def set_up(self):
self.temp_fs = TempFileSystem(parent=package_paths.test_path(),
prefix='PyMsBayesTestTemp-')
self.test_id = 'pymsbayes-' + random_str()
def main_cli():
description = '{name} {version}'.format(**_program_info)
parser = argparse.ArgumentParser(description = description)
parser.add_argument('-c', '--config',
type = arg_is_config,
required = True,
help = ('msBayes config file to be used to generate saturation '
'plot.'))
parser.add_argument('-n', '--num-prior-samples',
action = 'store',
type = int,
default = 1000,
help = ('The number of prior samples to simulate for the '
'saturation plot.'))
parser.add_argument('--np',
action = 'store',
type = int,
default = multiprocessing.cpu_count(),
help = ('The maximum number of processes to run in parallel. The '
'default is the number of CPUs available on the machine.'))
parser.add_argument('-o', '--output-dir',
action = 'store',
type = arg_is_dir,
help = ('The directory in which all output files will be written. '
'The default is to use the directory of the first observed '
'config file.'))
parser.add_argument('--temp-dir',
action = 'store',
type = arg_is_dir,
help = ('A directory to temporarily stage files. The default is to '
'use the output directory.'))
parser.add_argument('-s', '--stat-prefixes',
nargs = '*',
type = str,
default = ['pi', 'pi.net', 'wattTheta', 'tajD.denom'],
help = ('Prefixes of summary statistics to use in the analyses. '
'The prefixes should be separated by spaces. '
'Default: `-s pi pi.net wattTheta tajD.denom`.'))
parser.add_argument('--vertical-lines',
nargs = '*',
type = float,
default = [],
help = ('Positions along x-axis where vertical lines are to be '
'drawn. Default is to draw no vertical lines.'))
parser.add_argument('--compress',
action = 'store_true',
help = 'Compress plot data file.')
parser.add_argument('--keep-temps',
action = 'store_true',
help = 'Keep all temporary files.')
parser.add_argument('--seed',
action = 'store',
type = int,
help = 'Random number seed to use for the analysis.')
parser.add_argument('--version',
action = 'version',
version = '%(prog)s ' + _program_info['version'],
help = 'Report version and exit.')
parser.add_argument('--quiet',
action = 'store_true',
help = 'Run without verbose messaging.')
parser.add_argument('--debug',
action = 'store_true',
help = 'Run in debugging mode.')
args = parser.parse_args()
##########################################################################
## handle args
from pymsbayes.utils.messaging import (LoggingControl,
InfoLogger)
LoggingControl.set_logging_level("INFO")
if args.quiet:
LoggingControl.set_logging_level("WARNING")
if args.debug:
LoggingControl.set_logging_level("DEBUG")
log = LoggingControl.get_logger(__name__)
from pymsbayes.workers import MsBayesWorker
from pymsbayes.utils.parsing import (get_patterns_from_prefixes,
DEFAULT_STAT_PATTERNS, get_stats_by_time, dict_line_iter)
from pymsbayes.manager import Manager
from pymsbayes.utils.tempfs import TempFileSystem
from pymsbayes.utils import probability
from pymsbayes.utils.functions import long_division
from pymsbayes.config import MsBayesConfig
from pymsbayes.utils import GLOBAL_RNG, MSBAYES_SORT_INDEX, ToolPathManager
from pymsbayes.fileio import process_file_arg
from pymsbayes.plotting import MATPLOTLIB_AVAILABLE, SaturationPlotGrid
MSBAYES_SORT_INDEX.set_index(0)
# get full paths to tools
msbayes_path = ToolPathManager.get_tool_full_path('msbayes.pl')
dpp_msbayes_path = ToolPathManager.get_tool_full_path('dpp-msbayes.pl')
if not args.output_dir:
args.output_dir = os.path.dirname(args.config)
info = InfoLogger(os.path.join(args.output_dir, 'pymsbayes-info.txt'))
stats_by_time_path = os.path.join(args.output_dir, 'stats-by-time.txt')
if args.compress:
stats_by_time_path += '.gz'
plot_path = os.path.join(args.output_dir, 'saturation-plot.pdf')
if not args.temp_dir:
args.temp_dir = args.output_dir
temp_fs = TempFileSystem(parent=args.temp_dir, prefix='temp-files-')
args.stat_prefixes = [s.rstrip('.') for s in args.stat_prefixes]
stat_patterns = get_patterns_from_prefixes(
[s + '.' for s in args.stat_prefixes],
ignore_case=True)
if not args.seed:
args.seed = random.randint(1, 999999999)
GLOBAL_RNG.seed(args.seed)
compress_level = None
if args.compress:
compress_level = 9
cfg = MsBayesConfig(args.config)
num_taxon_pairs = cfg.npairs
cfg.div_model_prior = 'constrained'
cfg.psi = probability.DiscreteUniformDistribution(num_taxon_pairs,
num_taxon_pairs)
config_path = temp_fs.get_file_path(prefix='cfg-')
cfg.write(config_path)
info.write('[pymsbayes]', log.info)
info.write('\tprogram_name = {name}'.format(**_program_info), log.info)
info.write('\tversion = {version}'.format(**_program_info), log.info)
info.write('\tinvocation = {0!r}'.format(' '.join(sys.argv)), log.info)
info.write('\toutput_directory = {0!r}'.format(args.output_dir), log.info)
info.write('\ttemp_directory = {0!r}'.format(temp_fs.base_dir), log.info)
info.write('\tsort_index = {0}'.format(
MSBAYES_SORT_INDEX.current_value()), log.info)
info.write('\tstat_patterns = {0!r}'.format(
', '.join([p.pattern for p in stat_patterns])), log.info)
info.write('\tseed = {0}'.format(args.seed), log.info)
info.write('\tnum_prior_samples = {0}'.format(args.num_prior_samples),
log.info)
info.write('\tstats_by_time_path = {0!r}'.format(stats_by_time_path),
log.info)
info.write('\t[[tool_paths]]', log.info)
info.write('\t\tdpp_msbayes = {0}'.format(dpp_msbayes_path), log.info)
info.write('\t\tmsbayes = {0}'.format(msbayes_path), log.info)
info.write('\t[[config]]', log.debug)
info.write('{0}'.format(str(cfg)), log.debug)
##########################################################################
## begin analysis --- generate samples
start_time = datetime.datetime.now()
if args.np > args.num_prior_samples:
args.np = args.num_prior_samples
batch_size, remainder = long_division(args.num_prior_samples, args.np)
schema = 'abctoolbox'
workers = []
for i in range(args.np):
sample_size = batch_size
if i == (args.np - 1):
sample_size += remainder
w = MsBayesWorker(
temp_fs = temp_fs,
sample_size = sample_size,
config_path = config_path,
report_parameters = True,
schema = schema,
include_header = True,
stat_patterns = stat_patterns,
write_stats_file = False)
workers.append(w)
log.info('Generating samples...')
workers = Manager.run_workers(
workers = workers,
num_processors = args.np)
log.info('Parsing samples...')
stats_by_time = get_stats_by_time([w.prior_path for w in workers])
stat_keys = stats_by_time.keys()
stat_keys.remove('PRI.t')
for prefix in args.stat_prefixes:
if not prefix in stat_keys:
raise Exception('stat prefix {0!r} not found in simulated stats:'
'\n\t{1}'.format(prefix, ', '.join(stat_keys)))
header = ['PRI.t'] + args.stat_prefixes
log.info('Writing stats-by-time matrix...')
out, close = process_file_arg(stats_by_time_path, 'w',
compresslevel = compress_level)
for row in dict_line_iter(stats_by_time, sep = '\t', header = header):
out.write(row)
if close:
out.close()
log.info('Creating plots...')
if not MATPLOTLIB_AVAILABLE:
log.warning(
'`matplotlib` could not be imported, so the plot can not be\n'
'produced. The data to create the plot can be found in:\n\t'
'{0!r}'.format(stats_by_time_path))
else:
y_labels = {'pi': r'$\pi$',
'pi.net': r'$\pi_{net}$',
'wattTheta': r'$\theta_W$',
'tajD.denom': r'$SD(\pi - \theta_W)$'}
spg = SaturationPlotGrid(stats_by_time,
x_key = 'PRI.t',
y_keys = args.stat_prefixes,
y_labels = y_labels,
num_columns = 2,
vertical_line_positions = args.vertical_lines)
fig = spg.create_grid()
fig.savefig(plot_path)
stop_time = datetime.datetime.now()
log.info('Done!')
info.write('\t[[run_stats]]', log.info)
info.write('\t\tstart_time = {0}'.format(str(start_time)), log.info)
info.write('\t\tstop_time = {0}'.format(str(stop_time)), log.info)
info.write('\t\ttotal_duration = {0}'.format(str(stop_time - start_time)),
log.info)
if not args.keep_temps:
log.debug('purging temps...')
temp_fs.purge()
class PyMsBayesTestCase(unittest.TestCase):
def set_up(self):
self.temp_fs = TempFileSystem(parent=package_paths.test_path(),
prefix='PyMsBayesTestTemp-')
self.test_id = 'pymsbayes-' + random_str()
def tear_down(self):
self.register_file_system()
self.temp_fs.purge()
self.assertEqual(FileStream.open_files, set())
def get_test_path(self, parent=None, prefix='temp'):
return self.temp_fs.get_file_path(parent=parent, prefix=prefix)
def get_test_subdir(self, parent=None, prefix='temp'):
return self.temp_fs.create_subdir(parent=parent, prefix=prefix)
def register_file(self, path):
self.temp_fs._register_file(path)
def register_dir(self, path):
self.temp_fs._register_dir(path)
def register_file_system(self):
_LOG.debug('registering test file system...')
