904762, 0.35
1 06-Jul-16 00:04:36.952381, 0.3
1 06-Jul-16 00:04:37.000000, 0.35
22 06-Jul-16 00:04:37.050000, 0.3
2 06-Jul-16 00:04:38.150000, 0.35
10 06-Jul-16 00:04:38.250000, 0.3
1 06-Jul-16 00:04:38.750000, 0.35
1 06-Jul-16 00:04:38.800000, 0.3
and I need an output where the first column is 1, it's previous line and next line 1st columns must be more than 12 and fourth columns both bigger or both lower than current rows 4th column, like this
1 06-Jul-16 00:04:29.200000, 0.35
1 06-Jul-16 00:04:33.800000, 0.35
I tried to play with awk a bit but to no vain
awk '($1=1) && NR+1($1>12) && NR-1($1>12){print $0}'
And I understand that it is totally wrong.
Thanks for help.
$ cat tst.awk
NR==FNR { a[NR] = $0; next }
{ split(a[FNR-1],p); split(a[FNR+1],n) }
(FNR > 1) && ($1 == 1) && (p[1] > 12) && (n[1] > 12) &&
( ( (p[4] > $4) && (n[4] > $4) ) ||
( (p[4] < $4) && (n[4] < $4) ) )
$ awk -f tst.awk file file
1 06-Jul-16 00:04:29.200000, 0.35
1 06-Jul-16 00:04:33.800000, 0.35
or if you prefer it in one pass at the expense of a little more complexity:
$ cat tst.awk
{ split(prev,p); split(curr,c); split($0,n) }
(NR > 2) && (c[1] == 1) && (p[1] > 12) && (n[1] > 12) &&
( ( (p[4] > c[4]) && (n[4] > c[4]) ) ||
( (p[4] < c[4]) && (n[4] < c[4]) ) ) {
print curr
}
{prev = curr; curr = $0 }
$ awk -f tst.awk file
1 06-Jul-16 00:04:29.200000, 0.35
1 06-Jul-16 00:04:33.800000, 0.35
p = previous, c = current, n = next.
$ cat > test.awk
t[1]==1 && p[1]>12 && $1>12 && ((t[4]>p[4] && t[4]>$4) || (t[4]<p[4] && t[4]<$4)) {
print t[0]
}
{
p[1]=t[1];t[1]=$1;
p[0]=t[0];t[0]=$0;
p[4]=t[4];t[4]=$4;
}
$ awk -f test.awk test.in
1 06-Jul-16 00:04:29.200000, 0.35
1 06-Jul-16 00:04:33.800000, 0.35
This only reads the file once:
$1 == 1 {
line[1] = $0;
value[1] = $NF;
next;
}
$1 > 12 {
if (line[1] && line[0]) {
if ((value[0] > value[1] && $NF > value[1]) || (value[0] < value[1] && $NF < value[1])) {
print line[1];
line[1] = "";
}
}
line[0] = $0;
value[0] = $NF;
next;
}
{
line[0] = "";
}
I've got a big 7-column text file with sorted rows like this:
gi|352964122|gb|JH286168.1| 00884 C C 14 1.00 u
gi|352964122|gb|JH286168.1| 00884 C C 26 0.76 p
gi|352964122|gb|JH286168.1| 00884 C C 33 0.89 f
gi|352964122|gb|JH286168.1| 00885 G G 14 1.00 u
gi|352964122|gb|JH286168.1| 00885 A A 30 0.84 f
gi|352964122|gb|JH286168.1| 00886 T T 31 0.81 f
What I'm needing to do is, if the first two columns are the same in consecutive rows, append the rest of the columns to the first row. There can be 1, 2, or 3 "similar" rows, and I need placeholders to keep columns intact if less than 3. So the above would look like this:
gi|352964122|gb|JH286168.1| 00884 C C 14 1.00 u C C 26 0.76 p C C 33 0.89 f
gi|352964122|gb|JH286168.1| 00885 G G 14 1.00 u - - - ------------ G G 33 0.89 f
gi|352964122|gb|JH286168.1| 00886 T T 31 0.81 f - - - ---- - - - ------ - - -- ----- - -
I've tried many approaches with AWK but can't quite get it. How might this be done?
I'm unsure about how you get your second row but this might match at least how I understand the goal:
awk '
{
head=$1 " " $2
tail=$3 " " $4 " " $5 " " $6 " "$7
if(previous!=head) {
if(previous!="") printf("%s %s %s %s\n",previous,p[1],p[2],p[3])
previous=head
i=1
p[i]=tail
p[2]=p[3]="- - - -"
} else {
i=i+1
p[i]=tail
}
}
END { printf("%s %s %s %s\n",previous,p[1],p[2],p[3]) }'
Output:
gi|352964122|gb|JH286168.1| 00884 C C 14 1.00 u C C 26 0.76 p C C 33 0.89 f
gi|352964122|gb|JH286168.1| 00885 G G 14 1.00 u A A 30 0.84 f - - - -
gi|352964122|gb|JH286168.1| 00886 T T 31 0.81 f - - - - - - - -
This should do it:
(Edit: I didn't notice you needed placeholders. I'll look into it....)
awk '
$1 == last1 && $2 == last2 {
printf " %s %s %s %s %s",$3,$4,$5,$6,$7;
last1 = $1; last2 = $2;
next;
}
{
$1 = $1; # normalize spacing
printf "%s%s", NR==1?"":"\n", $0;
last1 = $1; last2 = $2;
}
END { print ""; }
' file
$ cat tst.awk
BEGIN { maxRecs = 3 }
function prta( i, dflt) {
dflt = a[1]
gsub(/[^[:space:]]+/,"-",dflt)
printf "%s ", key
for (i=1; i<=maxRecs; i++) {
printf "%s%s", (i in a ? a[i] : dflt), (i<maxRecs ? OFS : ORS)
delete a[i]
}
numRecs = 0
}
{ key = $1 FS $2 }
prev && (key != prev) { prta() }
{
$1 = $1
sub(/([^[:space:]]+[[:space:]]+){2}/,"")
a[++numRecs] = $0
prev = key
}
END { prta() }
$
$ awk -f tst.awk file
gi|352964122|gb|JH286168.1| 00885 C C 14 1.00 u C C 26 0.76 p C C 33 0.89 f
gi|352964122|gb|JH286168.1| 00886 G G 14 1.00 u A A 30 0.84 f - - - - -
gi|352964122|gb|JH286168.1| 00886 T T 31 0.81 f - - - - - - - - - -