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_trans():
"""
Calculate transition probabilities
"""
create_data = False
if create_data:
make_clean_dir('test/data/test_trans')
k = 8
n = 1e4
rho = 1.5e-8 * 20
length = 1000
times = argweaver.get_time_points(ntimes=10, maxtime=200000)
popsizes = [n] * len(times)
ntests = 40
# generate test data
if create_data:
for i in range(ntests):
arg = arglib.sample_arg(k, 2*n, rho, start=0, end=length)
argweaver.discretize_arg(arg, times)
arg.write('test/data/test_trans/%d.arg' % i)
for i in range(ntests):
print 'arg', i
arg = arglib.read_arg('test/data/test_trans/%d.arg' % i)
argweaver.discretize_arg(arg, times)
pos = 10
tree = arg.get_marginal_tree(pos)
assert argweaverc.assert_transition_probs(tree, times, popsizes, rho)
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_cdf_coal_cond_counts(self):
# test coalescent pdf when conditioned on future lineage counts
outdir = 'test/tmp/test_coal/Coal_test_cdf_coal_cond_counts/'
make_clean_dir(outdir)
a = 5
for b in xrange(2, a):
t = 500
n = 1000
p = Gnuplot()
p.enableOutput(False)
p.plotfunc(lambda x: coal.cdf_coal_cond_counts(
x, a, b, t, n), 0, t, 10)
# draw single coal samples using rejection sampling
s = []
for i in xrange(1000):
while True:
times = coal.sample_coal_times(a, n)
if times[a-b-1] < t and (b == 1 or times[a-b] > t):
break
s.append(times[0])
x2, y2 = stats.cdf(s)
p.plot(x2, y2, style='lines')
p.enableOutput(True)
p.save(outdir + 'plot-%d.png' % b)
eq_sample_pdf(
x2, lambda x: coal.prob_coal_cond_counts(x, a, b, t, n), 40)
def test2(self):
outdir = 'test/tmp/test_vistrans/Vis_test2/'
make_clean_dir(outdir)
stree = treelib.parse_newick(stree_newick)
tree = treelib.read_tree(treefile2)
brecon = phylo.read_brecon(breconfile2, tree, stree)
transsvg.draw_tree(tree, brecon, stree, filename=outdir + "tree.svg")
def test2(self):
outdir = 'test/tmp/test_vistrans/Vis_test2/'
make_clean_dir(outdir)
stree = treelib.parse_newick(stree_newick)
tree = treelib.read_tree(treefile2)
brecon = phylo.read_brecon(breconfile2, tree, stree)
transsvg.draw_tree(tree, brecon, stree, filename=outdir + "tree.svg")
def test_install():
"""
Test installing compbio.
"""
make_clean_dir("test/tmp/install")
run_cmd("python setup.py clean > /dev/null")
run_cmd("python setup.py install --prefix=test/tmp/install > /dev/null")
assert os.path.exists("test/tmp/install/bin/viewtree")
def test_install():
"""
Test installing ARGweaver.
"""
make_clean_dir("test/tmp/install")
run_cmd("python setup.py clean > /dev/null")
run_cmd("make install prefix=test/tmp/install > /dev/null")
run_cmd("PYTHONPATH=test/tmp/install python -c 'import argweaver'")
assert os.path.exists("test/tmp/install/bin/arg-sample")
def test_install():
"""
Test installing ARGweaver.
"""
make_clean_dir("test/data/install")
run_cmd("python setup.py clean > /dev/null")
run_cmd("make install prefix=test/data/install > /dev/null")
run_cmd("PYTHONPATH=test/data/install python -c 'import argweaver'")
assert os.path.exists("test/data/install/bin/arg-sample")
def test3(self):
outdir = 'test/tmp/test_vistrans/Vis_test3/'
make_clean_dir(outdir)
stree = treelib.parse_newick(stree_newick)
tree = treelib.read_tree(treefile3)
brecon = phylo.read_brecon(breconfile3, tree, stree)
phylo.add_implied_spec_nodes_brecon(tree, brecon)
phylo.write_brecon(open(outdir + 'brecon', 'w'), brecon)
transsvg.draw_tree(tree, brecon, stree, filename=outdir + "tree.svg")
def test3(self):
outdir = 'test/tmp/test_vistrans/Vis_test3/'
make_clean_dir(outdir)
stree = treelib.parse_newick(stree_newick)
tree = treelib.read_tree(treefile3)
brecon = phylo.read_brecon(breconfile3, tree, stree)
phylo.add_implied_spec_nodes_brecon(tree, brecon)
phylo.write_brecon(open(outdir + 'brecon', 'w'), brecon)
transsvg.draw_tree(tree, brecon, stree, filename=outdir + "tree.svg")
def test_install_prog():
"""
Test installing ARGweaver program.