for path, dirs, files, in os.walk(self.temp_fs.base_dir):
for f in files:
if f.startswith(self.test_id):
self.register_file(os.path.join(path, f))
for d in dirs:
if d.startswith(self.test_id):
self.register_dir(os.path.join(path, d))
def _exe_script(self,
script_name,
args,
stdout=None,
stderr=None,
return_code=0):
script_path = package_paths.script_path(script_name)
if isinstance(args, str):
arg_list = args.split()
else:
arg_list = args
arg_list = [str(x) for x in arg_list]
cmd = [sys.executable, script_path] + arg_list
_LOG.debug('Invocation:\n\t{0}'.format(' '.join(cmd)))
p = subprocess.Popen(cmd,
shell=False,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
o, e = p.communicate()
exit_code = p.wait()
if exit_code != return_code:
_LOG.error("exit code {0} did not match {1}".format(
exit_code, return_code))
_LOG.error("here is the stdout:\n{0}".format(o))
_LOG.error("here is the stderr:\n{0}".format(e))
self.assertEqual(exit_code, return_code)
if stdout != None:
if o != stdout:
_LOG.error("std out did not match expected:\n{0}".format(o))
self.assertEqual(o, stdout)
if stderr != None:
if e != stderr:
_LOG.error("std error did not match expected:\n{0}".format(e))
self.assertEqual(e, stderr)
def get_expected_indices(self,
num_pairs,
dummy_column=True,
parameters_reported=True):
num_summary_params = 4
if _CV_INCLUDED:
num_summary_params += 1
num_params = 4 * num_pairs
num_default_stats = 4 * num_pairs
start = 0
if dummy_column:
start = 1
param_indices = range(start, start + num_summary_params)
start += num_summary_params
if parameters_reported:
param_indices += range(start, start + num_params)
start += num_params
stat_indices = range(start, start + num_default_stats)
return param_indices, stat_indices
def prior_file_is_valid(self,
prior_path,
num_of_samples,
num_of_columns=None):
try:
prior_file = open(prior_path, 'rU')
except:
_LOG.error('prior invalid: could not open prior path {0}'.format(
prior_path))
return False
nrows = 0
for i, line in enumerate(prior_file):
if nrows == 0 and HEADER_PATTERN.match(line):
pass
else:
nrows += 1
if not num_of_columns:
num_of_columns = len(line.strip().split())
ncols = len(line.strip().split())
if num_of_columns != ncols:
_LOG.error('prior invalid: num of columns at line {0} is {1} '
'NOT {2}'.format(i + 1, ncols, num_of_columns))
return False
prior_file.close()
if num_of_samples != nrows:
_LOG.error('prior invalid: num of rows is {0} NOT {1}'.format(
nrows, num_of_samples))
return False
return True
def get_number_of_lines(self, path):
f, close = process_file_arg(path)
count = 0
for l in f:
count += 1
if close:
f.close()
return count
def get_number_of_header_lines(self, path):
f, close = process_file_arg(path)
count = 0
for l in f:
if HEADER_PATTERN.match(l.strip()):
count += 1
if close:
f.close()
return count
def parse_python_config(self, path):
return ConfigObj(path)
def get_config_from_msbayes_workers(self, msbayes_workers):
cfgs = [MsBayesConfig(w.config_path) for w in msbayes_workers]
self.assertSameConfigs(cfgs)
return cfgs[0]
def assertSameConfigs(self, cfgs):
configs = list(cfgs)
c1 = configs.pop(0)
for c2 in cfgs:
self.assertEqual(c1.time_in_subs_per_site,
c2.time_in_subs_per_site)
self.assertEqual(c1.npairs, c2.npairs)
self.assertEqual(c1.implementation, c2.implementation)
self.assertEqual(c1.div_model_prior, c2.div_model_prior)
self.assertEqual(c1.bottle_proportion_shared,
c2.bottle_proportion_shared)
self.assertEqual(c1.theta_parameters, c2.theta_parameters)
self.assertEqual(c1.taxa, c2.taxa)
self.assertTrue(c1.sample_table.equals(c2.sample_table))
if c1.psi:
self.assertSameDistributions(c1.psi, c2.psi)
else:
self.assertEqual(c1.psi, c2.psi)
if c1.tau:
self.assertSameDistributions(c1.tau, c2.tau)
else:
self.assertEqual(c1.tau, c2.tau)
if c1.theta:
self.assertSameDistributions(c1.theta, c2.theta)
else:
self.assertEqual(c1.theta, c2.theta)
if c1.a_theta:
self.assertSameDistributions(c1.a_theta, c2.a_theta)
else:
self.assertEqual(c1.a_theta, c2.a_theta)
if c1.d_theta:
self.assertSameDistributions(c1.d_theta, c2.d_theta)
else:
self.assertEqual(c1.d_theta, c2.d_theta)
if c1.recombination:
self.assertSameDistributions(c1.recombination,
c2.recombination)
else:
self.assertEqual(c1.recombination, c2.recombination)
if c1.migration:
self.assertSameDistributions(c1.migration, c2.migration)
else:
self.assertEqual(c1.migration, c2.migration)
if c1.dpp_concentration:
self.assertSameDistributions(c1.dpp_concentration,
c2.dpp_concentration)
else:
self.assertEqual(c1.dpp_concentration, c2.dpp_concentration)
if c1.bottle_proportion:
self.assertSameDistributions(c1.bottle_proportion,
c2.bottle_proportion)
else:
self.assertEqual(c1.bottle_proportion, c2.bottle_proportion)
def get_parameter_summaries_from_msbayes_workers(self,
msbayes_workers,
shuffle_taus=True):
msbayes_workers = list(msbayes_workers)
s = dict(
zip([i for i in msbayes_workers[0].parameter_indices], [
SampleSummarizer(tag=msbayes_workers[0].header[i])
for i in msbayes_workers[0].parameter_indices
]))
ncols = None
header = msbayes_workers[0].header
pi = msbayes_workers[0].parameter_indices
for w in msbayes_workers:
self.assertEqual(w.header, header)
self.assertEqual(w.parameter_indices, pi)
f = open(w.prior_path, 'rU')
for line_idx, row in enumerate(f):
if not ncols:
ncols = len(row.strip().split())
if HEADER_PATTERN.match(row.strip()):
continue
r = row.strip().split()
assert len(r) == ncols
if shuffle_taus: # because taus are sorted in prior files
psi_index = get_indices_of_patterns(
w.header, PSI_PATTERNS)[0]
tau_indices = get_indices_of_patterns(
w.header, TAU_PATTERNS)
psi = int(r[psi_index])
taus = [float(r[i]) for i in tau_indices]
self.assertEqual(psi, len(set(taus)))
random.shuffle(taus)
for n, i in enumerate(tau_indices):
s[i].add_sample(taus[n])
p_set = set(w.parameter_indices) - set(tau_indices)
p = sorted(list(p_set))
for i in p:
s[i].add_sample(float(r[i]))
else:
for i in w.parameter_indices:
s[i].add_sample(float(r[i]))
f.close()
return s
def assertPriorIsPrecise(self, msbayes_workers, places=2):
msbayes_workers = list(msbayes_workers)
self.assertWorkersFinished(msbayes_workers)
param_sums = self.get_parameter_summaries_from_msbayes_workers(
msbayes_workers)
sample_size = 0
for w in msbayes_workers:
sample_size += w.sample_size
for s in param_sums.itervalues():
self.assertEqual(s.n, sample_size)
cfg = self.get_config_from_msbayes_workers(msbayes_workers)
psi_indices = get_indices_of_patterns(msbayes_workers[0].header,
PSI_PATTERNS)
self.assertEqual(len(psi_indices), 1)
model_indices = get_indices_of_patterns(msbayes_workers[0].header,
MODEL_PATTERNS)
if not msbayes_workers[0].model_index is None:
self.assertEqual(len(model_indices), 1)
else:
self.assertEqual(len(model_indices), 0)
tau_indices = get_indices_of_patterns(msbayes_workers[0].header,
TAU_PATTERNS)
a_theta_indices = get_indices_of_patterns(msbayes_workers[0].header,
A_THETA_PATTERNS)
d_theta_indices = get_indices_of_patterns(msbayes_workers[0].header,
D_THETA_PATTERNS)
if msbayes_workers[0].report_parameters:
self.assertEqual(len(tau_indices), cfg.npairs)
self.assertEqual(len(a_theta_indices), cfg.npairs)
self.assertEqual(len(d_theta_indices), 2 * cfg.npairs)
else:
self.assertEqual(len(tau_indices), 0)
self.assertEqual(len(a_theta_indices), 0)
self.assertEqual(len(d_theta_indices), 0)
_LOG.debug('\n{0}\n'.format('\n'.join(
[str(param_sums[i]) for i in sorted(param_sums.iterkeys())])))
for i in psi_indices:
self.assertSampleIsFromDistribution(param_sums[i],
cfg.psi,
places=places)
for i in tau_indices:
self.assertSampleIsFromDistribution(param_sums[i],
cfg.tau,
places=places)
for i in a_theta_indices:
self.assertSampleIsFromDistribution(param_sums[i],
cfg.a_theta,
places=places)
for i in d_theta_indices:
self.assertSampleIsFromDistribution(param_sums[i],
cfg.d_theta,
mean_adj=cfg.theta.mean,
max_adj=cfg.theta.maximum,
compare_variance=False,
places=places)
def assertPriorIsAccurate(self, msbayes_workers, places=2):
msbayes_workers = list(msbayes_workers)
self.assertWorkersFinished(msbayes_workers)
pass
def assertPriorIsValid(self, msbayes_workers, places=2):
msbayes_workers = list(msbayes_workers)
self.assertWorkersFinished(msbayes_workers)
self.assertPriorIsPrecise(msbayes_workers, places=places)
self.assertPriorIsAccurate(msbayes_workers, places=places)
def assertWorkersFinished(self, msbayes_workers):
for w in msbayes_workers:
self.assertTrue(w.finished)
def assertSampleIsFromDistribution(self,
sample_sum,
dist,
places=2,
mean_adj=1,
max_adj=1,
compare_variance=True):
if isinstance(dist, probability.DiscreteUniformDistribution):
self.assertEqual(sample_sum.minimum, dist.minimum)
self.assertEqual(sample_sum.maximum, dist.maximum)
else:
if dist.minimum != float('-inf') or dist.minimum != float('inf'):
self.assertAlmostEqual(sample_sum.minimum, dist.minimum,
places)
if dist.maximum != float('-inf') or dist.maximum != float('inf'):
self.assertAlmostEqual(sample_sum.maximum,
dist.maximum * max_adj, places)
self.assertAlmostEqual(sample_sum.mean, dist.mean * mean_adj, places)
if compare_variance:
self.assertAlmostEqual(sample_sum.variance, dist.variance, places)
def assertApproxEqual(self, x, y, percent_tol=1e-6):
eq = (((abs(x - y) / ((abs(x) + abs(y)) / 2)) * 100) < percent_tol)
if not eq:
_LOG.error('x ({0}) and y ({1}) are not equal'.format(x, y))
self.assertTrue(eq)
def files_equal(self, f1, f2, exclude_line_endings=False):
equal = True
diffs = []
f1, c1 = process_file_arg(f1)
f2, c2 = process_file_arg(f2)
line = 0
f1_end = False
f2_end = False
lines_left = True
while True:
line += 1
if f1_end == False:
try:
l1 = f1.next()
except (StopIteration, EOFError):
f1_end = line
pass
if f2_end == False:
try:
l2 = f2.next()
except (StopIteration, EOFError):
f2_end = line
pass
if f1_end != False and f2_end != False:
break
if exclude_line_endings:
l1 = l1.strip()
l2 = l2.strip()
if f1_end == False and f2_end == False and l1 != l2:
diffs.append(line)
equal = False
if f1_end != f2_end:
mn = min([f1_end, f2_end])
mx = max([f1_end, f2_end])
diffs.extend(range(mn, mx + 1))
equal = False
assert len(diffs) == len(set(diffs))
if c1:
f1.close()
if c2:
f2.close()
return equal, diffs
def assertSameFiles(self, files, exclude_line_endings=False):
files = list(files)
all_equal = True
diffs = StringIO()
f1 = files.pop(0)
for f2 in files:
