if opts.no2d:
twoDplots=[]
greedy2savepaths,oned_data,confidence_uncertainty,confidence_levels,max_logls,dics=compare_bayes(outpath,zip(names,pos_list),opts.inj,opts.eventnum,opts.username,opts.password,opts.reload_flag,opts.clf,opts.ldg_flag,contour_figsize=(float(opts.cw),float(opts.ch)),contour_dpi=int(opts.cdpi),contour_figposition=[0.15,0.15,float(opts.cpw),float(opts.cph)],fail_on_file_err=not opts.readFileErr,covarianceMatrices=opts.covarianceMatrices,meanVectors=opts.meanVectors,Npixels2D=int(opts.npixels_2d))
####Print Confidence Levels######
output_confidence_levels_tex(confidence_levels,outpath)
output_confidence_levels_dat(confidence_levels,outpath)
####Save confidence uncertainty#####
output_confidence_uncertainty(confidence_uncertainty,outpath)
####Print HTML!#######
compare_page=bppu.htmlPage('Compare PDFs (single event)',css=bppu.__default_css_string)
param_section=compare_page.add_section('Meta')
param_section_write='<div><p>This comparison was created from the following analyses</p>'
param_section_write+='<table border="1">'
param_section_write+='<th>Analysis</th> <th> max(log(L)) </th> <th> DIC </th>'
for (name,logl_max), dic in zip(max_logls, dics):
param_section_write+='<tr><td><a href="%s">%s</a></td> <td>%g</td> <td>%.1f</td></tr>'%(dict(zip(names,pos_list))[name],name,logl_max,dic)
param_section_write+='</table></div>'
param_section.write(param_section_write)
param_section.write('<div><p><a href="confidence_table.tex">LaTeX table</a> of medians and confidence levels.</p></div>')
if oned_data:
param_section=compare_page.add_section('1D marginal posteriors')
def makeOutputPage(objs, params, outdir, confidencelevels):
"""
Make a summary page with table of results and plots for each param in params
"""
if not os.path.isdir(outdir):
os.makedirs(outdir)
#Bin size/resolution for binning. Need to match (converted) column names.
GreedyRes = {
'mc': 0.025,
'm1': 0.1,
'm2': 0.1,
'mass1': 0.1,
'mass2': 0.1,
'mtotal': 0.1,
'eta': 0.001,
'iota': 0.01,
'time': 1e-3,
'distance': 1.0,
'dist': 1.0,
'mchirp': 0.025,
'a1': 0.02,
'a2': 0.02,
'phi1': 0.05,
'phi2': 0.05,
'theta1': 0.05,
'theta2': 0.05,
'ra': 0.05,
'dec': 0.05
}
html = bppu.htmlPage('Injection Summary', css=bppu.__default_css_string)
html_meta = html.add_section('Summary')
html_meta.p('Analysed %i injections.' % (len(objs)))
# Make a directory for stdacc and errorbar plots
accdir = os.path.join(outdir, 'stdacc')
if not os.path.isdir(accdir):
os.makedirs(accdir)
errdir = os.path.join(outdir, 'errbar')
if not os.path.isdir(errdir):
os.makedirs(errdir)
boxdir = os.path.join(outdir, 'boxplot')
if not os.path.isdir(boxdir):
os.makedirs(boxdir)
# Calculate confidence intervals for each injection and parameter
#for par in params:
# par=par.lower()
# print 'Binning %s to determine confidence intervals'%(par)
#
# for obj in objs:
# try:
# obj[par]
# except KeyError:
# print 'No input chain for %s, skipping'%(par)
# continue
# try:
# GreedyRes[par]
# except KeyError:
# print 'No bin size for %s, skipping'%(par)
# continue
# binParams={par: GreedyRes[par]}
# toppoints,injectionconfidence,reses,injection_area=bppu.greedy_bin_one_param(obj,binParams, confidencelevels)
# oneDContCL, oneDContInj = bppu.contigious_interval_one_param(obj, binParams, confidencelevels)
print 'Calculating std accuracies'
# Calculate Std Accuracies
stdacc = {}
mean = {}
std = {}
for par in params:
if not reduce(lambda a, b: a and b, map(lambda z: par in z.names,
