From 0e225c6d140a5a4986d0771aefb8a8edbe5d435d Mon Sep 17 00:00:00 2001
From: wukong <wukong@longaeva>
Date: Sat, 13 Apr 2019 13:04:26 -0700
Subject: optimized covariance script; added 'nan' output to diff; added ':'
 output delimiter to lin_reg and quad_reg; fixed broken r^2 calc in quad_reg;

---
 cov.awk | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

(limited to 'cov.awk')

diff --git a/cov.awk b/cov.awk
index 56734e4..c06a447 100644
--- a/cov.awk
+++ b/cov.awk
@@ -4,6 +4,7 @@
 # online covariance algorithm
 
 BEGIN {
+    OFS = FS
     sign = "[+-]?"
     decimal = "[0-9]+[.]?[0-9]*"
     fraction = "[.][0-9]*"
@@ -22,16 +23,17 @@ NF > 0 {
 
     ### columns
     for (y=1; y<=nf_max; y++) {
-        if ($y == header[y])
-            continue
         ### rows
         for (x=1; x<=nf_max; x++) {
+            if ($x !~ number || $x == header[x])
+                continue
             count[x,y]++
             dx[x,y] = $x - meanx[x,y]
+            dy[x,y] = $y - meany[x,y]
             meanx[x,y] += dx[x,y]/count[x,y]
-            meany[x,y] += ($y - meany[x,y])/count[x,y]
-            C[x,y] += dx[x,y]*($y - meany[x,y])
-            cov_pop[x,y] = C[x,y]/count[x,y]
+            meany[x,y] += dy[x,y]/count[x,y]
+            C[x,y] += dx[x,y]*dy[x,y]
+            # cov_pop[x,y] = C[x,y]/count[x,y]
             (count[x,y] > 1) ? cov_samp[x,y] = C[x,y]/(count[x,y] - 1) : cov_samp[x,y] = ""
         }
     }
-- 
cgit v1.2.3