added covariance matrix calculation

1 files changed, 12 insertions, 15 deletions

diff --git a/mean_avg.awk b/mean_avg.awk
index 6f5a270..565dcc2 100644
--- a/mean_avg.awk
+++ b/mean_avg.awk
@@ -4,20 +4,17 @@
 # average columns of numerical data
 
 BEGIN {
-    OFS = "%.18g"
-    sign = "[+-±]?"
-    decimal = "[0-9]+[.]?[0-9]*"
-    fraction = "[.][0-9]*"
-    exponent = "([Ee]" sign "[0-9]+)?"
-    number = "^" sign "(" decimal "|" fraction ")" exponent "$"
+    OFMT = "%.18g"
+    #sign = "[+-]?"
+    #decimal = "[0-9]+[.]?[0-9]*"
+    #fraction = "[.][0-9]*"
+    #exponent = "([Ee]" "[+-]?" "[0-9]+)?"
+    number = "^[+-]?([0-9]+[.]?[0-9]*|[.][0-9]*)([Ee][+-]?[0-9]+)?$"
 }
 
 NR == 1 {
-    header_nf = NF
-    for (n=1; n<=NF; n++) {
-        if ($n !~ number)
-            header[n] = $n
-    }
+    for (n=1; n<=NF; n++)
+        ($n ~ number) ? header[n] = "col" n : header[n] = $n
 }
 
 # Welford's 'online' algorithm for variance
@@ -28,10 +25,10 @@ NF > 0 {
         if ($n ~ number) {
             count[n] += 1
             delta0[n] = $n - mean[n]
-            mean[n] = mean[n] + delta0[n]/count[n]
+            mean[n] += delta0[n]/count[n]
             delta1[n] = $n - mean[n]
-            M2[n] = M2[n] + delta0[n]*delta1[n]
-            (count[n] > 1) ? var[n] = M2[n]/(count[n] - 1) : var[n] = "0"
+            M2[n] += delta0[n]*delta1[n]
+            (count[n] > 1) ? var[n] = M2[n]/(count[n] - 1) : var[n] = ""
         }
     }
 }
@@ -42,7 +39,7 @@ END {
         if (header[n])
             print header[n], mean[n], sqrt(var[n]), sqrt(var[n]/count[n]), count[n]
         else
-            print "col_" n, mean[n], sqrt(var[n]), sqrt(var[n]/count[n]), count[n]
+            print "col" n, mean[n], sqrt(var[n]), sqrt(var[n]/count[n]), count[n]
     }
 }