equal, diff_list = self.files_equal(f1, f2, exclude_line_endings)
if not equal:
all_equal = False
n1 = f1
if not isinstance(n1, str):
n1 = f1.name
n2 = f2
if not isinstance(n2, str):
n2 = f2.name
diffs.write('{0} and {1} differ at lines:\n\t{2}\n'.format(
n1, n2, ','.join([str(i) for i in diff_list])))
if not all_equal:
_LOG.error('files are not equal:\n{0}\n'.format(diffs.getvalue()))
self.assertTrue(all_equal)
def assertSameUnsortedFiles(self, files):
files = list(files)
all_equal = True
diffs = StringIO()
f1, close = process_file_arg(files.pop(0))
lines1 = sorted(f1.readlines())
for f in files:
f2, close2 = process_file_arg(f)
lines2 = sorted(f2.readlines())
if len(lines1) != len(lines2):
all_equal = False
diffs.write('{0} ({1}) and {2} ({3}) have different '
'number of lines\n'.format(f1.name, len(lines1),
f2.name, len(lines2)))
for i in range(min(len(lines1), len(lines2))):
if lines1[i].strip().split() != lines2[i].strip().split():
all_equal = False
diffs.write('{0} and {1} differ at sorted index '
'{2}\n'.format(f1.name, f2.name, i))
if close2:
f2.close()
if not all_equal:
_LOG.error('files are not equal after sorting:\n{0}\n'.format(
diffs.getvalue()))
self.assertTrue(all_equal)
if close:
f1.close()
def same_samples(self, sample1, sample2, places=4, num_mismatches=0):
if len(sample1) != len(sample2):
return False
for i in range(len(sample1)):
if round(float(sample1[i]) - float(sample2[i]), places) != 0:
if num_mismatches < 1:
return False
num_mismatches -= 1
return True
def assertSameSamples(self,
files,
columns_to_ignore=[],
header=True,
places=5,
num_mismatches_per_sample=0,
num_sample_mismatches=0):
files = list(files)
all_equal = True
diffs = StringIO()
f1, close = process_file_arg(files.pop(0))
f1_lines = f1.readlines()
indices = [
i for i in range(len(f1_lines[0].strip().split()))
if i not in columns_to_ignore
]
h1 = []
if header:
head = f1_lines.pop(0).strip().split()
h1 = [head[i] for i in indices]
lines1 = sorted(f1_lines)
for f in files:
f2, close2 = process_file_arg(f)
f2_lines = f2.readlines()
h2 = []
if header:
head = f2_lines.pop(0).strip().split()
h2 = [head[i] for i in indices]
if h1 != h2:
all_equal = False
diffs.write('{0} and {1} have different headers; not '
'comparing further\n'.format(f1.name, f2.name))
continue
lines2 = sorted(f2_lines)
if len(lines1) != len(lines2):
all_equal = False
diffs.write('{0} ({1}) and {2} ({3}) have different '
'number of lines\n'.format(f1.name, len(lines1),
f2.name, len(lines2)))
n_matches = 0
n_mismatches = 0
for l1 in lines1:
found = False
for l2 in lines2:
values1 = l1.strip().split()
values2 = l2.strip().split()
v1 = [float(values1[x]) for x in indices]
v2 = [float(values2[x]) for x in indices]
if self.same_samples(
v1,
v2,
places=places,
num_mismatches=num_mismatches_per_sample):
found = True
if found:
n_matches += 1
else:
n_mismatches += 1
if n_mismatches > 0:
if n_mismatches > num_sample_mismatches:
all_equal = False
diffs.write('{0} and {1}\nhave {2} mismatching samples and '
'share {3} samples\n'.format(
f1.name, f2.name, n_mismatches, n_matches))
if close2:
f2.close()
if diffs.getvalue() != '':
_LOG.error('files are not equal after sorting:\n{0}\n'.format(
diffs.getvalue()))
self.assertTrue(all_equal)
if close:
f1.close()
def assertSameDistributions(self, d1, d2):
self.assertEqual(d1.name, d2.name)
self.assertEqual(str(d1), str(d2))
self.assertEqual(d1.minimum, d2.minimum)
self.assertEqual(d1.maximum, d2.maximum)
self.assertEqual(d1.mean, d2.mean)
self.assertEqual(d1.variance, d2.variance)
def assertSameIntegerPartitions(self, integer_partitions):
ips = list(integer_partitions)
ip1 = ips.pop(0)
for ip2 in ips:
self.assertEqual(ip1._initialized, ip2._initialized)
self.assertEqual(ip1.n, ip2.n)
self.assertEqual(ip1.key, ip2.key)
self.assertEqual(ip1.integer_partition, ip2.integer_partition)
self.assertEqual(ip1._items, ip2._items)
def assertSamePartitions(self, partitions):
ps = list(partitions)
p1 = ps.pop(0)
for p2 in ps:
self.assertEqual(p1._initialized, p2._initialized)
self.assertEqual(p1.n, p2.n)
self.assertEqual(p1.key, p2.key)
self.assertEqual(p1.partition, p2.partition)
self.assertEqual(p1.values, p2.values)
def set_up(self):
self.temp_fs = TempFileSystem(
parent = package_paths.test_path(),
prefix = 'PyMsBayesTestTemp-')
self.test_id = 'pymsbayes-' + random_str()
def main_cli():
description = '{name} {version}'.format(**_program_info)
parser = argparse.ArgumentParser(description = description,
formatter_class = argparse_utils.SmartHelpFormatter)
parser.add_argument('-c', '--config',
type = argparse_utils.arg_is_config,
required = True,
help = ('msBayes config file to be used to generate saturation '
'plot.'))
parser.add_argument('-n', '--num-prior-samples',
action = 'store',
type = int,
default = 1000,
help = ('The number of prior samples to simulate for the '
'saturation plot.'))
parser.add_argument('--np',
action = 'store',
type = int,
default = multiprocessing.cpu_count(),
help = ('The maximum number of processes to run in parallel. The '
'default is the number of CPUs available on the machine.'))
parser.add_argument('-o', '--output-dir',
action = 'store',
type = argparse_utils.arg_is_dir,
help = ('The directory in which all output files will be written. '
'The default is to use the directory of the first observed '
'config file.'))
parser.add_argument('--temp-dir',
action = 'store',
type = argparse_utils.arg_is_dir,
help = ('A directory to temporarily stage files. The default is to '
'use the output directory.'))
parser.add_argument('-s', '--stat-prefixes',
nargs = '*',
type = str,
default = ['pi', 'pi.net', 'wattTheta', 'tajD.denom'],
help = ('Prefixes of summary statistics to use in the analyses. '
'The prefixes should be separated by spaces. '
'Default: `-s pi pi.net wattTheta tajD.denom`.'))
parser.add_argument('--sort-index',
action = 'store',
type = int,
default = 0,
choices = range(12),
help = argparse_utils.get_sort_index_help_message())
parser.add_argument('--compress',
action = 'store_true',
help = 'Compress plot data file.')
parser.add_argument('--keep-temps',
action = 'store_true',
help = 'Keep all temporary files.')
parser.add_argument('--seed',
action = 'store',
type = int,
help = 'Random number seed to use for the analysis.')
parser.add_argument('--version',
action = 'version',
version = '%(prog)s ' + _program_info['version'],
help = 'Report version and exit.')
parser.add_argument('--quiet',
action = 'store_true',
help = 'Run without verbose messaging.')
parser.add_argument('--debug',
action = 'store_true',
help = 'Run in debugging mode.')
args = parser.parse_args()
##########################################################################
## handle args
from pymsbayes.utils.messaging import (LoggingControl,
InfoLogger)
LoggingControl.set_logging_level("INFO")
if args.quiet:
LoggingControl.set_logging_level("WARNING")
if args.debug:
LoggingControl.set_logging_level("DEBUG")
log = LoggingControl.get_logger(__name__)
from pymsbayes.workers import MsBayesWorker
from pymsbayes.utils.parsing import (get_patterns_from_prefixes,
DEFAULT_STAT_PATTERNS, get_dict_from_spreadsheets, dict_line_iter)
from pymsbayes.manager import Manager
from pymsbayes.utils.tempfs import TempFileSystem
from pymsbayes.utils import probability, stats
from pymsbayes.utils.functions import long_division
from pymsbayes.config import MsBayesConfig
from pymsbayes.utils import GLOBAL_RNG, MSBAYES_SORT_INDEX, ToolPathManager
from pymsbayes.fileio import process_file_arg
from pymsbayes import plotting
MSBAYES_SORT_INDEX.set_index(args.sort_index)
# get full paths to tools
msbayes_path = ToolPathManager.get_tool_full_path('msbayes.pl')
dpp_msbayes_path = ToolPathManager.get_tool_full_path('dpp-msbayes.pl')
if not args.output_dir:
args.output_dir = os.path.dirname(args.config)
info = InfoLogger(os.path.join(args.output_dir, 'pymsbayes-info.txt'))
sample_path = os.path.join(args.output_dir, 'prior-sample.txt')
if args.compress:
sample_path += '.gz'
if not args.temp_dir:
args.temp_dir = args.output_dir
temp_fs = TempFileSystem(parent=args.temp_dir, prefix='temp-files-')
args.stat_prefixes = [s.rstrip('.') for s in args.stat_prefixes]
stat_patterns = get_patterns_from_prefixes(
[s + '.' for s in args.stat_prefixes],
ignore_case=True)
if not args.seed:
args.seed = random.randint(1, 999999999)
GLOBAL_RNG.seed(args.seed)
compress_level = None
if args.compress:
compress_level = 9
cfg = MsBayesConfig(args.config)
num_taxon_pairs = cfg.npairs
info.write('[pymsbayes]', log.info)
info.write('\tprogram_name = {name}'.format(**_program_info), log.info)
info.write('\tversion = {version}'.format(**_program_info), log.info)
info.write('\tinvocation = {0!r}'.format(' '.join(sys.argv)), log.info)
info.write('\toutput_directory = {0!r}'.format(args.output_dir), log.info)
info.write('\ttemp_directory = {0!r}'.format(temp_fs.base_dir), log.info)
info.write('\tsort_index = {0}'.format(
MSBAYES_SORT_INDEX.current_value()), log.info)
info.write('\tstat_patterns = {0!r}'.format(
', '.join([p.pattern for p in stat_patterns])), log.info)
info.write('\tseed = {0}'.format(args.seed), log.info)
info.write('\tnum_prior_samples = {0}'.format(args.num_prior_samples),
log.info)
info.write('\tsample_path = {0!r}'.format(sample_path), log.info)
info.write('\t[[tool_paths]]', log.info)
info.write('\t\tdpp_msbayes = {0}'.format(dpp_msbayes_path), log.info)
info.write('\t\tmsbayes = {0}'.format(msbayes_path), log.info)
info.write('\t[[config]]', log.debug)
info.write('{0}'.format(str(cfg)), log.debug)
##########################################################################
## begin analysis --- generate samples
start_time = datetime.datetime.now()
if args.np > args.num_prior_samples:
args.np = args.num_prior_samples
batch_size, remainder = long_division(args.num_prior_samples, args.np)
schema = 'abctoolbox'
workers = []
for i in range(args.np):
sample_size = batch_size
if i == (args.np - 1):
sample_size += remainder
w = MsBayesWorker(
temp_fs = temp_fs,
sample_size = sample_size,
config_path = args.config,
report_parameters = True,
schema = schema,
include_header = True,
stat_patterns = stat_patterns,
write_stats_file = False)
workers.append(w)
log.info('Generating samples...')
workers = Manager.run_workers(
workers = workers,
num_processors = args.np)
log.info('Parsing samples...')
