1 files changed, 47 insertions, 0 deletions
diff --git a/sum_col.awk b/sum_col.awk
new file mode 100644
index 0000000..f08ec06
--- /dev/null
+++ b/sum_col.awk
@@ -0,0 +1,47 @@
+#!/usr/bin/awk -f
+
+### sum_col.awk
+# sum columns of numerical data
+# input: delimited data as text
+# output: list of univariate summary stats
+
+
+BEGIN {
+    OFS = FS
+    sign = "[+-]?"
+    decimal = "[0-9]+[.]?[0-9]*"
+    fraction = "[.][0-9]+"
+    exponent = "([Ee]" sign "[0-9]+)?"
+    number = "^" sign "(" decimal "|" fraction ")" exponent "$"
+}
+
+
+# read column headers
+NR == 1 {
+    for (n=1; n<=NF; n++)
+        ($n ~ number) ? header[n] = "col" n : header[n] = $n
+}
+
+
+# iterate over columns
+NF > 0 {
+    (NF > nf_max) ? nf_max = NF : nf_max = nf_max
+    for (n=1; n <= NF; n++) {
+        if ($n ~ number) {
+            count[n] += 1
+            sum[n] += $n
+        }
+    }
+}
+
+
+END {
+    print "col", "sum", "count"
+    for (n=1; n<=nf_max; n++) {
+        if (header[n])
+            print header[n], sum[n], count[n]
+        else
+            print "col" n, sum[n], count[n]
+    }
+}
+