objs)):
print '%s not found in all objects, skipping' % (par)
continue
stdacc[par] = []
mean[par] = []
std[par] = []
for obj in objs:
oneDpos = obj[par]
stdacc[par].append(oneDpos.stacc)
mean[par].append(oneDpos.mean)
std[par].append(oneDpos.stdev)
html_scatter = html.add_section('Standard Accuracy')
html_scatter_content = '<table>'
print 'Making std accuracy plots'
# Make a scatter plot for std accuracy against each injection parameter
for p1 in params: # X axis, injection values
try:
injval = map(lambda o: o._getinjpar(p1), objs)
except KeyError:
print 'Error! Unable to find parameter %s in injection!' % (p1)
continue
html_scatter_content += '<tr><td>%s</td>' % (p1)
for p2 in params: # Y axis
try:
stdacc[p2]
except KeyError:
print 'No stdacc data for %s, skipping' % (p2)
html_scatter_content += '<td>%s not found</td>' % (p2)
continue
fig = scatterAcc(injval, stdacc[p2], p1, p2)
figname = p1 + '-' + p2 + '.png'
figpath = os.path.join(accdir, figname)
fig.savefig(figpath)
html_scatter_content += '<td><img src="%s" alt="%s-%s" /></td>' % (
figpath, p1, p2)
html_scatter_content += '</tr>'
html_scatter_content += '</table>'
html_scatter.write(html_scatter_content)
print 'Making errorbar plots'
# Make an errorbar plot for each parameter against each injection parameter
html_err = html.add_section('Parameter Estimates')
html_err_content = '<table>'
for p1 in params: # X axis, injection values
try:
injval = map(lambda o: o._getinjpar(p1), objs)
except KeyError:
print 'Error! Unable to find parameter %s in injection!' % (p1)
continue
html_err_content += '<tr><td>%s</td>' % (p1)
for p2 in params:
try:
mean[p2]
except KeyError:
print 'No mean for %s, skipping' % (p2)
html_err_content += '<td>%s not found</td>' % (p2)
continue
yinjval = map(lambda o: o._getinjpar(p2), objs)
fig = plt.figure()
plt.errorbar(injval, mean[p2], std[p2], linestyle='None')
plt.plot(injval, yinjval, 'gx')
plt.xlabel(p1)
plt.ylabel(p2)
figname = p1 + '-' + p2 + '.png'
figpath = os.path.join(errdir, figname)
fig.savefig(figpath)
html_err_content += '<td><img src="%s" alt="%s-%s" /></td>' % (
figpath, p1, p2)
html_err_content += '</tr>'
html_err_content += '</table>'
html_err.write(html_err_content)
# Box and whiskers plot for each parameter pair
html_box = html.add_section('Box plots')
html_box_content = '<table>'
print 'Making box plots'
for p1 in params:
# Error checking to be put here
injval = map(lambda o: o._getinjpar(p1), objs)
html_box_content += '<tr><td>%s</td>' % (p1)
for p2 in params:
try:
mean[p2]
except KeyError:
print 'No mean for %s, skipping' % (p2)
html_box_content += '<td>%s not found</td>' % (p2)
continue
posteriors = map(lambda o: o[p2].samples, objs)
yinjval = map(lambda o: o._getinjpar(p2), objs)
fig = plt.figure()
upper = max(injval)
lower = min(injval)
boxwidth = 0.75 * (upper - lower) / len(injval)
plt.boxplot(posteriors, positions=injval, widths=boxwidth)
plt.plot(injval, yinjval, 'gx')
plt.xlabel(p1)
plt.ylabel(p2)
plt.xlim(lower - 0.5 * boxwidth, upper + 0.5 * boxwidth)
figname = p1 + '-' + p2 + '.png'
figpath = os.path.join(boxdir, figname)
fig.savefig(figpath)
html_box_content += '<td><img src="%s" alt="%s-%s" /></td>' % (
figpath, p1, p2)
html_box_content += '</tr>'
html_box_content += '</table>'
html_box.write(html_box_content)
html_footer = html.add_section('')
html_footer.p('Produced using cbcBayesInjProc.py at ' +
strftime("%Y-%m-%d %H:%M:%S") + ' .')