Use Makefile to install.
"""
make_clean_dir("test/tmp/install")
run_cmd("python setup.py clean > /dev/null")
run_cmd("make install prefix=test/tmp/install > /dev/null")
run_cmd("PYTHONPATH=test/tmp/install python -c 'import argweaver; "
"assert argweaver.argweaverc.argweaverclib'")
assert os.path.exists("test/tmp/install/bin/arg-sample")
def test_trans_switch():
"""
Calculate transition probabilities for switch matrix
Only calculate a single matrix
"""
create_data = False
if create_data:
make_clean_dir('test/data/test_trans_switch')
# model parameters
k = 12
n = 1e4
rho = 1.5e-8 * 20
length = 1000
times = argweaver.get_time_points(ntimes=20, maxtime=200000)
popsizes = [n] * len(times)
ntests = 100
# generate test data
if create_data:
for i in range(ntests):
# Sample ARG with at least one recombination.
while True:
arg = argweaver.sample_arg_dsmc(k,
2 * n,
rho,
start=0,
end=length,
times=times)
if any(x.event == "recomb" for x in arg):
break
arg.write('test/data/test_trans_switch/%d.arg' % i)
for i in range(ntests):
print('arg', i)
arg = arglib.read_arg('test/data/test_trans_switch/%d.arg' % i)
argweaver.discretize_arg(arg, times)
recombs = [x.pos for x in arg if x.event == "recomb"]
pos = recombs[0]
tree = arg.get_marginal_tree(pos - .5)
rpos, r, c = next(arglib.iter_arg_sprs(arg, start=pos - .5))
spr = (r, c)
if not argweaverc.assert_transition_switch_probs(
tree, spr, times, popsizes, rho):
tree2 = tree.get_tree()
treelib.remove_single_children(tree2)
treelib.draw_tree_names(tree2, maxlen=5, minlen=5)
assert False
def test_read_sites():
"""
Test reading site files.
"""
make_clean_dir("test/tmp/test_read_sites")
os.system("""bin/arg-sim \
-k 10 -L 10000 \
-N 1e4 -r 1.5e-8 -m 2.5e-8 \
--ntimes 10 --maxtime 400e3 \
-o test/tmp/test_read_sites/0 > /dev/null""")
sites = argweaverc.argweaver_read_sites('test/tmp/test_read_sites/0.sites',
-1, -1)
argweaverc.argweaver_delete_sites(sites)
def test_read_sites():
"""
Test reading site files.
"""
make_clean_dir("test/tmp/test_read_sites")
os.system("""bin/arg-sim \
-k 10 -L 10000 \
-N 1e4 -r 1.5e-8 -m 2.5e-8 \
--ntimes 10 --maxtime 400e3 \
-o test/tmp/test_read_sites/0 > /dev/null""")
sites = argweaverc.argweaver_read_sites(
'test/tmp/test_read_sites/0.sites', -1, -1)
argweaverc.argweaver_delete_sites(sites)
def test_trans_switch():
"""
Calculate transition probabilities for switch matrix
Only calculate a single matrix
"""
create_data = False
if create_data:
make_clean_dir('test/data/test_trans_switch')
# model parameters
k = 12
n = 1e4
rho = 1.5e-8 * 20
length = 1000
times = argweaver.get_time_points(ntimes=20, maxtime=200000)
popsizes = [n] * len(times)
ntests = 100
# generate test data
if create_data:
for i in range(ntests):
# Sample ARG with at least one recombination.
while True:
arg = argweaver.sample_arg_dsmc(
k, 2*n, rho, start=0, end=length, times=times)
if any(x.event == "recomb" for x in arg):
break
arg.write('test/data/test_trans_switch/%d.arg' % i)
for i in range(ntests):
print 'arg', i
arg = arglib.read_arg('test/data/test_trans_switch/%d.arg' % i)
argweaver.discretize_arg(arg, times)
recombs = [x.pos for x in arg if x.event == "recomb"]
pos = recombs[0]
tree = arg.get_marginal_tree(pos-.5)
rpos, r, c = arglib.iter_arg_sprs(arg, start=pos-.5).next()
spr = (r, c)
if not argweaverc.assert_transition_switch_probs(
tree, spr, times, popsizes, rho):
tree2 = tree.get_tree()
treelib.remove_single_children(tree2)
treelib.draw_tree_names(tree2, maxlen=5, minlen=5)
assert False
def test_install_lib():
"""
Test installing ARGweaver python lib.