sample = get_dict_from_spreadsheets([w.prior_path for w in workers])
log.info('Writing prior samples...')
out, close = process_file_arg(sample_path, 'w',
compresslevel = compress_level)
for row in dict_line_iter(sample, sep = '\t'):
out.write(row)
if close:
out.close()
log.info('Creating plots...')
if not plotting.MATPLOTLIB_AVAILABLE:
log.warning(
'`matplotlib` could not be imported, so the plot can not be\n'
'produced. The data to create the plot can be found in:\n\t'
'{0!r}'.format(sample_path))
sys.exit(1)
for stat_pattern in stat_patterns:
found = False
for stat, values in sample.iteritems():
if stat_pattern.match(stat):
values = [float(v) for v in values]
found = True
plot_path = os.path.join(args.output_dir,
'plot-{0}.pdf'.format(stat))
summary = stats.get_summary(values)
s = r'mean = {0:.4f} ({1:.4f}-{2:.4f})'.format(
summary['mean'],
summary['qi_95'][0],
summary['qi_95'][1])
hd = plotting.HistData(x = values,
normed = True,
bins = 20,
histtype = 'bar',
align = 'mid',
orientation = 'vertical',
zorder = 0)
hist = plotting.ScatterPlot(hist_data_list = [hd],
right_text = s)
hist.left_text_size = 12.0
hist.right_text_size = 12.0
xticks = [i for i in hist.ax.get_xticks()]
xtick_labels = [i for i in xticks]
yticks = [i for i in hist.ax.get_yticks()]
ytick_labels = [i for i in yticks]
if len(xtick_labels) >= 8:
for i in range(1, len(xtick_labels), 2):
xtick_labels[i] = ''
if len(ytick_labels) >= 8:
for i in range(1, len(ytick_labels), 2):
ytick_labels[i] = ''
xticks_obj = plotting.Ticks(ticks = xticks,
labels = xtick_labels,
horizontalalignment = 'center')
yticks_obj = plotting.Ticks(ticks = yticks,
labels = ytick_labels)
hist.xticks_obj = xticks_obj
hist.yticks_obj = yticks_obj
plot_grid = plotting.PlotGrid(subplots = [hist],
num_columns = 1,
label_schema = None,
title = stat,
title_size = 14.0,
title_top = False,
y_title = 'Density',
y_title_position = 0.001,
y_title_size = 14.0,
height = 4.0,
width = 6.0,
auto_height = False)
plot_grid.auto_adjust_margins = False
plot_grid.margin_left = 0.04
plot_grid.margin_bottom = 0.04
plot_grid.margin_right = 1.0
plot_grid.margin_top = 0.97
plot_grid.reset_figure()
plot_grid.savefig(plot_path)
if not found:
raise Exception('stat pattern {0!r} not found in simulated stats:'
'\n\t{1}'.format(stat_pattern, ', '.join(sample.keys())))
stop_time = datetime.datetime.now()
log.info('Done!')
info.write('\t[[run_stats]]', log.info)
info.write('\t\tstart_time = {0}'.format(str(start_time)), log.info)
info.write('\t\tstop_time = {0}'.format(str(stop_time)), log.info)
info.write('\t\ttotal_duration = {0}'.format(str(stop_time - start_time)),
log.info)
if not args.keep_temps:
log.debug('purging temps...')
temp_fs.purge()
class PyMsBayesTestCase(unittest.TestCase):
def set_up(self):
self.temp_fs = TempFileSystem(
parent = package_paths.test_path(),
prefix = 'PyMsBayesTestTemp-')
self.test_id = 'pymsbayes-' + random_str()
def tear_down(self):
self.register_file_system()
self.temp_fs.purge()
self.assertEqual(FileStream.open_files, set())
def get_test_path(self, parent=None, prefix='temp'):
return self.temp_fs.get_file_path(parent=parent, prefix=prefix)
def get_test_subdir(self, parent=None, prefix='temp'):
return self.temp_fs.create_subdir(parent=parent, prefix=prefix)
def register_file(self, path):
self.temp_fs._register_file(path)
def register_dir(self, path):
self.temp_fs._register_dir(path)
def register_file_system(self):
_LOG.debug('registering test file system...')
for path, dirs, files, in os.walk(self.temp_fs.base_dir):
for f in files:
if f.startswith(self.test_id):
self.register_file(os.path.join(path, f))
for d in dirs:
if d.startswith(self.test_id):
self.register_dir(os.path.join(path, d))
def _exe_script(self, script_name, args, stdout = None, stderr = None,
return_code = 0):
script_path = package_paths.script_path(script_name)
if isinstance(args, str):
arg_list = args.split()
else:
arg_list = args
arg_list = [str(x) for x in arg_list]
cmd = [sys.executable, script_path] + arg_list
_LOG.debug('Invocation:\n\t{0}'.format(' '.join(cmd)))
p = subprocess.Popen(cmd, shell=False, stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
o, e = p.communicate()
exit_code = p.wait()
if exit_code != return_code:
_LOG.error("exit code {0} did not match {1}".format(exit_code,
return_code))
_LOG.error("here is the stdout:\n{0}".format(o))
_LOG.error("here is the stderr:\n{0}".format(e))
self.assertEqual(exit_code, return_code)
if stdout != None:
if o != stdout:
_LOG.error("std out did not match expected:\n{0}".format(o))
self.assertEqual(o, stdout)
if stderr != None:
if e != stderr:
_LOG.error("std error did not match expected:\n{0}".format(e))
self.assertEqual(e, stderr)
def get_expected_indices(self, num_pairs, dummy_column=True,
parameters_reported=True):
num_summary_params = 4
if _CV_INCLUDED:
num_summary_params += 1
num_params = 4*num_pairs
num_default_stats = 4*num_pairs
start = 0
if dummy_column:
start = 1
param_indices = range(start, start+num_summary_params)
start += num_summary_params
if parameters_reported:
param_indices += range(start, start+num_params)
start += num_params
stat_indices = range(start, start+num_default_stats)
return param_indices, stat_indices
def prior_file_is_valid(self, prior_path, num_of_samples,
num_of_columns=None):
try:
prior_file = open(prior_path, 'rU')
except:
_LOG.error('prior invalid: could not open prior path {0}'.format(
prior_path))
return False
nrows = 0
for i, line in enumerate(prior_file):
if nrows == 0 and HEADER_PATTERN.match(line):
pass
else:
nrows += 1
if not num_of_columns:
num_of_columns = len(line.strip().split())
ncols = len(line.strip().split())
if num_of_columns != ncols:
_LOG.error('prior invalid: num of columns at line {0} is {1} '
'NOT {2}'.format(i+1, ncols, num_of_columns))
return False
prior_file.close()
if num_of_samples != nrows:
_LOG.error('prior invalid: num of rows is {0} NOT {1}'.format(
nrows, num_of_samples))
return False
return True
def get_number_of_lines(self, path):
f, close = process_file_arg(path)
count = 0
for l in f:
count += 1
if close:
f.close()
return count
def get_number_of_header_lines(self, path):
f, close = process_file_arg(path)
count = 0
for l in f:
if HEADER_PATTERN.match(l.strip()):
count += 1
if close:
f.close()
return count
def parse_python_config(self, path):
return ConfigObj(path)
def get_config_from_msbayes_workers(self, msbayes_workers):
cfgs = [MsBayesConfig(w.config_path) for w in msbayes_workers]
self.assertSameConfigs(cfgs)
return cfgs[0]
def assertSameConfigs(self, cfgs):
configs = list(cfgs)
c1 = configs.pop(0)
for c2 in cfgs:
self.assertEqual(c1.time_in_subs_per_site,
c2.time_in_subs_per_site)
self.assertEqual(c1.npairs, c2.npairs)
self.assertEqual(c1.implementation, c2.implementation)
self.assertEqual(c1.div_model_prior, c2.div_model_prior)
self.assertEqual(c1.bottle_proportion_shared,
c2.bottle_proportion_shared)
self.assertEqual(c1.theta_parameters, c2.theta_parameters)
self.assertEqual(c1.taxa, c2.taxa)
self.assertTrue(c1.sample_table.equals(c2.sample_table))
if c1.psi:
self.assertSameDistributions(c1.psi, c2.psi)
else:
self.assertEqual(c1.psi, c2.psi)
if c1.tau:
self.assertSameDistributions(c1.tau, c2.tau)
else:
self.assertEqual(c1.tau, c2.tau)
if c1.theta:
self.assertSameDistributions(c1.theta, c2.theta)
else:
self.assertEqual(c1.theta, c2.theta)
if c1.a_theta:
self.assertSameDistributions(c1.a_theta, c2.a_theta)
else:
self.assertEqual(c1.a_theta, c2.a_theta)
if c1.d_theta:
self.assertSameDistributions(c1.d_theta, c2.d_theta)
else:
self.assertEqual(c1.d_theta, c2.d_theta)
if c1.recombination:
self.assertSameDistributions(c1.recombination, c2.recombination)
else:
self.assertEqual(c1.recombination, c2.recombination)
if c1.migration:
self.assertSameDistributions(c1.migration, c2.migration)
else:
self.assertEqual(c1.migration, c2.migration)
if c1.dpp_concentration:
self.assertSameDistributions(c1.dpp_concentration,
c2.dpp_concentration)
else:
self.assertEqual(c1.dpp_concentration, c2.dpp_concentration)
if c1.bottle_proportion:
self.assertSameDistributions(c1.bottle_proportion,
c2.bottle_proportion)
else:
self.assertEqual(c1.bottle_proportion, c2.bottle_proportion)
def get_parameter_summaries_from_msbayes_workers(self, msbayes_workers,
shuffle_taus=True):
msbayes_workers = list(msbayes_workers)
s = dict(zip(
[i for i in msbayes_workers[0].parameter_indices],
[SampleSummarizer(
tag=msbayes_workers[0].header[i]) for i in msbayes_workers[
0].parameter_indices]))
ncols = None
header = msbayes_workers[0].header
pi = msbayes_workers[0].parameter_indices
for w in msbayes_workers:
self.assertEqual(w.header, header)
self.assertEqual(w.parameter_indices, pi)
f = open(w.prior_path, 'rU')
for line_idx, row in enumerate(f):
if not ncols:
ncols = len(row.strip().split())
if HEADER_PATTERN.match(row.strip()):
continue
r = row.strip().split()
assert len(r) == ncols
if shuffle_taus: # because taus are sorted in prior files
psi_index = get_indices_of_patterns(w.header,
PSI_PATTERNS)[0]
tau_indices = get_indices_of_patterns(w.header,
TAU_PATTERNS)
psi = int(r[psi_index])
taus = [float(r[i]) for i in tau_indices]
self.assertEqual(psi, len(set(taus)))
random.shuffle(taus)
for n, i in enumerate(tau_indices):
s[i].add_sample(taus[n])
p_set = set(w.parameter_indices) - set(tau_indices)
p = sorted(list(p_set))
for i in p:
s[i].add_sample(float(r[i]))
else:
for i in w.parameter_indices:
s[i].add_sample(float(r[i]))
f.close()
return s
def assertPriorIsPrecise(self, msbayes_workers, places=2):