html_footer.p(git_version.verbose_msg)
# Save page
resultspage = open(os.path.join(outdir, 'injectionsummary.html'), 'w')
resultspage.write(str(html))
resultspage.close()
def cbcBayesConvergence(
outdir,
data,
#Number of live points used in data
ns_Nlive,
#Threshold for failure for gelman-rubin test
gelmanthresh=1.01
#
):
"""
This is a script which calculates convergence statistics for nested
sampling runs.
"""
if data is None:
raise RuntimeError('You must specify an input data file')
#
if outdir is None:
raise RuntimeError("You must specify an output directory.")
if not os.path.isdir(outdir):
os.makedirs(outdir)
#
import string
from numpy import loadtxt
pos_samples = []
new_data = []
for d in reversed(data):
temp = [d]
new_data.append(temp)
peparser = bppu.PEOutputParser('ns')
posfilename = os.path.join(outdir, 'posterior_samples.dat')
for i in range(len(data)):
# Create a posterior object (Npost=None avoids repeated samples which ruin the KS test)
commonResultsObj = peparser.parse(new_data[i],
Nlive=ns_Nlive,
Npost=None)
pos = bppu.Posterior(commonResultsObj)
pos.write_to_file(posfilename)
with open(posfilename) as f:
param_arr = string.split(f.readline())
loadfile = loadtxt(f)
pos_samples.append(loadfile)
#==================================================================#
#Create webpage with nested sampling convergence information
#==================================================================#
import pylal.nsconvergence as nsc
runs = len(pos_samples)
html_nsconvergence = bppu.htmlPage('Convergence Information',
css=bppu.__default_css_string)
convergencedir = os.path.join(outdir, 'convergence')
if not os.path.isdir(convergencedir):
os.makedirs(convergencedir)
#Summary Section
html_nsconvergence_stats = html_nsconvergence.add_section('Summary')
max_l, l_diff = nsc.compare_maxl(pos_samples, param_arr)
html_nsconvergence_stats.p('Max difference in loglikelihood: %f' % l_diff)
summary_table_string = ''
summary_table_header = '<table border="1"><tr><th>Run</th><th>maxloglikelihood</th>'
#maxposterior column
if param_arr.count('prior') > 0:
max_pos, pos_diff = nsc.compare_maxposterior(pos_samples, param_arr)
html_nsconvergence_stats.p('Max difference in posterior: %f' %
pos_diff)
summary_table_header += '<th>maxposterior</th>'
summary_table_header += '</tr>'
summary_table_string += summary_table_header
for i in range(runs):
max_l_val = max_l[i]
summary_table_string += '<tr><td>%i</td><td>%f</td>' % (i, max_l_val)
if param_arr.count('prior') > 0:
max_pos_val = max_pos[i]
summary_table_string += '<td>%f</td>' % max_pos_val
summary_table_string += '</tr>'
summary_table_string += '</table>'
html_nsconvergence_stats.write(summary_table_string)
#KS Test Section
html_nsconvergence_ks = html_nsconvergence.add_section('KS Test')
ks_arr = nsc.kstest(pos_samples, param_arr, convergencedir)
for index, p in enumerate(param_arr):
ks_table_string = '<table><caption>%s</caption><tr><th></th>' % p
for i in range(runs):
ks_table_string += '<th>Run%i</th>' % i
ks_table_string += '</tr>'
for i in range(runs):
ks_table_string += '<tr><th>Run%i</th>' % i
for j in range(i * runs, (i * runs) + runs):
pval = ks_arr[index][j]
ks_table_string += '<td>%f</td>' % pval
ks_table_string += '</tr>'
ks_table_string += '</table>'
html_nsconvergence_ks.write(ks_table_string)
for p in param_arr:
html_nsconvergence_ks.write(
