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_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 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)
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)