def test_coin_sample_post(self):
"""Test sampling from posterior distribution"""
outdir = 'test/tmp/test_hmm/test_coin_sample_post/'
make_clean_dir(outdir)
model = make_coin_model()
# sample states and data
ndata = 100
states = list(islice(hmm.sample_hmm_states(model), ndata))
data = list(hmm.sample_hmm_data(model, states))
model.prob_emission = (
lambda pos, state: model.prob_emission_data(state, data[pos]))
p = Gnuplot()
p.enableOutput(False)
p.plot(states, style="lines")
probs = hmm.get_posterior_probs(model, len(data))
states2 = [exp(probs[i][1]) for i in xrange(len(data))]
p.plot(util.vadds(states2, 1.5), style="lines", miny=-1, maxy=12)
for i in range(2, 10):
states2 = hmm.sample_posterior(model, ndata)
self.assertTrue(stats.corr(states, states2) > .5)
p.plot(util.vadds(states2, 1.5 * i),
style="lines",
miny=-1,
maxy=12)
p.enableOutput(True)
p.save(outdir + 'plot.png')
def test_coin_sample_post(self):
"""Test sampling from posterior distribution"""
outdir = 'test/tmp/test_hmm/test_coin_sample_post/'
make_clean_dir(outdir)
model = make_coin_model()
# sample states and data
ndata = 100
states = list(islice(hmm.sample_hmm_states(model), ndata))
data = list(hmm.sample_hmm_data(model, states))
model.prob_emission = (lambda pos, state:
model.prob_emission_data(state, data[pos]))
p = Gnuplot()
p.enableOutput(False)
p.plot(states, style="lines")
probs = hmm.get_posterior_probs(model, len(data))
states2 = [exp(probs[i][1]) for i in xrange(len(data))]
p.plot(util.vadds(states2, 1.5), style="lines", miny=-1, maxy=12)
for i in range(2, 10):
states2 = hmm.sample_posterior(model, ndata)
self.assertTrue(stats.corr(states, states2) > .5)
p.plot(util.vadds(states2, 1.5*i), style="lines", miny=-1, maxy=12)
p.enableOutput(True)
p.save(outdir + 'plot.png')
def test_coin(self):
"""Test that viterbi and posterior coding work well."""
outdir = 'test/tmp/test_hmm/test_coin/'
make_clean_dir(outdir)
model = make_coin_model()
# sample states
ndata = 100
states = list(islice(hmm.sample_hmm_states(model), ndata))
p = Gnuplot()
p.enableOutput(False)
p.plot(states, style="lines")
# sample data
data = list(hmm.sample_hmm_data(model, states))
# viterbi
model.prob_emission = (
lambda pos, state: model.prob_emission_data(state, data[pos]))
states2 = hmm.viterbi(model, len(data))
# posterior
probs = hmm.get_posterior_probs(model, len(data))
states3 = [exp(probs[i][1]) for i in xrange(len(data))]
# assert that inferences correlates with true state
self.assertTrue(stats.corr(states, states2) > .5)
self.assertTrue(stats.corr(states, states3) > .5)
# plot inference
p.plot(util.vadds(states2, 1.5), style="lines", miny=-1, maxy=4)
p.plot(util.vadds(states3, 2.5), style="lines", miny=-1, maxy=4)
p.enableOutput(True)
p.save(outdir + 'plot.png')
def test_coin(self):
"""Test that viterbi and posterior coding work well."""
outdir = 'test/tmp/test_hmm/test_coin/'
make_clean_dir(outdir)
model = make_coin_model()
# sample states
ndata = 100
states = list(islice(hmm.sample_hmm_states(model), ndata))
p = Gnuplot()
p.enableOutput(False)
p.plot(states, style="lines")
# sample data
data = list(hmm.sample_hmm_data(model, states))
# viterbi
model.prob_emission = (lambda pos, state:
model.prob_emission_data(state, data[pos]))
states2 = hmm.viterbi(model, len(data))
# posterior
probs = hmm.get_posterior_probs(model, len(data))
states3 = [exp(probs[i][1]) for i in xrange(len(data))]
# assert that inferences correlates with true state
self.assertTrue(stats.corr(states, states2) > .5)
self.assertTrue(stats.corr(states, states3) > .5)
# plot inference
p.plot(util.vadds(states2, 1.5), style="lines", miny=-1, maxy=4)
p.plot(util.vadds(states3, 2.5), style="lines", miny=-1, maxy=4)
p.enableOutput(True)
p.save(outdir + 'plot.png')
def test_top(self):
outdir = 'test/tmp/test_coal/BMC_test_top/'
make_clean_dir(outdir)
stree = treelib.parse_newick(
"(((A:200, E:200):800, B:1000):500, (C:700, D:700):800);")
n = 500
T = 2000
nsamples = 4000
# compare top hist with simpler rejection sampling
tops = {}
tops2 = {}
for i in xrange(nsamples):
# use rejection sampling
tree, recon = coal.sample_bounded_multicoal_tree_reject(
stree, n, T, namefunc=lambda x: x)
# sample tree
tree2, recon2 = coal.sample_bounded_multicoal_tree(
stree, n, T, namefunc=lambda x: x)
top = phylo.hash_tree(tree)
top2 = phylo.hash_tree(tree2)
tops.setdefault(top, [0, tree, recon])[0] += 1
tops.setdefault(top2, [0, tree2, recon2])
tops2.setdefault(top2, [0, tree2, recon2])[0] += 1
tops2.setdefault(top, [0, tree, recon])
keys = tops.keys()
x = [safelog(tops[i][0], default=0) for i in keys]
y = [safelog(tops2[i][0], default=0) for i in keys]
self.assertTrue(stats.corr(x, y) > .9)
p = Gnuplot()
p.enableOutput(False)
p.plot(x, y)
p.plot([min(x), max(x)], [min(x), max(x)], style="lines")
p.enableOutput(True)
p.save(outdir + 'plot.png')