'<a href="./convergence/ks/' + p +
'_ks.png" target="_blank"><img width="35%" src="./convergence/ks/'
+ p + '_ks.png"/></a>')
#Gelman Rubin Section
html_nsconvergence_gelman = html_nsconvergence.add_section('Gelman Rubin')
gelmandir = os.path.join(convergencedir, 'gelmanrubin')
if not os.path.isdir(gelmandir):
os.makedirs(gelmandir)
gelmanrubin = nsc.gelman_rubin(pos_samples, param_arr, gelmandir)
warn = False
warnparams = []
for index, g in enumerate(gelmanrubin):
if g > gelmanthresh:
warn = True
warnparams.append(index)
if warn:
with open(outdir + '/warning.txt', 'w') as warnfile:
warnfile.write('Gelman-Rubin threshold set to %f\n' % gelmanthresh)
for i in warnparams:
warnfile.write('%s has an R-value of %f\n' %
(param_arr[i], gelmanrubin[i]))
colors = ['b', 'r', 'g', 'c', 'k', 'm', 'y', .25, .5, .75]
for param_index, param in enumerate(param_arr):
for i in range(runs):
data_range = []
for j in range(len(pos_samples[i])):
data_range.append(j)
col = nsc.get_data_col(pos_samples[i], param_arr, param)
plt.figure(param_index)
plt.scatter(data_range, col, c=colors[i], s=5, edgecolors='none')
plt.title('R = ' + str(gelmanrubin[param_index]))
plt.xlabel('Sample')
plt.ylabel(param)
plt.xlim(0, len(pos_samples[i]))
plt.ylim(min(col), max(col))
plt.savefig(gelmandir + '/' + param)
for p in param_arr:
html_nsconvergence_gelman.write(
'<a href="./convergence/gelmanrubin/' + p +
'.png" target="_blank"><img width="35%" src="./convergence/gelmanrubin/'
+ p + '.png"/></a>')
#Write convergence page
nsconvergencepage = open(os.path.join(outdir, 'convergence.html'), 'w')
nsconvergencepage.write(str(html_nsconvergence))
nsconvergencepage.close()
def makeOutputPage(objs, params, outdir, confidencelevels):
"""
Make a summary page with table of results and plots for each param in params
"""
if not os.path.isdir(outdir):
os.makedirs(outdir)
#Bin size/resolution for binning. Need to match (converted) column names.
GreedyRes={'mc':0.025,'m1':0.1,'m2':0.1,'mass1':0.1,'mass2':0.1,'mtotal':0.1,'eta':0.001,'iota':0.01,'time':1e-3,'distance':1.0,'dist':1.0,'mchirp':0.025,'a1':0.02,'a2':0.02,'phi1':0.05,'phi2':0.05,'theta1':0.05,'theta2':0.05,'ra':0.05,'dec':0.05}
html=bppu.htmlPage('Injection Summary',css=bppu.__default_css_string)
html_meta=html.add_section('Summary')
html_meta.p('Analysed %i injections.'%(len(objs)))
# Make a directory for stdacc and errorbar plots
accdir=os.path.join(outdir,'stdacc')
if not os.path.isdir(accdir):
os.makedirs(accdir)
errdir=os.path.join(outdir,'errbar')
if not os.path.isdir(errdir):
os.makedirs(errdir)
boxdir=os.path.join(outdir,'boxplot')
if not os.path.isdir(boxdir):
os.makedirs(boxdir)
# Calculate confidence intervals for each injection and parameter
#for par in params:
# par=par.lower()
# print 'Binning %s to determine confidence intervals'%(par)
#
# for obj in objs:
# try:
# obj[par]
# except KeyError:
# print 'No input chain for %s, skipping'%(par)
# continue
# try:
# GreedyRes[par]
# except KeyError:
# print 'No bin size for %s, skipping'%(par)
# continue
# binParams={par: GreedyRes[par]}
# toppoints,injectionconfidence,reses,injection_area=bppu.greedy_bin_one_param(obj,binParams, confidencelevels)
# oneDContCL, oneDContInj = bppu.contigious_interval_one_param(obj, binParams, confidencelevels)
print 'Calculating std accuracies'
# Calculate Std Accuracies
stdacc={}