msbayes_workers = list(msbayes_workers)
self.assertWorkersFinished(msbayes_workers)
param_sums = self.get_parameter_summaries_from_msbayes_workers(
msbayes_workers)
sample_size = 0
for w in msbayes_workers:
sample_size += w.sample_size
for s in param_sums.itervalues():
self.assertEqual(s.n, sample_size)
cfg = self.get_config_from_msbayes_workers(msbayes_workers)
psi_indices = get_indices_of_patterns(msbayes_workers[0].header,
PSI_PATTERNS)
self.assertEqual(len(psi_indices), 1)
model_indices = get_indices_of_patterns(msbayes_workers[0].header,
MODEL_PATTERNS)
if not msbayes_workers[0].model_index is None:
self.assertEqual(len(model_indices), 1)
else:
self.assertEqual(len(model_indices), 0)
tau_indices = get_indices_of_patterns(msbayes_workers[0].header,
TAU_PATTERNS)
a_theta_indices = get_indices_of_patterns(msbayes_workers[0].header,
A_THETA_PATTERNS)
d_theta_indices = get_indices_of_patterns(msbayes_workers[0].header,
D_THETA_PATTERNS)
if msbayes_workers[0].report_parameters:
self.assertEqual(len(tau_indices), cfg.npairs)
self.assertEqual(len(a_theta_indices), cfg.npairs)
self.assertEqual(len(d_theta_indices), 2*cfg.npairs)
else:
self.assertEqual(len(tau_indices), 0)
self.assertEqual(len(a_theta_indices), 0)
self.assertEqual(len(d_theta_indices), 0)
_LOG.debug('\n{0}\n'.format('\n'.join(
[str(param_sums[i]) for i in sorted(param_sums.iterkeys())])))
for i in psi_indices:
self.assertSampleIsFromDistribution(param_sums[i], cfg.psi,
places=places)
for i in tau_indices:
self.assertSampleIsFromDistribution(param_sums[i], cfg.tau,
places=places)
for i in a_theta_indices:
self.assertSampleIsFromDistribution(param_sums[i], cfg.a_theta,
places=places)
for i in d_theta_indices:
self.assertSampleIsFromDistribution(param_sums[i], cfg.d_theta,
mean_adj=cfg.theta.mean,
max_adj=cfg.theta.maximum,
compare_variance=False,
places=places)
def assertPriorIsAccurate(self, msbayes_workers, places=2):
msbayes_workers = list(msbayes_workers)
self.assertWorkersFinished(msbayes_workers)
pass
def assertPriorIsValid(self, msbayes_workers, places=2):
msbayes_workers = list(msbayes_workers)
self.assertWorkersFinished(msbayes_workers)
self.assertPriorIsPrecise(msbayes_workers, places=places)
self.assertPriorIsAccurate(msbayes_workers, places=places)
def assertWorkersFinished(self, msbayes_workers):
for w in msbayes_workers:
self.assertTrue(w.finished)
def assertSampleIsFromDistribution(self, sample_sum, dist, places=2,
mean_adj=1,
max_adj=1,
compare_variance=True):
if isinstance(dist, probability.DiscreteUniformDistribution):
self.assertEqual(sample_sum.minimum, dist.minimum)
self.assertEqual(sample_sum.maximum, dist.maximum)
else:
if dist.minimum != float('-inf') or dist.minimum != float('inf'):
self.assertAlmostEqual(sample_sum.minimum, dist.minimum, places)
if dist.maximum != float('-inf') or dist.maximum != float('inf'):
self.assertAlmostEqual(sample_sum.maximum, dist.maximum*max_adj, places)
self.assertAlmostEqual(sample_sum.mean, dist.mean*mean_adj, places)
if compare_variance:
self.assertAlmostEqual(sample_sum.variance, dist.variance, places)
def assertApproxEqual(self, x, y, percent_tol=1e-6):
eq = (((abs(x-y) / ((abs(x)+abs(y))/2))*100) < percent_tol)
if not eq:
_LOG.error('x ({0}) and y ({1}) are not equal'.format(x, y))
self.assertTrue(eq)
def files_equal(self, f1, f2, exclude_line_endings=False):
equal = True
diffs = []
f1, c1 = process_file_arg(f1)
f2, c2 = process_file_arg(f2)
line = 0
f1_end = False
f2_end = False
lines_left = True
while True:
line += 1
if f1_end == False:
try:
l1 = f1.next()
except (StopIteration, EOFError):
f1_end = line
pass
if f2_end == False:
try:
l2 = f2.next()
except (StopIteration, EOFError):
f2_end = line
pass
if f1_end != False and f2_end != False:
break
if exclude_line_endings:
l1 = l1.strip()
l2 = l2.strip()
if f1_end == False and f2_end == False and l1 != l2:
diffs.append(line)
equal = False
if f1_end != f2_end:
mn = min([f1_end, f2_end])
mx = max([f1_end, f2_end])
diffs.extend(range(mn, mx+1))
equal = False
assert len(diffs) == len(set(diffs))
if c1:
f1.close()
if c2:
f2.close()
return equal, diffs
def assertSameFiles(self, files, exclude_line_endings=False):
files = list(files)
all_equal = True
diffs = StringIO()
f1 = files.pop(0)
for f2 in files:
equal, diff_list = self.files_equal(f1, f2, exclude_line_endings)
if not equal:
all_equal = False
n1 = f1
if not isinstance(n1, str):
n1 = f1.name
n2 = f2
if not isinstance(n2, str):
n2 = f2.name
diffs.write('{0} and {1} differ at lines:\n\t{2}\n'.format(
n1, n2, ','.join([str(i) for i in diff_list])))
if not all_equal:
_LOG.error('files are not equal:\n{0}\n'.format(diffs.getvalue()))
self.assertTrue(all_equal)
def assertSameUnsortedFiles(self, files):
files = list(files)
all_equal = True
diffs = StringIO()
f1, close = process_file_arg(files.pop(0))
lines1 = sorted(f1.readlines())
for f in files:
f2, close2 = process_file_arg(f)
lines2 = sorted(f2.readlines())
if len(lines1) != len(lines2):
all_equal = False
diffs.write('{0} ({1}) and {2} ({3}) have different '
'number of lines\n'.format(f1.name, len(lines1),
f2.name, len(lines2)))
for i in range(min(len(lines1), len(lines2))):
if lines1[i].strip().split() != lines2[i].strip().split():
all_equal = False
diffs.write('{0} and {1} differ at sorted index '
'{2}\n'.format(f1.name, f2.name, i))
if close2:
f2.close()
if not all_equal:
_LOG.error('files are not equal after sorting:\n{0}\n'.format(
diffs.getvalue()))
self.assertTrue(all_equal)
if close:
f1.close()
def same_samples(self, sample1, sample2, places = 4, num_mismatches = 0):
if len(sample1) != len(sample2):
return False
for i in range(len(sample1)):
if round(float(sample1[i]) - float(sample2[i]), places) != 0:
if num_mismatches < 1:
return False
num_mismatches -= 1
return True
def assertSameSamples(self, files, columns_to_ignore = [], header = True,
places = 5, num_mismatches_per_sample = 0,
num_sample_mismatches = 0):
files = list(files)
all_equal = True
diffs = StringIO()
f1, close = process_file_arg(files.pop(0))
f1_lines = f1.readlines()
indices = [i for i in range(len(
f1_lines[0].strip().split())) if i not in columns_to_ignore]
h1 = []
if header:
head = f1_lines.pop(0).strip().split()
h1 = [head[i] for i in indices]
lines1 = sorted(f1_lines)
for f in files:
f2, close2 = process_file_arg(f)
f2_lines = f2.readlines()
h2 = []
if header:
head = f2_lines.pop(0).strip().split()
h2 = [head[i] for i in indices]
if h1 != h2:
all_equal = False
diffs.write('{0} and {1} have different headers; not '
'comparing further\n'.format(
f1.name, f2.name))
continue
lines2 = sorted(f2_lines)
if len(lines1) != len(lines2):
all_equal = False
diffs.write('{0} ({1}) and {2} ({3}) have different '
'number of lines\n'.format(f1.name, len(lines1),
f2.name, len(lines2)))
n_matches = 0
n_mismatches = 0
for l1 in lines1:
found = False
for l2 in lines2:
values1 = l1.strip().split()
values2 = l2.strip().split()
v1 = [float(values1[x]) for x in indices]
v2 = [float(values2[x]) for x in indices]
if self.same_samples(v1, v2, places = places,
num_mismatches = num_mismatches_per_sample):
found = True
if found:
n_matches += 1
else:
n_mismatches += 1
if n_mismatches > 0:
if n_mismatches > num_sample_mismatches:
all_equal = False
diffs.write('{0} and {1}\nhave {2} mismatching samples and '
'share {3} samples\n'.format(
f1.name, f2.name, n_mismatches, n_matches))
if close2:
f2.close()
if diffs.getvalue() != '':
_LOG.error('files are not equal after sorting:\n{0}\n'.format(
diffs.getvalue()))
self.assertTrue(all_equal)
if close:
f1.close()
def assertSameDistributions(self, d1, d2):
self.assertEqual(d1.name, d2.name)
self.assertEqual(str(d1), str(d2))
self.assertEqual(d1.minimum, d2.minimum)
self.assertEqual(d1.maximum, d2.maximum)
self.assertEqual(d1.mean, d2.mean)
self.assertEqual(d1.variance, d2.variance)
def assertSameIntegerPartitions(self, integer_partitions):
ips = list(integer_partitions)
ip1 = ips.pop(0)
for ip2 in ips:
self.assertEqual(ip1._initialized, ip2._initialized)
self.assertEqual(ip1.n, ip2.n)
self.assertEqual(ip1.key, ip2.key)
self.assertEqual(ip1.integer_partition, ip2.integer_partition)
self.assertEqual(ip1._items, ip2._items)
def assertSamePartitions(self, partitions):
ps = list(partitions)
p1 = ps.pop(0)
for p2 in ps:
self.assertEqual(p1._initialized, p2._initialized)
self.assertEqual(p1.n, p2.n)
self.assertEqual(p1.key, p2.key)
self.assertEqual(p1.partition, p2.partition)
self.assertEqual(p1.values, p2.values)
def main_cli():
description = '{name} {version}'.format(**_program_info)
parser = argparse.ArgumentParser(description=description)
parser.add_argument(
'-c',
'--config',
type=arg_is_config,
required=True,
help=('msBayes config file to be used to generate saturation '
'plot.'))
parser.add_argument(
'-n',
'--num-prior-samples',
action='store',
type=int,
default=1000,
help=('The number of prior samples to simulate for the '
'saturation plot.'))
parser.add_argument(
'--np',
action='store',
type=int,
default=multiprocessing.cpu_count(),
help=('The maximum number of processes to run in parallel. The '
'default is the number of CPUs available on the machine.'))
parser.add_argument(
'-o',
'--output-dir',
action='store',
type=arg_is_dir,
help=('The directory in which all output files will be written. '
'The default is to use the directory of the first observed '
'config file.'))
parser.add_argument(
'--temp-dir',
action='store',
type=arg_is_dir,
help=('A directory to temporarily stage files. The default is to '
'use the output directory.'))
