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_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_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_read_write(self):
"""Read and write an ARG"""
rho = 1.5e-8 # recomb/site/gen
l = 10000 # length of locus
k = 10 # number of lineages
n = 2*10000 # effective popsize
arg = arglib.sample_arg(k, n, rho, 0, l)
# round ages and pos for easy equality
for node in arg:
node.age = round(node.age)
node.pos = round(node.pos)
stream = StringIO.StringIO()
arglib.write_arg(stream, arg)
stream.seek(0)
arg2 = arglib.read_arg(stream)
self.assertTrue(arg.equal(arg2))
def show_plots(arg_file, sites_file, stats_file, output_prefix,
rho, mu, popsize, ntimes=20, maxtime=200000):
"""
Show plots of convergence.
"""
# read true arg and seqs
times = argweaver.get_time_points(ntimes=ntimes, maxtime=maxtime)
arg = arglib.read_arg(arg_file)
argweaver.discretize_arg(arg, times, ignore_top=False, round_age="closer")
arg = arglib.smcify_arg(arg)
seqs = argweaver.sites2seqs(argweaver.read_sites(sites_file))
# compute true stats
arglen = arglib.arglen(arg)
arg = argweaverc.arg2ctrees(arg, times)
nrecombs = argweaverc.get_local_trees_ntrees(arg[0]) - 1
lk = argweaverc.calc_likelihood(
arg, seqs, mu=mu, times=times,
delete_arg=False)
prior = argweaverc.calc_prior_prob(
arg, rho=rho, times=times, popsizes=popsize,
delete_arg=False)
joint = lk + prior
data = read_table(stats_file)
# joint
y2 = joint
y = data.cget("joint")
rplot_start(output_prefix + ".trace.joint.pdf", width=8, height=5)
rp.plot(y, t="l", ylim=[min(min(y), y2), max(max(y), y2)],
main="joint probability",
xlab="iterations",
ylab="joint probability")
rp.lines([0, len(y)], [y2, y2], col="gray")
rplot_end(True)
# lk
y2 = lk
y = data.cget("likelihood")
rplot_start(output_prefix + ".trace.lk.pdf", width=8, height=5)
rp.plot(y, t="l", ylim=[min(min(y), y2), max(max(y), y2)],
main="likelihood",
xlab="iterations",
ylab="likelihood")
rp.lines([0, len(y)], [y2, y2], col="gray")
rplot_end(True)
# prior
y2 = prior
y = data.cget("prior")
rplot_start(output_prefix + ".trace.prior.pdf", width=8, height=5)
rp.plot(y, t="l", ylim=[min(min(y), y2), max(max(y), y2)],
main="prior probability",
xlab="iterations",
ylab="prior probability")
rp.lines([0, len(y)], [y2, y2], col="gray")
rplot_end(True)
# nrecombs
y2 = nrecombs
y = data.cget("recombs")
rplot_start(output_prefix + ".trace.nrecombs.pdf",
width=8, height=5)
rp.plot(y, t="l", ylim=[min(min(y), y2), max(max(y), y2)],
main="number of recombinations",
xlab="iterations",
ylab="number of recombinations")
rp.lines([0, len(y)], [y2, y2], col="gray")
rplot_end(True)
# arglen
y2 = arglen
y = data.cget("arglen")
rplot_start(output_prefix + ".trace.arglen.pdf",
width=8, height=5)
rp.plot(y, t="l", ylim=[min(min(y), y2), max(max(y), y2)],
main="ARG branch length",
xlab="iterations",
ylab="ARG branch length")
rp.lines([0, len(y)], [y2, y2], col="gray")
rplot_end(True)
i, j = util.binsearch(times3, x)
if i is None: i = j
if j is None: j = i
if abs(times3[i] - x) < 1:
times.append(times3[i])
elif abs(times3[j] - x) < 1:
times.append(times3[j])
else:
times.append(x)
return times
#=============================================================================
if 1:
#times = arghmm.get_time_points(ntimes=20)
arg = arglib.read_arg("test/data/sample.arg")
seqs = read_fasta("test/data/sample.fa")
trees = list(arglib.iter_tree_tracks(arg, convert=True))
# draw mappings
win = argvis.show_tree_track(trees)
nleaves = ilen(arg.leaves())
for i in xrange(len(trees)-1):
block1, _tree1 = trees[i]
block2, _tree2 = trees[i + 1]
pos = block2[0]
tree1 = arg.get_marginal_tree(pos-.5)
tree2 = arg.get_marginal_tree(pos+.5)
layout1 = argvis.layout_arg(tree1)
def show_plots(arg_file, sites_file, stats_file, output_prefix,
rho, mu, popsize, ntimes=20, maxtime=200000):
"""
Show plots of convergence.