mean={}
std={}
for par in params:
if not reduce( lambda a,b: a and b, map(lambda z: par in z.names, objs)):
print '%s not found in all objects, skipping'%(par)
continue
stdacc[par]=[]
mean[par]=[]
std[par]=[]
for obj in objs:
oneDpos=obj[par]
stdacc[par].append(oneDpos.stacc)
mean[par].append(oneDpos.mean)
std[par].append(oneDpos.stdev)
html_scatter=html.add_section('Standard Accuracy')
html_scatter_content='<table>'
print 'Making std accuracy plots'
# Make a scatter plot for std accuracy against each injection parameter
for p1 in params: # X axis, injection values
try:
injval=map(lambda o: o._getinjpar(p1), objs)
except KeyError:
print 'Error! Unable to find parameter %s in injection!'%(p1)
continue
html_scatter_content+='<tr><td>%s</td>'%(p1)
for p2 in params: # Y axis
try:
stdacc[p2]
except KeyError:
print 'No stdacc data for %s, skipping'%(p2)
html_scatter_content+='<td>%s not found</td>'%(p2)
continue
fig = scatterAcc(injval,stdacc[p2],p1,p2)
figname=p1+'-'+p2+'.png'
figpath=os.path.join(accdir,figname)
fig.savefig(figpath)
html_scatter_content+='<td><img src="%s" alt="%s-%s" /></td>'%(figpath,p1,p2)
html_scatter_content+='</tr>'
html_scatter_content+='</table>'
html_scatter.write(html_scatter_content)
print 'Making errorbar plots'
# Make an errorbar plot for each parameter against each injection parameter
html_err=html.add_section('Parameter Estimates')
html_err_content='<table>'
for p1 in params: # X axis, injection values
try:
injval=map(lambda o: o._getinjpar(p1),objs)
except KeyError:
print 'Error! Unable to find parameter %s in injection!'%(p1)
continue
html_err_content+='<tr><td>%s</td>'%(p1)
for p2 in params:
try:
mean[p2]
except KeyError:
print 'No mean for %s, skipping'%(p2)
html_err_content+='<td>%s not found</td>'%(p2)
continue
yinjval=map(lambda o: o._getinjpar(p2), objs)
fig = plt.figure()
plt.errorbar(injval,mean[p2],std[p2],linestyle='None')
plt.plot(injval,yinjval,'gx')
plt.xlabel(p1)
plt.ylabel(p2)
figname=p1+'-'+p2+'.png'
figpath=os.path.join(errdir,figname)
fig.savefig(figpath)
html_err_content+='<td><img src="%s" alt="%s-%s" /></td>'%(figpath,p1,p2)
html_err_content+='</tr>'
html_err_content+='</table>'
html_err.write(html_err_content)
# Box and whiskers plot for each parameter pair
html_box=html.add_section('Box plots')
html_box_content='<table>'
print 'Making box plots'
for p1 in params:
# Error checking to be put here
injval=map(lambda o: o._getinjpar(p1),objs)
html_box_content+='<tr><td>%s</td>'%(p1)
for p2 in params:
try:
mean[p2]
except KeyError:
print 'No mean for %s, skipping'%(p2)
html_box_content+='<td>%s not found</td>'%(p2)
continue
posteriors=map(lambda o: o[p2].samples, objs)
yinjval=map(lambda o: o._getinjpar(p2),objs)
fig=plt.figure()
upper=max(injval)
lower=min(injval)
boxwidth=0.75*(upper-lower)/len(injval)
plt.boxplot(posteriors,positions=injval,widths=boxwidth )
plt.plot(injval,yinjval,'gx')
plt.xlabel(p1)
plt.ylabel(p2)
plt.xlim(lower-0.5*boxwidth,upper+0.5*boxwidth)
figname=p1+'-'+p2+'.png'
figpath=os.path.join(boxdir,figname)
fig.savefig(figpath)
html_box_content+='<td><img src="%s" alt="%s-%s" /></td>'%(figpath,p1,p2)
html_box_content+='</tr>'
html_box_content+='</table>'
html_box.write(html_box_content)
html_footer=html.add_section('')
html_footer.p('Produced using cbcBayesInjProc.py at '+strftime("%Y-%m-%d %H:%M:%S")+' .')