Use setup.py to install and check that module can be imported.
Also ensure that c library is installed.
"""
make_clean_dir("test/tmp/install_lib")
run_cmd("python setup.py clean > /dev/null")
run_cmd(
"python setup.py install --prefix=test/tmp/install_lib "
"--install-lib=test/tmp/install_lib/lib/python/site-packages "
"> /dev/null")
run_cmd("cd test; PYTHONPATH=tmp/install_lib/lib/python/site-packages "
"python -c 'import argweaver; "
"assert argweaver.argweaverc.argweaverclib'")
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')
def test_sample_lineages(self):
"""lineage over time"""
outdir = 'test/tmp/test_arglib/Arg_test_sample_lineages/'
make_clean_dir(outdir)
rho = 1.5e-8 # recomb/site/gen
l = 5000 # length of locus
k = 60 # number of lineages
n = 2*10000 # effective popsize
r = rho * l # recomb/locus/gen
rplot_start(outdir + '/plot.pdf')
rp.plot([1, 40000], [1, k], t="n", log="xy")
times, events = arglib.sample_coal_recomb_times(k, n, r)
lineages = list(arglib.lineages_over_time(k, events))
rp.lines(times, lineages)
rplot_end()
def test_install_sdist():
"""
Test installing ARGweaver from a sdist.
"""
make_clean_dir("test/tmp/install_sdist")
run_cmd("python setup.py clean > /dev/null")
run_cmd("python setup.py sdist --dist-dir=test/tmp/install_sdist")
run_cmd("cd test/tmp/install_sdist; "
"tar zxvf *.tar.gz; "
"cd argweaver-*; "
"python setup.py install --prefix=. "
"--install-lib=lib/python/site-packages "
"> /dev/null")
run_cmd("cd test/tmp/install_sdist/argweaver-*; "
"PYTHONPATH=lib/python/site-packages "
"python -c 'import argweaver; "
"assert argweaver.argweaverc.argweaverclib'")
def _test_prog_infsites():
make_clean_dir("test/data/test_prog_infsites")
run_cmd("""bin/arg-sim \
-k 40 -L 200000 \
-N 1e4 -r 1.5e-8 -m 2.5e-8 --infsites \
--ntimes 20 --maxtime 400e3 \
-o test/data/test_prog_infsites/0""")
make_clean_dir("test/data/test_prog_infsites/0.sample")
run_cmd("""bin/arg-sample \
-s test/data/test_prog_infsites/0.sites \
-N 1e4 -r 1.5e-8 -m 2.5e-8 \
--ntimes 5 --maxtime 100e3 -c 1 \
--climb 0 -n 20 --infsites \
-x 1 \
-o test/data/test_prog_infsites/0.sample/out""")
arg = argweaver.read_arg(
"test/data/test_prog_infsites/0.sample/out.0.smc.gz")
sites = argweaver.read_sites("test/data/test_prog_infsites/0.sites")
print "names", sites.names
print
noncompats = []
for block, tree in arglib.iter_local_trees(arg):
tree = tree.get_tree()
treelib.remove_single_children(tree)
phylo.hash_order_tree(tree)
for pos, col in sites.iter_region(block[0]+1, block[1]+1):
assert block[0]+1 <= pos <= block[1]+1, (block, pos)
split = sites_split(sites.names, col)
node = arglib.split_to_tree_branch(tree, split)
if node is None:
noncompats.append(pos)
print "noncompat", block, pos, col
print phylo.hash_tree(tree)
print tree.leaf_names()
print "".join(col[sites.names.index(name)]
for name in tree.leaf_names())
print split
print