parser.add_argument(
'-s',
'--stat-prefixes',
nargs='*',
type=str,
default=['pi', 'pi.net', 'wattTheta', 'tajD.denom'],
help=('Prefixes of summary statistics to use in the analyses. '
'The prefixes should be separated by spaces. '
'Default: `-s pi pi.net wattTheta tajD.denom`.'))
parser.add_argument(
'--vertical-lines',
nargs='*',
type=float,
default=[],
help=('Positions along x-axis where vertical lines are to be '
'drawn. Default is to draw no vertical lines.'))
parser.add_argument('--compress',
action='store_true',
help='Compress plot data file.')
parser.add_argument('--keep-temps',
action='store_true',
help='Keep all temporary files.')
parser.add_argument('--seed',
action='store',
type=int,
help='Random number seed to use for the analysis.')
parser.add_argument('--version',
action='version',
version='%(prog)s ' + _program_info['version'],
help='Report version and exit.')
parser.add_argument('--quiet',
action='store_true',
help='Run without verbose messaging.')
parser.add_argument('--debug',
action='store_true',
help='Run in debugging mode.')
args = parser.parse_args()
##########################################################################
## handle args
from pymsbayes.utils.messaging import (LoggingControl, InfoLogger)
LoggingControl.set_logging_level("INFO")
if args.quiet:
LoggingControl.set_logging_level("WARNING")
if args.debug:
LoggingControl.set_logging_level("DEBUG")
log = LoggingControl.get_logger(__name__)
from pymsbayes.workers import MsBayesWorker
from pymsbayes.utils.parsing import (get_patterns_from_prefixes,
DEFAULT_STAT_PATTERNS,
get_stats_by_time, dict_line_iter)
from pymsbayes.manager import Manager
from pymsbayes.utils.tempfs import TempFileSystem
from pymsbayes.utils import probability
from pymsbayes.utils.functions import long_division
from pymsbayes.config import MsBayesConfig
from pymsbayes.utils import GLOBAL_RNG, MSBAYES_SORT_INDEX, ToolPathManager
from pymsbayes.fileio import process_file_arg
from pymsbayes.plotting import MATPLOTLIB_AVAILABLE, SaturationPlotGrid
MSBAYES_SORT_INDEX.set_index(0)
# get full paths to tools
msbayes_path = ToolPathManager.get_tool_full_path('msbayes.pl')
dpp_msbayes_path = ToolPathManager.get_tool_full_path('dpp-msbayes.pl')
if not args.output_dir:
args.output_dir = os.path.dirname(args.config)
info = InfoLogger(os.path.join(args.output_dir, 'pymsbayes-info.txt'))
stats_by_time_path = os.path.join(args.output_dir, 'stats-by-time.txt')
if args.compress:
stats_by_time_path += '.gz'
plot_path = os.path.join(args.output_dir, 'saturation-plot.pdf')
if not args.temp_dir:
args.temp_dir = args.output_dir
temp_fs = TempFileSystem(parent=args.temp_dir, prefix='temp-files-')
args.stat_prefixes = [s.rstrip('.') for s in args.stat_prefixes]
stat_patterns = get_patterns_from_prefixes(
[s + '.' for s in args.stat_prefixes], ignore_case=True)
if not args.seed:
args.seed = random.randint(1, 999999999)
GLOBAL_RNG.seed(args.seed)
compress_level = None
if args.compress:
compress_level = 9
cfg = MsBayesConfig(args.config)
num_taxon_pairs = cfg.npairs
cfg.div_model_prior = 'constrained'
cfg.psi = probability.DiscreteUniformDistribution(num_taxon_pairs,
num_taxon_pairs)
config_path = temp_fs.get_file_path(prefix='cfg-')
cfg.write(config_path)
info.write('[pymsbayes]', log.info)
info.write('\tprogram_name = {name}'.format(**_program_info), log.info)
info.write('\tversion = {version}'.format(**_program_info), log.info)
info.write('\tinvocation = {0!r}'.format(' '.join(sys.argv)), log.info)
info.write('\toutput_directory = {0!r}'.format(args.output_dir), log.info)
info.write('\ttemp_directory = {0!r}'.format(temp_fs.base_dir), log.info)
info.write('\tsort_index = {0}'.format(MSBAYES_SORT_INDEX.current_value()),
log.info)
info.write(
'\tstat_patterns = {0!r}'.format(', '.join(
[p.pattern for p in stat_patterns])), log.info)
info.write('\tseed = {0}'.format(args.seed), log.info)
info.write('\tnum_prior_samples = {0}'.format(args.num_prior_samples),
log.info)
info.write('\tstats_by_time_path = {0!r}'.format(stats_by_time_path),
log.info)
info.write('\t[[tool_paths]]', log.info)
info.write('\t\tdpp_msbayes = {0}'.format(dpp_msbayes_path), log.info)
info.write('\t\tmsbayes = {0}'.format(msbayes_path), log.info)
info.write('\t[[config]]', log.debug)
info.write('{0}'.format(str(cfg)), log.debug)
##########################################################################
## begin analysis --- generate samples
start_time = datetime.datetime.now()
if args.np > args.num_prior_samples:
args.np = args.num_prior_samples
batch_size, remainder = long_division(args.num_prior_samples, args.np)
schema = 'abctoolbox'
workers = []
for i in range(args.np):
sample_size = batch_size
if i == (args.np - 1):
sample_size += remainder
w = MsBayesWorker(temp_fs=temp_fs,
sample_size=sample_size,
config_path=config_path,
report_parameters=True,
schema=schema,
include_header=True,
stat_patterns=stat_patterns,
write_stats_file=False)
workers.append(w)
log.info('Generating samples...')
workers = Manager.run_workers(workers=workers, num_processors=args.np)
log.info('Parsing samples...')
stats_by_time = get_stats_by_time([w.prior_path for w in workers])
stat_keys = stats_by_time.keys()
stat_keys.remove('PRI.t')
for prefix in args.stat_prefixes:
if not prefix in stat_keys:
raise Exception('stat prefix {0!r} not found in simulated stats:'
'\n\t{1}'.format(prefix, ', '.join(stat_keys)))
header = ['PRI.t'] + args.stat_prefixes
log.info('Writing stats-by-time matrix...')
out, close = process_file_arg(stats_by_time_path,
'w',
compresslevel=compress_level)
for row in dict_line_iter(stats_by_time, sep='\t', header=header):
out.write(row)
if close:
out.close()
log.info('Creating plots...')
if not MATPLOTLIB_AVAILABLE:
log.warning(
'`matplotlib` could not be imported, so the plot can not be\n'
'produced. The data to create the plot can be found in:\n\t'
'{0!r}'.format(stats_by_time_path))
else:
y_labels = {
'pi': r'$\pi$',
'pi.net': r'$\pi_{net}$',
'wattTheta': r'$\theta_W$',
'tajD.denom': r'$SD(\pi - \theta_W)$'
}
spg = SaturationPlotGrid(stats_by_time,
x_key='PRI.t',
y_keys=args.stat_prefixes,
y_labels=y_labels,
num_columns=2,
vertical_line_positions=args.vertical_lines)
fig = spg.create_grid()
fig.savefig(plot_path)
stop_time = datetime.datetime.now()
log.info('Done!')
info.write('\t[[run_stats]]', log.info)
info.write('\t\tstart_time = {0}'.format(str(start_time)), log.info)
info.write('\t\tstop_time = {0}'.format(str(stop_time)), log.info)
info.write('\t\ttotal_duration = {0}'.format(str(stop_time - start_time)),
log.info)
if not args.keep_temps:
log.debug('purging temps...')
temp_fs.purge()
def main_cli(argv = sys.argv):
description = '{name} {version}'.format(**_program_info)
parser = argparse.ArgumentParser(description = description,
formatter_class = argparse_utils.SmartHelpFormatter)
parser.add_argument('-o', '--observed-configs',
nargs = '+',
type = argparse_utils.arg_is_config,
required = True,
help = ('One or more msBayes config files to be used to either '
'calculate or simulate observed summary statistics. If '
'used in combination with `-r` each config will be used to '
'simulate pseudo-observed data. If analyzing real data, do '
'not use the `-r` option, and the fasta files specified '
'within the config must exist and contain the sequence '
'data.'))
parser.add_argument('-p', '--prior-configs',
nargs = '+',
type = argparse_utils.arg_is_path,
required = True,
help = ('One or more config files to be used to generate prior '
'samples. If more than one config is specified, they '
'should be separated by spaces. '
'This option can also be used to specify the path to a '
'directory containing the prior samples and summary '
'statistic means and standard deviations generated by a '
'previous run using the `generate-samples-only` option. '
'These files should be found in the directory '
'`pymsbayes-output/prior-stats-summaries`. The'
'`pymsbayes-output/model-key.txt` also needs to be present.'
' If specifying this directory, it should be the only '
'argument (i.e., no other directories or config files can '
'be provided).'))
parser.add_argument('-r', '--reps',
action = 'store',
type = argparse_utils.arg_is_nonnegative_int,
default = 0,
help = ('This option has two effects. First, it signifies that '
'the analysis will be simulation based (i.e., no real '
'data will be used). Second, it specifies how many '
'simulation replicates to perform (i.e., how many data '
'sets to simulate and analyze).'))
parser.add_argument('-n', '--num-prior-samples',
action = 'store',
type = argparse_utils.arg_is_positive_int,
default = 1000000,
help = ('The number of prior samples to simulate for each prior '
'config specified with `-p`.'))
parser.add_argument('--prior-batch-size',
action = 'store',
type = argparse_utils.arg_is_positive_int,
default = 10000,
help = ('The number of prior samples to simulate for each batch.'))
parser.add_argument('--generate-samples-only',
action = 'store_true',
help = ('Only generate samples from models as requested. I.e., '
'No analyses are performed to approximate posteriors. '
'This option can be useful if you want the prior samples '
'for other purposes.'))
parser.add_argument('--num-posterior-samples',
action = 'store',
type = argparse_utils.arg_is_positive_int,
default = 1000,
help = ('The number of posterior samples desired for each '
'analysis. Default: 1000.'))
parser.add_argument('--num-standardizing-samples',
action = 'store',
type = argparse_utils.arg_is_positive_int,
default = 10000,
help = ('The number of prior samples desired to use for '
'standardizing statistics. Default: 10000.'))
parser.add_argument('--np',
action = 'store',
type = argparse_utils.arg_is_positive_int,
default = multiprocessing.cpu_count(),
help = ('The maximum number of processes to run in parallel. The '
'default is the number of CPUs available on the machine.'))
parser.add_argument('--output-dir',
action = 'store',
type = argparse_utils.arg_is_dir,
help = ('The directory in which all output files will be written. '
'The default is to use the directory of the first observed '
'config file.'))
parser.add_argument('--temp-dir',
action = 'store',
type = argparse_utils.arg_is_dir,
help = ('A directory to temporarily stage files. The default is to '
'use the output directory.'))
parser.add_argument('--staging-dir',
action = 'store',
type = argparse_utils.arg_is_dir,
help = ('A directory to temporarily stage prior files. This option '
'can be useful on clusters to speed up I/O while '
'generating prior samples. You can designate a local temp '
'directory on a compute node to avoid constant writing to '
'a shared drive. The default is to use the `temp-dir`.'))