html_footer.p(git_version.verbose_msg)
# Save page
resultspage=open(os.path.join(outdir,'injectionsummary.html'),'w')
resultspage.write(str(html))
resultspage.close()
if len(opts.pos_list)!=len(names):
print "Either add names for all posteriors or dont put any at all!"
greedy2savepaths,oned_data,confidence_uncertainty,confidence_levels,max_logls=compare_bayes(outpath,zip(names,opts.pos_list),opts.inj,opts.eventnum,opts.username,opts.password,opts.reload_flag,opts.clf,opts.ldg_flag,contour_figsize=(float(opts.cw),float(opts.ch)),contour_dpi=int(opts.cdpi),contour_figposition=[0.15,0.15,float(opts.cpw),float(opts.cph)],fail_on_file_err=not opts.readFileErr,covarianceMatrices=opts.covarianceMatrices,meanVectors=opts.meanVectors,Npixels2D=int(opts.npixels_2d))
####Print Confidence Levels######
output_confidence_levels_tex(confidence_levels,outpath)
output_confidence_levels_dat(confidence_levels,outpath)
####Save confidence uncertainty#####
output_confidence_uncertainty(confidence_uncertainty,outpath)
####Print HTML!#######
compare_page=bppu.htmlPage('Compare PDFs (single event)',css=bppu.__default_css_string)
param_section=compare_page.add_section('Meta')
param_section_write='<div><p>This comparison was created from the following analyses</p>'
param_section_write+='<table border="1">'
param_section_write+='<th>Analysis</th> <th> max(log(L)) </th>'
for name,logl_max in max_logls:
param_section_write+='<tr><td><a href="%s">%s</a></td> <td>%g</td></tr>'%(dict(zip(names,opts.pos_list))[name],name,logl_max)
param_section_write+='</table></div>'
param_section.write(param_section_write)
param_section.write('<div><p><a href="confidence_table.tex">LaTeX table</a> of medians and confidence levels.</p></div>')
if oned_data:
param_section=compare_page.add_section('1D marginal posteriors')
def cbcBayesConvergence(
outdir,data,
#Number of live points used in data
ns_Nlive,
#Threshold for failure for gelman-rubin test
gelmanthresh=1.01
#
):
"""
This is a script which calculates convergence statistics for nested
sampling runs.
"""
if data is None:
raise RuntimeError('You must specify an input data file')
#
if outdir is None:
raise RuntimeError("You must specify an output directory.")
