summaryrefslogtreecommitdiff
path: root/lin_reg1.awk
diff options
context:
space:
mode:
authorwukong <wukong@longaeva>2018-11-04 10:59:44 -0800
committerwukong <wukong@longaeva>2018-11-04 10:59:44 -0800
commite14342e827e2b42e43c006df90c7ad99e5124b3c (patch)
treec73e930f3b111bb659957df1509e7d9f5a3c8493 /lin_reg1.awk
parent72fdb25210c579beaabc35cae7ec803436887f20 (diff)
added gaussian.awk based on hamming script;
added pwr(x,p) function to sterling_approx; minor clean up all around;
Diffstat (limited to 'lin_reg1.awk')
-rw-r--r--lin_reg1.awk23
1 files changed, 13 insertions, 10 deletions
diff --git a/lin_reg1.awk b/lin_reg1.awk
index 9d9f257..ae59c77 100644
--- a/lin_reg1.awk
+++ b/lin_reg1.awk
@@ -22,28 +22,30 @@ NF > 0 {
### iterate over columns
for (y=1; y<=nf_max; y++) {
+ if ($y == header[n])
+ continue
if ($y ~ number) {
### mean
count[y] += 1
sum[y] += $y
sum2[y] += $y*$y
- mean[y] = sum[y]/count[y]
+ delta0[y] = $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]
- ### difference from the mean
- delta[y] = $y - mean[y]
- sum_delta[y] += delta[y]
- sum_delta2[y] += delta[y]*delta[y]
- # x = row, y = col
+ # x = row, y = col, trendline: y = A + Bx
for (x=1; x<=nf_max; x++) {
count[x,y] += 1
sum_xy[x,y] += $x*$y
- sum_delta_xy[x,y] += delta[x]*delta[y]
+ sum_delta_xy[x,y] += delta0[x]*delta1[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] = 0
+ (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]) {
@@ -65,9 +67,10 @@ END {
for (y=1; y<=nf_max; y++) {
for (x=1; x<=nf_max; x++) {
if (x != y && r[x,y]) {
- r2[x,y] = r[x,y]*r[x,y]
printf(OFMT OFS "(%s)" OFS " = " OFMT "(%s)" OFS " + " OFMT ORS,
- 10.0*log(r2[x,y])/log(10.0), header[y], b[x,y], header[x], a[x,y])
+ 10.0*log(r[x,y]*r[x,y])/log(10.0),
+ header[y], b[x,y],
+ header[x], a[x,y])
}
}
}