print "num noncompats", len(noncompats)
def _test_prog_infsites():
make_clean_dir("test/tmp/test_prog_infsites")
run_cmd("""bin/arg-sim \
-k 40 -L 200000 \
-N 1e4 -r 1.5e-8 -m 2.5e-8 --infsites \
--ntimes 20 --maxtime 400e3 \
-o test/tmp/test_prog_infsites/0""")
make_clean_dir("test/tmp/test_prog_infsites/0.sample")
run_cmd("""bin/arg-sample \
-s test/tmp/test_prog_infsites/0.sites \
-N 1e4 -r 1.5e-8 -m 2.5e-8 \
--ntimes 5 --maxtime 100e3 -c 1 \
--climb 0 -n 20 --infsites \
-x 1 \
-o test/tmp/test_prog_infsites/0.sample/out""")
arg = argweaver.read_arg(
"test/tmp/test_prog_infsites/0.sample/out.0.smc.gz")
sites = argweaver.read_sites("test/tmp/test_prog_infsites/0.sites")
print "names", sites.names
print
noncompats = []
for block, tree in arglib.iter_local_trees(arg):
tree = tree.get_tree()
treelib.remove_single_children(tree)
phylo.hash_order_tree(tree)
for pos, col in sites.iter_region(block[0] + 1, block[1] + 1):
assert block[0] + 1 <= pos <= block[1] + 1, (block, pos)
split = sites_split(sites.names, col)
node = arglib.split_to_tree_branch(tree, split)
if node is None:
noncompats.append(pos)
print "noncompat", block, pos, col
print phylo.hash_tree(tree)
print tree.leaf_names()
print "".join(col[sites.names.index(name)]
for name in tree.leaf_names())
print split
print
print "num noncompats", len(noncompats)
def test_prog_small():
"""
Test arg-sample on a small simulated dataset
"""
make_clean_dir("test/data/test_prog_small")
run_cmd("""bin/arg-sim \
-k 4 -L 100000 \
-N 1e4 -r 1.5e-8 -m 2.5e-8 \
--ntimes 10 --maxtime 400e3 \
-o test/data/test_prog_small/0 > /dev/null""")
make_clean_dir("test/data/test_prog_small/0.sample")
run_cmd("""bin/arg-sample -q \
-s test/data/test_prog_small/0.sites \
-x 1 -N 1e4 -r 1.5e-8 -m 2.5e-8 \
--ntimes 10 --maxtime 400e3 -c 20 \
-n 10 --sample-step 1 \
-o test/data/test_prog_small/0.sample/out""")
def test_prob_coal2(self):
outdir = 'test/tmp/test_coal/Coal_test_prob_coal2/'
make_clean_dir(outdir)
k = 2
n = 1000
p = Gnuplot()
p.enableOutput(False)
p.plotfunc(lambda t: coal.prob_coal(t, k, n), 0, 4000, 10,
ymin=0)
# draw single coal samples
x = [coal.sample_coal(k, n) for i in xrange(200)]
plotdistrib(x, 40, plot=p)
p.enableOutput(True)
p.save(outdir + 'plot.png')
eq_sample_pdf(x, lambda t: coal.prob_coal(t, k, n), 40)
def test_prog_small():
"""
Test arg-sample on a small simulated dataset
"""
make_clean_dir("test/tmp/test_prog_small")
run_cmd("""bin/arg-sim \
-k 4 -L 100000 \
-N 1e4 -r 1.5e-8 -m 2.5e-8 \
--ntimes 10 --maxtime 400e3 \
-o test/tmp/test_prog_small/0 > /dev/null""")
make_clean_dir("test/tmp/test_prog_small/0.sample")
run_cmd("""bin/arg-sample -q \
-s test/tmp/test_prog_small/0.sites \
-x 1 -N 1e4 -r 1.5e-8 -m 2.5e-8 \
--ntimes 10 --maxtime 400e3 -c 20 \
-n 10 --sample-step 1 \
-o test/tmp/test_prog_small/0.sample/out""")
def test_prog_popsizes():
"""
Ensure arg-sample can use multiple population sizes from a file.