parser.add_argument('-s', '--stat-prefixes',
nargs = '*',
type = str,
help = ('Prefixes of summary statistics to use in the analyses. '
'The prefixes should be separated by spaces. '
'Default: `-s pi wattTheta pi.net tajD.denom`.'))
parser.add_argument('-b', '--bandwidth',
action = 'store',
type = float,
help = ('Smoothing parameter for the posterior kernal density '
'estimation. This option is used for the `glm` '
'regression method. The default is 2 / '
'`num-posterior-samples`.'))
parser.add_argument('-q', '--num-posterior-quantiles',
action = 'store',
type = argparse_utils.arg_is_positive_int,
default = 1000,
help = ('The number of equally spaced quantiles at which to '
'evaluate the GLM-estimated posterior density. '
'Default: 1000.'))
parser.add_argument('--reporting-frequency',
action = 'store',
type = argparse_utils.arg_is_nonnegative_int,
default = 0,
help = ('Suggested frequency (in number of prior samples) for '
'running regression and reporting current results. '
'Default: 0 (only report final results). '
'If a value is given, it may be adjusted so that the '
'reporting frequency is a multiple of the multi-processed '
'batch size.'))
parser.add_argument('--sort-index',
action = 'store',
type = argparse_utils.arg_is_nonnegative_int,
default = 0,
choices = range(12),
help = argparse_utils.get_sort_index_help_message())
parser.add_argument('--no-global-estimate',
action = 'store_true',
help = ('If multiple prior models are specified, by default a '
'global estimate is performed averaging over all models. '
'This option prevents the global estimation (i.e., only '
'inferences for each model are made).'))
parser.add_argument('--compress',
action = 'store_true',
help = 'Compress large results files.')
parser.add_argument('--keep-temps',
action = 'store_true',
help = 'Keep all temporary files.')
parser.add_argument('--seed',
action = 'store',
type = int,
help = 'Random number seed to use for the analysis.')
parser.add_argument('--output-prefix',
action = 'store',
type = str,
default = '',
help = ('Prefix to use at beginning of output files. The default '
'is no prefix.'))
parser.add_argument('--data-key-path',
action = 'store',
type = argparse_utils.arg_is_file,
help = ('The path to a `data-key.txt` file generated by a previous '
'run. This file should be found in the directory '
'`pymsbayes-output/data-key.txt`. This option '
'will override the `-o`/`--observed-configs` option, and '
'is intended to be used in combination with the '
'`--start-from` option to restart an analysis.'))
parser.add_argument('--start-from-simulation-index',
action = 'store',
type = argparse_utils.arg_is_nonnegative_int,
default = 0,
help = ('The simulation index at which to begin analyses. Must be '
'used in combination with either the number of simulation '
'replicates (`-r`/`--reps`) or the `--data-key-path` '
'option, and must be a positive '
'integer that is less than the number of simulation '
'replicates. This option can be useful if an analysis '
'needs to be restarted.'))
parser.add_argument('--start-from-observed-index',
action = 'store',
type = argparse_utils.arg_is_nonnegative_int,
default = 0,
help = ('The observed config index at which to begin analyses. '
'Can be used in combination with the `--data-key-path` '
'option to restart long-running, multi-observed-config '
'analyses'))
parser.add_argument('--dry-run',
action = 'store_true',
help = 'Do not run analyses; only process settings')
parser.add_argument('--version',
action = 'version',
version = '%(prog)s ' + _program_info['version'],
help = 'Report version and exit.')
parser.add_argument('--quiet',
action = 'store_true',
help = 'Run without verbose messaging.')
parser.add_argument('--debug',
action = 'store_true',
help = 'Run in debugging mode.')
if argv == sys.argv:
args = parser.parse_args()
else:
args = parser.parse_args(argv)
##########################################################################
## handle args
from pymsbayes.utils.messaging import (LoggingControl,
InfoLogger)
LoggingControl.set_logging_level("INFO")
if args.quiet:
LoggingControl.set_logging_level("WARNING")
if args.debug:
LoggingControl.set_logging_level("DEBUG")
log = LoggingControl.get_logger(__name__)
from pymsbayes.workers import (MsBayesWorker, merge_prior_files,
ObsSumStatsWorker)
from pymsbayes.teams import ABCTeam
from pymsbayes.utils.functions import (is_file, is_dir, long_division,
mk_new_dir)
from pymsbayes.utils.parsing import (get_patterns_from_prefixes,
DEFAULT_STAT_PATTERNS, DIV_MODEL_PATTERNS, MODEL_PATTERNS,
PSI_PATTERNS, MEAN_TAU_PATTERNS, OMEGA_PATTERNS, CV_PATTERNS,
line_count)
from pymsbayes.utils import sumresults, errors
from pymsbayes.manager import Manager
from pymsbayes.utils.tempfs import TempFileSystem
from pymsbayes.config import MsBayesConfig
from pymsbayes.utils import (GLOBAL_RNG, set_memory_trace,
MSBAYES_SORT_INDEX, ToolPathManager)
MSBAYES_SORT_INDEX.set_index(args.sort_index)
if len(args.observed_configs) != len(set(args.observed_configs)):
raise ValueError('All paths to observed config files must be unique')
if args.num_standardizing_samples > args.num_prior_samples:
args.num_standardizing_samples = args.num_prior_samples
# get full paths to tools
msbayes_path = ToolPathManager.get_tool_full_path('msbayes.pl')
dpp_msbayes_path = ToolPathManager.get_tool_full_path('dpp-msbayes.pl')
eureject_path = ToolPathManager.get_tool_full_path('eureject')
abctb_path = ToolPathManager.get_tool_full_path('ABCestimator')
# vet prior-configs option
using_previous_priors = False
previous_prior_dir = None
if (len(args.prior_configs) == 1) and (is_dir(args.prior_configs[0])):
previous_prior_dir = args.prior_configs.pop(0)
previous_priors = glob.glob(os.path.join(previous_prior_dir,
'*-prior-sample.txt'))
previous_sums = glob.glob(os.path.join(previous_prior_dir,
'*-means-and-std-devs.txt'))
if (not previous_priors) or (not previous_sums):
raise ValueError('directory {0!r} specified with `prior-configs` '
'option does not contain necessary prior and summary '
'files'.format(args.prior_configs[0]))
using_previous_priors = True
else:
for path in args.prior_configs:
if not is_file(path):
raise ValueError('prior config {0!r} is not a file'.format(
path))
if len(args.prior_configs) != len(set(args.prior_configs)):
raise ValueError('All paths to prior config files must be unique')
if not args.output_dir:
args.output_dir = os.path.dirname(args.observed_configs[0])
base_dir = mk_new_dir(os.path.join(args.output_dir, 'pymsbayes-results'))
if not args.temp_dir:
args.temp_dir = base_dir
info_path = os.path.join(base_dir, args.output_prefix + \
'pymsbayes-info.txt')
info = InfoLogger(info_path)
info.write('[pymsbayes]'.format(base_dir))
info.write('\tversion = {version}'.format(**_program_info))
info.write('\toutput_directory = {0}'.format(base_dir))
temp_fs = TempFileSystem(parent=args.temp_dir, prefix='temp-files-')
base_temp_dir = temp_fs.base_dir
info.write('\ttemp_directory = {0}'.format(base_temp_dir))
info.write('\tsort_index = {0}'.format(
MSBAYES_SORT_INDEX.current_value()))
info.write('\tsimulation_reps = {0}'.format(args.reps))
stat_patterns = DEFAULT_STAT_PATTERNS
if args.stat_prefixes:
for i in range(len(args.stat_prefixes)):
if not args.stat_prefixes[i].endswith('.'):
args.stat_prefixes[i] += '.'
stat_patterns = get_patterns_from_prefixes(
args.stat_prefixes,
ignore_case=True)
if not args.bandwidth:
args.bandwidth = 2 / float(args.num_posterior_samples)
if not args.seed:
args.seed = random.randint(1, 999999999)
GLOBAL_RNG.seed(args.seed)
if args.data_key_path:
observed_map = sumresults.parse_data_key_file(args.data_key_path)
observed_paths = [observed_map[k] for k in sorted(observed_map.keys())]
else:
observed_dir = mk_new_dir(os.path.join(base_dir,
'observed-summary-stats'))
observed_paths = [os.path.join(observed_dir, args.output_prefix + \
'observed-{0}.txt'.format(i+1)) for i in range(len(
args.observed_configs))]
info.write('\tseed = {0}'.format(args.seed))
info.write('\tnum_processors = {0}'.format(args.np))
info.write('\tnum_prior_samples = {0}'.format(
args.num_prior_samples))
info.write('\tnum_standardizing_samples = {0}'.format(
args.num_standardizing_samples))
info.write('\tbandwidth = {0}'.format(args.bandwidth))
info.write('\tposterior_quantiles = {0}'.format(
args.num_posterior_quantiles))
info.write('\tposterior_sample_size = {0}'.format(
args.num_posterior_samples))
info.write('\tstat_patterns = {0}'.format(
', '.join([p.pattern for p in stat_patterns])))
# vet observed configs
ref_config_path = args.observed_configs[0]
ref_config = MsBayesConfig(ref_config_path)
all_config_paths = []
num_taxon_pairs = ref_config.npairs
assert num_taxon_pairs > 0
for config in args.observed_configs:
all_config_paths.append(config)
if not ref_config.equal_sample_table(config):
if not args.keep_temps:
temp_fs.purge()
raise errors.SampleTableError(
'sample tables in config {0!r} and {1!r} differ; '
'all sample tables must be the same.'.format(
ref_config_path, config))
info.write('\tnum_taxon_pairs = {0}'.format(num_taxon_pairs))
info.write('\tdry_run = {0}'.format(args.dry_run))
info.write('\t[[tool_paths]]')
info.write('\t\tdpp_msbayes = {0}'.format(dpp_msbayes_path))
info.write('\t\tmsbayes = {0}'.format(msbayes_path))
info.write('\t\teureject = {0}'.format(eureject_path))
info.write('\t\tabcestimator = {0}'.format(abctb_path))
info.write('\t[[observed_configs]]')
for i, cfg in enumerate(args.observed_configs):
info.write('\t\t{0} = {1}'.format(i + 1, os.path.relpath(cfg,
os.path.dirname(info_path))))
abc_team = ABCTeam(
temp_fs = temp_fs,
observed_stats_files = observed_paths,
num_taxon_pairs = num_taxon_pairs,
config_paths = args.prior_configs,
previous_prior_dir = previous_prior_dir,
num_prior_samples = args.num_prior_samples,
num_processors = args.np,
num_standardizing_samples = args.num_standardizing_samples,
num_posterior_samples = args.num_posterior_samples,
num_posterior_density_quantiles = args.num_posterior_quantiles,
batch_size = args.prior_batch_size,
output_dir = base_dir,
output_prefix = args.output_prefix,
prior_temp_dir = args.staging_dir,
rng = GLOBAL_RNG,
report_parameters = True,
stat_patterns = stat_patterns,
eureject_exe_path = eureject_path,
abctoolbox_exe_path = abctb_path,
msbayes_exe_path = None,
abctoolbox_bandwidth = args.bandwidth,
omega_threshold = 0.01,
cv_threshold = 0.01,
compress = args.compress,
reporting_frequency = args.reporting_frequency,
keep_temps = args.keep_temps,
global_estimate_only = False,
global_estimate = not args.no_global_estimate,
generate_prior_samples_only = args.generate_samples_only,
start_from_simulation_index = args.start_from_simulation_index,
start_from_observed_index = args.start_from_observed_index)
models_to_configs = {}
configs_to_models = {}
for k, v in abc_team.models.iteritems():
models_to_configs[k] = v
configs_to_models[v] = k
cfg = MsBayesConfig(v)
all_config_paths.append(v)
# vet prior configs
if not ref_config.equal_sample_table(cfg):
if not args.keep_temps:
temp_fs.purge()
raise errors.SampleTableError(
'sample tables in config {0!r} and {1!r} differ; '
'all sample tables must be the same.'.format(
ref_config_path, v))
info.write('\t[[observed_paths]]')
for i in sorted(abc_team.observed_stats_paths.iterkeys()):
info.write('\t\t{0} = {1}'.format(i, os.path.relpath(
abc_team.observed_stats_paths[i],
os.path.dirname(info_path))))
info.write('\t[[prior_configs]]')
for i in sorted(abc_team.models.iterkeys()):
info.write('\t\t{0} = {1}'.format(i, os.path.relpath(
abc_team.models[i],
os.path.dirname(info_path))))
##########################################################################
## begin analysis --- get observed summary stats
set_memory_trace() # start logging memory profile
start_time = datetime.datetime.now()
if args.data_key_path:
log.info('Using provided summary statitics...')