"""
# read true arg and seqs
times = argweaver.get_time_points(ntimes=ntimes, maxtime=maxtime)
arg = arglib.read_arg(arg_file)
argweaver.discretize_arg(arg, times, ignore_top=False, round_age="closer")
arg = arglib.smcify_arg(arg)
seqs = argweaver.sites2seqs(argweaver.read_sites(sites_file))
# compute true stats
arglen = arglib.arglen(arg)
arg = argweaverc.arg2ctrees(arg, times)
nrecombs = argweaverc.get_local_trees_ntrees(arg[0]) - 1
lk = argweaverc.calc_likelihood(
arg, seqs, mu=mu, times=times,
delete_arg=False)
prior = argweaverc.calc_prior_prob(
arg, rho=rho, times=times, popsizes=popsize,
delete_arg=False)
joint = lk + prior
data = read_table(stats_file)
# joint
y2 = joint
y = data.cget("joint")
rplot_start(output_prefix + ".trace.joint.pdf", width=8, height=5)
rp.plot(y, t="l", ylim=[min(min(y), y2), max(max(y), y2)],
main="joint probability",
xlab="iterations",
ylab="joint probability")
rp.lines([0, len(y)], [y2, y2], col="gray")
rplot_end(True)
# lk
y2 = lk
y = data.cget("likelihood")
rplot_start(output_prefix + ".trace.lk.pdf", width=8, height=5)
rp.plot(y, t="l", ylim=[min(min(y), y2), max(max(y), y2)],
main="likelihood",
xlab="iterations",
ylab="likelihood")
rp.lines([0, len(y)], [y2, y2], col="gray")
rplot_end(True)
# prior
y2 = prior
y = data.cget("prior")
rplot_start(output_prefix + ".trace.prior.pdf", width=8, height=5)
rp.plot(y, t="l", ylim=[min(min(y), y2), max(max(y), y2)],
main="prior probability",
xlab="iterations",
ylab="prior probability")
rp.lines([0, len(y)], [y2, y2], col="gray")
rplot_end(True)
# nrecombs
y2 = nrecombs
y = data.cget("recombs")
rplot_start(output_prefix + ".trace.nrecombs.pdf",
width=8, height=5)
rp.plot(y, t="l", ylim=[min(min(y), y2), max(max(y), y2)],
main="number of recombinations",
xlab="iterations",
ylab="number of recombinations")
rp.lines([0, len(y)], [y2, y2], col="gray")
rplot_end(True)
# arglen
y2 = arglen
y = data.cget("arglen")
rplot_start(output_prefix + ".trace.arglen.pdf",
width=8, height=5)
rp.plot(y, t="l", ylim=[min(min(y), y2), max(max(y), y2)],
main="ARG branch length",
xlab="iterations",
ylab="ARG branch length")
rp.lines([0, len(y)], [y2, y2], col="gray")
rplot_end(True)
i, j = util.binsearch(times3, x)
if i is None: i = j
if j is None: j = i
if abs(times3[i] - x) < 1:
times.append(times3[i])
elif abs(times3[j] - x) < 1:
times.append(times3[j])
else:
times.append(x)
return times
#=============================================================================
if 1:
#times = arghmm.get_time_points(ntimes=20)
arg = arglib.read_arg("test/data/sample.arg")
seqs = read_fasta("test/data/sample.fa")
trees = list(arglib.iter_tree_tracks(arg, convert=True))
# draw mappings
win = argvis.show_tree_track(trees)
nleaves = ilen(arg.leaves())
for i in xrange(len(trees) - 1):
block1, _tree1 = trees[i]
block2, _tree2 = trees[i + 1]
pos = block2[0]
tree1 = arg.get_marginal_tree(pos - .5)
tree2 = arg.get_marginal_tree(pos + .5)
layout1 = argvis.layout_arg(tree1)