added covariance matrix calculation

1 files changed, 17 insertions, 17 deletions

diff --git a/lin_reg.awk b/lin_reg.awk
index 8622289..56114a2 100644
--- a/lin_reg.awk
+++ b/lin_reg.awk
@@ -4,7 +4,7 @@
 # simple linear regression between columns
 
 BEGIN {
-    OFS = "%.18g"
+    OFMT = "%.18g"
     sign = "[+-]?"
     decimal = "[0-9]+[.]?[0-9]*"
     fraction = "[.][0-9]*"
@@ -13,13 +13,11 @@ BEGIN {
 }
 
 NR == 1 {
-    header_nf = NF
-    for (n=1; n<=NF; n++) {
-        ($n !~ number) ? header[n] = $n : header[n] = "col" n
-    }
+    for (n=1; n<=NF; n++)
+        ($n ~ number) ? header[n] = "col" n : header[n] = $n
 }
 
-NF != 0 {
+NF > 0 {
     if (NF > nf_max)
         nf_max = NF
 
@@ -31,15 +29,14 @@ NF != 0 {
             count[y] += 1
             sum[y] += $y
             sum2[y] += $y*$y
-            mean[y] = sum[y]/count[y]
-
-            ### difference from the mean
-            delta[y] = $y - mean[y]
-            sum_delta[y] += delta[y]
-            sum_delta2[y] += delta[y]*delta[y]
+            delta0[y] = $y - mean[y]
+            mean[y] = mean[y] + delta0[y]/count[y]
+            delta1[y] = $y - mean[y]
+            sum_delta[y] += delta1[y]
+            sum_delta2[y] += delta0[y]*delta1[y]
 
             ### sample variance
-            (count[y] > 1) ? var[y] = sum_delta2[y]/(count[y] - 1) : var[y] = 0
+            (count[y] > 1) ? var[y] = sum_delta2[y]/(count[y] - 1) : var[y] = ""
 
             # x = row, y = col
             for (x=1; x<=nf_max; x++) {
@@ -47,9 +44,12 @@ NF != 0 {
                 sum_xy[x,y] += $x*$y
                 sum_delta_xy[x,y] += delta[x]*delta[y]
 
+                # covariance
+                #(count[x,y] > 1) ? cov[x,y] = sum_delta_xy[x,y]/(count[x,y] - 1) : cov[x,y] = ""
+
                 # correlation
                 r_den[x,y] = sqrt(sum_delta2[x]*sum_delta2[y])
-                (r_den[x,y]) ?  r[x,y] = sum_delta_xy[x,y]/r_den[x,y] : r[x,y] = 1
+                (r_den[x,y]) ? r[x,y] = sum_delta_xy[x,y]/r_den[x,y] : r[x,y] = 1
 
                 ab_den[x,y] = (count[x,y]*sum2[x] - sum[x]*sum[x])
                 if (ab_den[x,y]) {
@@ -84,9 +84,9 @@ END {
     for (y=1; y<=nf_max; y++) {
         for (x=1; x<=nf_max; x++) {
             if (x != y && r[x,y]) {
-                printf("\n  %.18g \t (%s) \t = (%.18g +/- %.18g)(%s) \t + (%.18g +/- %.18g)",
-                    10.0*log(r[x,y]*r[x,y])/log(10), header[y], b[x,y], b_err[x,y], header[x],
-                    a[x,y], a_err[x,y])
+                printf("%.9g "OFS" (%s) "OFS" = (%.9g +/- %.9g)(%s) "OFS" + (%.9g +/- %.9g)%s",
+                    10.0*log(r[x,y]*r[x,y])/log(10.0), header[y], b[x,y],
+                    b_err[x,y], header[x], a[x,y], a_err[x,y], ORS)
             }
         }
     }