for j in range(len(dim)):
if i == j:
continue
else:
figure()
scatter((glitches[:,i]),(glitches[:,j]),s=2)
xlabel(dim[i])
ylabel(dim[j])
title(dim[i]+' vs. '+dim[j])
xlim(min(glitches[:,i]),max(glitches[:,i]))
ylim(min(glitches[:,j]),max(glitches[:,j]))
savefig(snr_path + '/' + dim[i]+'vs'+dim[j]+'.png')
close()
print 'Working..'
labels,max_k,centroids = gMeans(glitches,runs,snr_path)
#savetxt(str(ks_crit)+'_saved_labels.txt',saved_labels)
# Use the webgen.py python script to generate an .html file for displaying the plots
# and various other statistics from ksmeans.
ks = 0
num_k = max_k
webgen(ks,gps_start,gps_end,mean(num_k),std(num_k),dim,snr_low,snr_high,freq_low,freq_high,sci_time,g_found,new_path,max_k,srvName)
colors = rand(max_k+1,3)
# Plots the clustered parameters against each other for display on the .html page.
print 'Plotting clusters...'
q = 0
j = 0
scatter((glitches[:,i]),(glitches[:,j]),s=2)
xlabel(dim[i])
ylabel(dim[j])
title(dim[i]+' vs. '+dim[j])
xlim(min(glitches[:,i]) - 0.1*max(glitches[:,i]),max(glitches[:,i]) + 0.1*max(glitches[:,i]))
ylim(min(glitches[:,j]) - 0.1*max(glitches[:,j]),max(glitches[:,j]) + 0.1*max(glitches[:,j]))
savefig(snr_path + '/' + dim[i]+'vs'+dim[j]+'.png')
close()
## Runs ksmeans for n runs, this while loop will continue to for a run
## until all clusters found have more than 2 members, this is to
## prevent ksmeans from diverging to it assigning every glitch its
## own cluster. i.e. N clusters for N glitches
labels,ks,centroids = gMeans(glitches,runs)
num_k = ks
max_k = ks
colors = rand(max_k,3)
## Generates the .html page for viewing the glitch parameter and cluster plots
webgen(ks,gps_start,gps_end,mean(num_k),std(num_k),dim,snr_low,snr_high,freq_low,freq_high,sci_time,g_found,new_path,max_k)
print 'Plotting clusters...'
## Plots the clustered glitch parameters
q = 0
j = 0
for l in range(len(dim)):
j = q
for j in range(len(dim)):
