def scoring(fname, n, test):
# load test data
a_test, age_err, age_errp, a_errm, p_test, p_err, bv_test, bv_err, g, g_err, \
g_errp, g_errm, flag = load_dat(fname, test, cv=True)
# load parameters from training data
data = np.genfromtxt('/Users/angusr/Python/noisy-plane/parameters%s%s.txt'%(n,fname)).T
pars = data[0][:3]
# calculate score
p_pred = period_model(pars, a_test, bv_test, .45)
l = np.isfinite(p_pred)
n = len(p_pred[l])
# root mean squared error
return np.sqrt((np.sum((p_test[l] - p_pred[l])**2))/n)
pars[:3] = data[0][:3]
pars[3] = 0.45
print age, log_age_model(pars, np.log10(p[i]), bv[i])
if __name__ == "__main__":
loo()
raw_input('enter')
trains = ['CF45', 'HF45', 'PF45', 'PF5']
tests = ['AHP', 'ACP', 'ACH', 'ACH']
RMS = []
for i in range(len(tests)):
# load test data
a_test, age_err, age_errp, a_errm, p_test, p_err, bv_test, bv_err, g, g_err, \
g_errp, g_errm, flag = load_dat(tests[i], False, False)
print len(p_test)
# load parameters from training data
data = np.genfromtxt('/Users/angusr/Python/noisy-plane/parameters%s.txt'%trains[i]).T
pars = data[0][:3]
# calculate score
p_pred = period_model(pars, a_test, bv_test, .45)
l = np.isfinite(p_pred)
n = len(p_pred[l])
# root mean squared error
RMS.append(np.sqrt((np.sum(((p_test[l] - p_pred[l])**2)))/n))
def MCMC(fname, n, c, train, cv, sampling):
# load MAP values
try:
params = np.genfromtxt('parameters%s.txt'%fname).T
par_true = params[0]
print 'initialising with MAP values'
print par_true
except:
# par_true = [0.7725, 0.5189, .601, 5., 10., \ # Barnes
par_true = [0.6, 0.5189, .601, 5., 10., \
8., 30., 9., 5., .67] # better initialisation
print par_true
# load real data
age_obs, age_err, age_errp, age_errm, period_obs, period_err, bv_obs, bv_err, \
logg_obs, logg_err, logg_errp, logg_errm, flag = load_dat(fname, train, cv)
pl.clf()
pl.errorbar(age_obs, period_obs, xerr=age_err, yerr=period_err, fmt='k.',
capsize=0, ecolor='.8')
# pl.show()
# Now generate samples
nsamp = 100 # FIXME
np.random.seed(12)
age_samp = np.vstack([x0+xe*np.random.randn(nsamp) for x0, xe in zip(age_obs, age_err)])
np.random.seed(12)
bv_samp = np.vstack([x0+xe*np.random.randn(nsamp) for x0, xe in zip(bv_obs, bv_err)])
np.random.seed(12)
logg_samp = np.vstack([x0+xe*np.random.randn(nsamp) for x0, xe in zip(logg_obs, logg_err)])
np.random.seed(12)
period_samp = np.vstack([x0+xe*np.random.randn(nsamp) for x0, xe in zip(period_obs, period_err)])
if sampling:
print 'initial likelihood = ', lnlike(par_true, age_samp, bv_samp, \
period_samp, logg_samp, age_obs, age_err, bv_obs, bv_err, period_obs, period_err, \
logg_obs, logg_err, c)
else:
print 'initial likelihood = ', nslnlike(par_true, age_samp, bv_samp, \
period_samp, logg_samp, age_obs, age_err, bv_obs, bv_err, period_obs, period_err, \
logg_obs, logg_err, c)
nwalkers, ndim = 32, len(par_true)
p0 = [par_true+1e-4*np.random.rand(ndim) for i in range(nwalkers)]
args = (age_samp, bv_samp, period_samp, logg_samp, age_obs, age_err, bv_obs, \
bv_err, period_obs, period_err, logg_obs, logg_err, c, sampling)
sampler = emcee.EnsembleSampler(nwalkers, ndim, lnprob, args = args)
print("Burn-in")
p0, lp, state = sampler.run_mcmc(p0, 5000)
# p0, lp, state = sampler.run_mcmc(p0, 300)
sampler.reset()
print("Production run")
# nstep = 3000
# nruns = 500.
nstep = 20000
nruns = 2000.
for j in range(int(nstep/nruns)):
print fname, n
print datetime.datetime.now()
print 'run', j
p0, lp, state = sampler.run_mcmc(p0, nruns)
flat = sampler.chain[:, 50:, :].reshape((-1, ndim))
mcmc_result = map(lambda v: (v[1], v[2]-v[1], v[1]-v[0]),
zip(*np.percentile(flat, [16, 50, 84], axis=0)))
mres = np.array(mcmc_result)[:, 0]
print 'mcmc_result = ', mres
print "saving samples"
f = h5py.File("samples_%s" %fname, "w")
data = f.create_dataset("samples", np.shape(sampler.chain))
data[:,:] = np.array(sampler.chain)
f.close()
samples = sampler.chain[:, 50:, :].reshape((-1, ndim))
likelihood = lnlike(mres, age_samp, bv_samp, period_samp,
logg_samp, age_obs, age_err, bv_obs, bv_err,
period_obs, period_err, logg_obs, logg_err, c)
print 'likelihood = ', likelihood
# np.savetxt('likelihood%s%s.txt'%(n, fname), likelihood)
# save parameters and print to screen
print 'initial values', par_true
np.savetxt("parameters%s%s.txt" %(n, fname), np.array(mcmc_result))
mcmc_result = np.array(mcmc_result)[:, 0]
mcmc_result = [mcmc_result[0], mcmc_result[1], mcmc_result[2], c, \
mcmc_result[3], mcmc_result[4]]
# save samples
f = h5py.File("samples_%s%s" %(n, fname), "w")
data = f.create_dataset("samples", np.shape(sampler.chain))
data[:,:] = np.array(sampler.chain)
f.close()
