UNIX for Dummies Questions & Answers

count/file1,1.5 ,0.25
count/file2,0 ,1
count/file3,NA, NA

$ tail -n 100 data/*
==> data/file1 <==
this is me
this is me again

==> data/file2 <==
hello hello hello
hello

==> data/file3 <==
2 3 5
73 543 567 56788

$ cat meanvar.awk

# Output separator is ,
BEGIN { OFS="," }

# Whenever the filename changes, print results and start over
F != FILENAME {
        if(n>0)
        {
                mean=s/n;
                for(i in x)
                {
                        ss += (x[i]-mean)^2;
                        delete x[i];
                }
                var=(ss/n);

                print F, mean, var;
        }

        ss=0;   s=0;    n=0;    F=FILENAME
}

# First line of every file, grab the number of columns
FNR==1 { COLS=NF }

{
        x[++n]=NF;
        s+=NF;
}

# Also a special case for when the last file ends.
END {
        if(n>0)
        {
                mean=s/n;
                for(i in x)
                {
                        ss += (x[i]-mean)^2;
                        delete x[i];
                }
                var=(ss/n);

                print F, mean, var;
        }
}

$ awk -f meanvar.awk data/*
data/file1,3.5,0.25
data/file2,2,1
data/file3,3.5,0.25

$

else 
	{
		print F, NA, NA;
	}

else if (n=0) 
	{
		print F, NA, NA;
	}

awk ... > output

for FILE in data/*
do
        [ -s "$FILE" ] || echo "$FILE,0,0"
done >> output