if not os.path.isdir(outdir):
os.makedirs(outdir)
#
import string
from numpy import loadtxt
pos_samples = []
new_data = []
for d in reversed(data):
temp = [d]
new_data.append(temp)
peparser=bppu.PEOutputParser('ns')
posfilename=os.path.join(outdir,'posterior_samples.dat')
for i in range(len(data)):
# Create a posterior object (Npost=None avoids repeated samples which ruin the KS test)
commonResultsObj=peparser.parse(new_data[i],Nlive=ns_Nlive,Npost=None)
pos = bppu.Posterior(commonResultsObj)
pos.write_to_file(posfilename)
with open(posfilename) as f:
param_arr = string.split(f.readline())
loadfile = loadtxt(f)
pos_samples.append(loadfile)
#==================================================================#
#Create webpage with nested sampling convergence information
#==================================================================#
import pylal.nsconvergence as nsc
runs = len(pos_samples)
html_nsconvergence=bppu.htmlPage('Convergence Information', css=bppu.__default_css_string)
convergencedir = os.path.join(outdir, 'convergence')
if not os.path.isdir(convergencedir):
os.makedirs(convergencedir)
#Summary Section
html_nsconvergence_stats=html_nsconvergence.add_section('Summary')
max_l, l_diff = nsc.compare_maxl(pos_samples, param_arr)
html_nsconvergence_stats.p('Max difference in loglikelihood: %f'%l_diff)
summary_table_string = ''
summary_table_header = '<table border="1"><tr><th>Run</th><th>maxloglikelihood</th>'
#maxposterior column
if param_arr.count('prior') > 0:
max_pos, pos_diff = nsc.compare_maxposterior(pos_samples, param_arr)
html_nsconvergence_stats.p('Max difference in posterior: %f'%pos_diff)
summary_table_header += '<th>maxposterior</th>'
summary_table_header += '</tr>'
summary_table_string += summary_table_header
for i in range(runs):
max_l_val = max_l[i]
summary_table_string += '<tr><td>%i</td><td>%f</td>'%(i,max_l_val)
if param_arr.count('prior') > 0:
max_pos_val = max_pos[i]
summary_table_string += '<td>%f</td>'%max_pos_val
summary_table_string += '</tr>'
summary_table_string += '</table>'
html_nsconvergence_stats.write(summary_table_string)
#KS Test Section
html_nsconvergence_ks=html_nsconvergence.add_section('KS Test')
ks_arr = nsc.kstest(pos_samples, param_arr, convergencedir)
for index, p in enumerate(param_arr):
ks_table_string = '<table><caption>%s</caption><tr><th></th>'%p
for i in range(runs):
ks_table_string += '<th>Run%i</th>'%i
ks_table_string+='</tr>'
for i in range(runs):
ks_table_string += '<tr><th>Run%i</th>'%i
for j in range(i*runs,(i*runs)+runs):
pval = ks_arr[index][j]
ks_table_string += '<td>%f</td>'%pval
ks_table_string += '</tr>'
ks_table_string += '</table>'
html_nsconvergence_ks.write(ks_table_string)
for p in param_arr:
html_nsconvergence_ks.write('<a href="./convergence/ks/'+p+'_ks.png" target="_blank"><img width="35%" src="./convergence/ks/'+p+'_ks.png"/></a>')
#Gelman Rubin Section
html_nsconvergence_gelman=html_nsconvergence.add_section('Gelman Rubin')
gelmandir = os.path.join(convergencedir,'gelmanrubin')
if not os.path.isdir(gelmandir):
os.makedirs(gelmandir)
gelmanrubin = nsc.gelman_rubin(pos_samples, param_arr, gelmandir)
warn = False
warnparams = []
for index,g in enumerate(gelmanrubin):
if g > gelmanthresh:
warn = True
warnparams.append(index)
if warn:
with open(outdir+'/warning.txt', 'w') as warnfile:
warnfile.write('Gelman-Rubin threshold set to %f\n'%gelmanthresh)
for i in warnparams:
warnfile.write('%s has an R-value of %f\n'%(param_arr[i], gelmanrubin[i]))
colors = ['b', 'r', 'g', 'c', 'k', 'm', 'y', .25, .5, .75]
for param_index, param in enumerate(param_arr):
for i in range(runs):
data_range = []
for j in range(len(pos_samples[i])):
data_range.append(j)
col = nsc.get_data_col(pos_samples[i], param_arr, param)
plt.figure(param_index)
plt.scatter(data_range, col, c = colors[i], s = 5, edgecolors = 'none')
plt.title('R = ' + str(gelmanrubin[param_index]))
plt.xlabel('Sample')
plt.ylabel(param)
plt.xlim(0,len(pos_samples[i]))
plt.ylim(min(col),max(col))
plt.savefig(gelmandir+'/'+param)
for p in param_arr:
html_nsconvergence_gelman.write('<a href="./convergence/gelmanrubin/'+p+'.png" target="_blank"><img width="35%" src="./convergence/gelmanrubin/'+p+'.png"/></a>')
#Write convergence page
nsconvergencepage=open(os.path.join(outdir, 'convergence.html'), 'w')
nsconvergencepage.write(str(html_nsconvergence))
nsconvergencepage.close()
