def lnprob(theta, x, y, yerr):
lp = lnprior(theta)
if not np.isfinite(lp):
return -np.inf
try:
return lp + lnlike(theta, x, y, yerr)
except:
print theta
raise
def lnprob(theta, x, y, yerr):
lp = lnprior(theta)
if not np.isfinite(lp):
return -np.inf
try:
return lp + lnlike(theta, x, y, yerr)
except:
print theta
raise
# theta = [0., 0, .5, .5, 0.] # inital try
theta = [0., .2, .5, .5, 6.2] # better parameterisation
theta = ml_theta
# plot data
pl.clf()
pl.errorbar(x, y, yerr=yerr, fmt='k.')
xs = np.linspace(min(x), max(x), 500)
pl.plot(xs, predict(xs, x, y, yerr, theta)[0], 'r-')
pl.xlabel('time (days)')
pl.savefig('data')
raw_input('enter')
print "Initial parameters = (exp)", theta
start = time.clock()
print "Initial lnlike = ", lnlike(theta, x, y, yerr),"\n"
elapsed = (time.clock() - start)
print 'time =', elapsed
# Sample the posterior probability for m.
nwalkers, ndim = 64, len(theta)
p0 = [theta+1e-4*np.random.rand(ndim) for i in range(nwalkers)]
sampler = emcee.EnsembleSampler(nwalkers, ndim, lnprob, args = (x, y, yerr))
bi, pr = 500, 1000
# print 'predicted time = ', (elapsed*bi+elapsed*pr)
start = time.clock()
print("Burn-in")
p0, lp, state = sampler.run_mcmc(p0, bi)
sampler.reset()
print("Production run")
sampler.run_mcmc(p0, pr)
q = tbdata["SAP_QUALITY"]
# remove nans
n = np.isfinite(x)*np.isfinite(y)*np.isfinite(yerr)*(q==0)
l = 500.
x = x[n][:l]
y = y[n][:l]
yerr = yerr[n][:l]
mu = np.median(y)
y = y/mu - 1.
yerr /= mu
pl.clf()
pl.errorbar(x, y, yerr=yerr, fmt='k.')
pl.xlabel('time (days)')
pl.savefig('data')
theta = [1e-8, 1., 10., 2.]
P = np.arange(0.1, 5, 0.1)
L = np.empty_like(P)
for i, per in enumerate(P):
theta[1] = per
L[i] = lnlike(theta, x, y, yerr)
pl.clf()
pl.plot(P, L, 'k-')
pl.xlabel('Period (days)')
pl.ylabel('likelihood')
pl.savefig('likelihood2')
# theta = [0., 0, .5, .5, 0.] # inital try
theta = [0., .2, .5, .5, 6.2] # better parameterisation
theta = ml_theta
# plot data
pl.clf()
pl.errorbar(x, y, yerr=yerr, fmt='k.')
xs = np.linspace(min(x), max(x), 500)
pl.plot(xs, predict(xs, x, y, yerr, theta)[0], 'r-')
pl.xlabel('time (days)')
pl.savefig('data')
raw_input('enter')
print "Initial parameters = (exp)", theta
start = time.clock()
print "Initial lnlike = ", lnlike(theta, x, y, yerr), "\n"
elapsed = (time.clock() - start)
print 'time =', elapsed
# Sample the posterior probability for m.
nwalkers, ndim = 64, len(theta)
p0 = [theta + 1e-4 * np.random.rand(ndim) for i in range(nwalkers)]
sampler = emcee.EnsembleSampler(nwalkers, ndim, lnprob, args=(x, y, yerr))
bi, pr = 500, 1000
# print 'predicted time = ', (elapsed*bi+elapsed*pr)
start = time.clock()
print("Burn-in")
p0, lp, state = sampler.run_mcmc(p0, bi)
sampler.reset()
print("Production run")
sampler.run_mcmc(p0, pr)