"""
make_clean_dir("test/tmp/test_prog_popsizes")
# Setup popsize config file.
popsizes = range(10000, 0, -1000)
with open('test/tmp/test_prog_popsizes/popsizes', 'w') as out:
out.write('\n'.join(map(str, popsizes)))
run_cmd("""bin/arg-sim \
-k 4 -L 100000 \
-N 1e4 -r 1.5e-8 -m 2.5e-8 \
--ntimes 10 --maxtime 400e3 \
-o test/tmp/test_prog_popsizes/0 > /dev/null""")
make_clean_dir("test/tmp/test_prog_popsizes/0.sample")
run_cmd("""bin/arg-sample -q \
-s test/tmp/test_prog_popsizes/0.sites \
-x 1 -N 1e4 -r 1.5e-8 -m 2.5e-8 \
--ntimes 10 --maxtime 400e3 -c 20 \
--popsize-file test/tmp/test_prog_popsizes/popsizes \
-n 10 --sample-step 1 \
-o test/tmp/test_prog_popsizes/0.sample/out""")
# Write too few population sizes to config file.
popsizes_bad = range(10000, 5000, -1000)
with open('test/tmp/test_prog_popsizes/popsizes-bad', 'w') as out:
out.write('\n'.join(map(str, popsizes_bad)))
# Expect an error.
run_cmd(
"""bin/arg-sample -q \
-s test/tmp/test_prog_popsizes/0.sites \
-x 1 -N 1e4 -r 1.5e-8 -m 2.5e-8 \
--ntimes 10 --maxtime 400e3 -c 20 \
--popsize-file test/tmp/test_prog_popsizes/popsizes-bad \
-n 10 --sample-step 1 \
-o test/tmp/test_prog_popsizes/0.sample/out-bad""", EXIT_ERROR)
def test_prog_popsizes():
"""
Ensure arg-sample can use multiple population sizes from a file.
"""
make_clean_dir("test/tmp/test_prog_popsizes")
# Setup popsize config file.
popsizes = range(10000, 0, -1000)
with open('test/tmp/test_prog_popsizes/popsizes', 'w') as out:
out.write('\n'.join(map(str, popsizes)))
run_cmd("""bin/arg-sim \
-k 4 -L 100000 \
-N 1e4 -r 1.5e-8 -m 2.5e-8 \
--ntimes 10 --maxtime 400e3 \
-o test/tmp/test_prog_popsizes/0 > /dev/null""")
make_clean_dir("test/tmp/test_prog_popsizes/0.sample")
run_cmd("""bin/arg-sample -q \
-s test/tmp/test_prog_popsizes/0.sites \
-x 1 -N 1e4 -r 1.5e-8 -m 2.5e-8 \
--ntimes 10 --maxtime 400e3 -c 20 \
--popsize-file test/tmp/test_prog_popsizes/popsizes \
-n 10 --sample-step 1 \
-o test/tmp/test_prog_popsizes/0.sample/out""")
# Write too few population sizes to config file.
popsizes_bad = range(10000, 5000, -1000)
with open('test/tmp/test_prog_popsizes/popsizes-bad', 'w') as out:
out.write('\n'.join(map(str, popsizes_bad)))
# Expect an error.
run_cmd("""bin/arg-sample -q \
-s test/tmp/test_prog_popsizes/0.sites \
-x 1 -N 1e4 -r 1.5e-8 -m 2.5e-8 \
--ntimes 10 --maxtime 400e3 -c 20 \
--popsize-file test/tmp/test_prog_popsizes/popsizes-bad \
-n 10 --sample-step 1 \
-o test/tmp/test_prog_popsizes/0.sample/out-bad""",
EXIT_ERROR)
def test_cdf_mrca(self):
outdir = 'test/tmp/test_coal/Coal_test_cdf_mrca/'
make_clean_dir(outdir)
n = 1000
k = 6
step = 10
x = list(frange(0, 5000, step))
y = [coal.prob_mrca(i, k, n) * step for i in x]
y2 = cumsum(y)
y3 = [coal.cdf_mrca(t, k, n) for t in x]
p = Gnuplot()
p.enableOutput(False)
p.plot(x, y2, style="lines")
p.plot(x, y3, style="lines")
p.enableOutput(True)
p.save(outdir + 'plot.png')
eq_sample_pdf(x, lambda t: coal.cdf_mrca(t, k, n), 40)
def test_prob_coal_cond_counts_simple(self):
# when we condition on b=1, it is the same as the bounded coal
# PDF.
# prob_coal_cond_counts is actually a more general version of
# prob_bounded_coal
outdir = 'test/tmp/test_coal/Coal_test_prob_coal_counys_simple/'
make_clean_dir(outdir)
a = 5
b = 1
t = 2000
n = 1000
p = Gnuplot()
p.enableOutput(False)
for x in frange(0, 2000, 10):
y = coal.prob_coal_cond_counts_simple(x, a, b, t, n)
y2 = coal.prob_bounded_coal(x, a, n, t)
self.assertAlmostEqual(y, y2)
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')