elif not args.dry_run:
obs_temp_dir = base_temp_dir
if args.staging_dir:
obs_temp_dir = args.staging_dir
observed_temp_fs = TempFileSystem(parent = obs_temp_dir,
prefix = 'observed-temps-')
if args.reps < 1:
log.info('Calculating summary statistics from sequence data...')
obs_workers = []
for i, cfg in enumerate(args.observed_configs):
ss_worker = ObsSumStatsWorker(
temp_fs = observed_temp_fs,
config_path = cfg,
output_path = observed_paths[i],
schema = 'abctoolbox',
stat_patterns = stat_patterns)
obs_workers.append(ss_worker)
obs_workers = Manager.run_workers(
workers = obs_workers,
num_processors = args.np)
# re-vet all configs to see if some were changed by obsSumStats.pl
new_ref_config = ref_config
ref_modified = False
# new ref because if all configs were updated all is good
if not ref_config.equal_sample_table(ref_config_path):
ref_modified = True
new_ref_config = MsBayesConfig(ref_config_path)
log.warning("""
The alignment lengths in config
{0!r}
have been corrected for sites with *any* ambiguous bases and/or gaps by
obsSumStats.pl.
""".format(ref_config_path))
for config in all_config_paths:
if not new_ref_config.equal_sample_table(config):
corrected_config = config
if ref_modified:
corrected_config = ref_config_path
if not args.keep_temps:
observed_temp_fs.purge()
temp_fs.purge()
raise errors.SampleTableError("""
The sample tables in configs
{0!r}
and
{1!r}
differ because obsSumStats.pl modified alignment lengths in config
{2!r}
to correct for sites in the alignments with *any* ambiguous bases and/or gaps.
Please make sure the sample tables in all configs will be the same after
correcting alignment lengths for sites that contain *any* ambiguous bases
and/or gaps. You can do this by copying and pasting the sample table in
{2!r}
that has been corrected by obsSumStats.pl into the other configs that were not
corrected.
""".format(ref_config_path, config, corrected_config))
else:
log.info('Simulating summary statistics from observed configs...')
num_observed_workers = min([args.reps, args.np])
if args.reps <= args.np:
observed_batch_size = 1
remainder = 0
else:
observed_batch_size, remainder = long_division(args.reps,
args.np)
msbayes_workers = []
for idx, cfg in enumerate(args.observed_configs):
observed_model_idx = configs_to_models.get(cfg,
None)
schema = 'abctoolbox'
for i in range(num_observed_workers):
worker = MsBayesWorker(
temp_fs = observed_temp_fs,
sample_size = observed_batch_size,
config_path = cfg,
model_index = observed_model_idx,
report_parameters = True,
schema = schema,
include_header = True,
stat_patterns = stat_patterns,
write_stats_file = False,
staging_dir = None,
tag = idx)
msbayes_workers.append(worker)
if remainder > 0:
worker = MsBayesWorker(
temp_fs = observed_temp_fs,
sample_size = remainder,
config_path = cfg,
model_index = observed_model_idx,
report_parameters = True,
schema = schema,
include_header = True,
stat_patterns = stat_patterns,
write_stats_file = False,
staging_dir = None,
tag = idx)
msbayes_workers.append(worker)
# run parallel msbayes processes
msbayes_workers = Manager.run_workers(
workers = msbayes_workers,
num_processors = args.np)
workers = dict(zip(range(len(args.observed_configs)),
[[] for i in range(len(args.observed_configs))]))
for w in msbayes_workers:
workers[w.tag].append(w)
# merge simulated observed data into one file
for i in range(len(args.observed_configs)):
merge_prior_files([w.prior_path for w in workers[i]],
observed_paths[i])
lc = line_count(observed_paths[i], ignore_headers=True)
if lc != args.reps:
if not args.keep_temps:
temp_fs.purge()
raise Exception('The number of observed simulations ({0}) '
'generated for observed config {1!r} and output to '
'file {2!r} does not match the number of reps '
'({3})'.format(lc, args.observed_configs[i],
observed_paths[i], args.reps))
if not args.keep_temps:
log.debug('purging observed temps...')
observed_temp_fs.purge()
##########################################################################
## Begin ABC analyses
if not args.dry_run:
abc_team.run()
stop_time = datetime.datetime.now()
log.info('Done!')
info.write('\t[[run_stats]]', log.info)
info.write('\t\tstart_time = {0}'.format(str(start_time)), log.info)
info.write('\t\tstop_time = {0}'.format(str(stop_time)), log.info)
info.write('\t\ttotal_duration = {0}'.format(str(stop_time - start_time)),
log.info)
if not args.keep_temps:
log.debug('purging temps...')
temp_fs.purge()
def main_cli(argv=sys.argv):
description = '{name} {version}'.format(**_program_info)
parser = argparse.ArgumentParser(
description=description,
formatter_class=argparse_utils.SmartHelpFormatter)
parser.add_argument(
'-o',
'--observed-configs',
nargs='+',
type=argparse_utils.arg_is_config,
required=True,
help=('One or more msBayes config files to be used to either '
'calculate or simulate observed summary statistics. If '
'used in combination with `-r` each config will be used to '
'simulate pseudo-observed data. If analyzing real data, do '
'not use the `-r` option, and the fasta files specified '
'within the config must exist and contain the sequence '
'data.'))
parser.add_argument(
'-p',
'--prior-configs',
nargs='+',
type=argparse_utils.arg_is_path,
required=True,
help=('One or more config files to be used to generate prior '
'samples. If more than one config is specified, they '
'should be separated by spaces. '
'This option can also be used to specify the path to a '
'directory containing the prior samples and summary '
'statistic means and standard deviations generated by a '
'previous run using the `generate-samples-only` option. '
'These files should be found in the directory '
'`pymsbayes-output/prior-stats-summaries`. The'
'`pymsbayes-output/model-key.txt` also needs to be present.'
' If specifying this directory, it should be the only '
'argument (i.e., no other directories or config files can '
'be provided).'))
parser.add_argument(
'-r',
'--reps',
action='store',
type=argparse_utils.arg_is_nonnegative_int,
default=0,
help=('This option has two effects. First, it signifies that '
'the analysis will be simulation based (i.e., no real '
'data will be used). Second, it specifies how many '
'simulation replicates to perform (i.e., how many data '
'sets to simulate and analyze).'))
parser.add_argument(
'-n',
'--num-prior-samples',
action='store',
type=argparse_utils.arg_is_positive_int,
default=1000000,
help=('The number of prior samples to simulate for each prior '
'config specified with `-p`.'))
parser.add_argument(
'--prior-batch-size',
action='store',
type=argparse_utils.arg_is_positive_int,
default=10000,
help=('The number of prior samples to simulate for each batch.'))
parser.add_argument(
'--generate-samples-only',
action='store_true',
help=('Only generate samples from models as requested. I.e., '
'No analyses are performed to approximate posteriors. '
'This option can be useful if you want the prior samples '
'for other purposes.'))
parser.add_argument(
'--num-posterior-samples',
action='store',
type=argparse_utils.arg_is_positive_int,
default=1000,
help=('The number of posterior samples desired for each '
'analysis. Default: 1000.'))
parser.add_argument('--num-standardizing-samples',
action='store',
type=argparse_utils.arg_is_positive_int,
default=10000,
help=('The number of prior samples desired to use for '
'standardizing statistics. Default: 10000.'))
parser.add_argument(
'--np',
action='store',
type=argparse_utils.arg_is_positive_int,
default=multiprocessing.cpu_count(),
help=('The maximum number of processes to run in parallel. The '
'default is the number of CPUs available on the machine.'))
parser.add_argument(
'--output-dir',
action='store',
type=argparse_utils.arg_is_dir,
help=('The directory in which all output files will be written. '
'The default is to use the directory of the first observed '
'config file.'))
parser.add_argument(
'--temp-dir',
action='store',
type=argparse_utils.arg_is_dir,
help=('A directory to temporarily stage files. The default is to '
'use the output directory.'))
parser.add_argument(
'--staging-dir',
action='store',
type=argparse_utils.arg_is_dir,
help=('A directory to temporarily stage prior files. This option '
'can be useful on clusters to speed up I/O while '
'generating prior samples. You can designate a local temp '
'directory on a compute node to avoid constant writing to '
'a shared drive. The default is to use the `temp-dir`.'))
parser.add_argument(
'-s',
'--stat-prefixes',
nargs='*',
type=str,
help=('Prefixes of summary statistics to use in the analyses. '
'The prefixes should be separated by spaces. '
'Default: `-s pi wattTheta pi.net tajD.denom`.'))
parser.add_argument(
'-b',
'--bandwidth',
action='store',
type=float,
help=('Smoothing parameter for the posterior kernal density '
'estimation. This option is used for the `glm` '
'regression method. The default is 2 / '
'`num-posterior-samples`.'))
parser.add_argument(
'-q',
'--num-posterior-quantiles',
action='store',
type=argparse_utils.arg_is_positive_int,
default=1000,
help=('The number of equally spaced quantiles at which to '
'evaluate the GLM-estimated posterior density. '
'Default: 1000.'))
parser.add_argument(
'--reporting-frequency',
action='store',
type=argparse_utils.arg_is_nonnegative_int,
default=0,
help=('Suggested frequency (in number of prior samples) for '
'running regression and reporting current results. '
'Default: 0 (only report final results). '
'If a value is given, it may be adjusted so that the '
'reporting frequency is a multiple of the multi-processed '
'batch size.'))
parser.add_argument('--sort-index',
action='store',
type=argparse_utils.arg_is_nonnegative_int,
default=0,
choices=range(12),
help=argparse_utils.get_sort_index_help_message())
parser.add_argument(
'--no-global-estimate',
action='store_true',
help=('If multiple prior models are specified, by default a '
'global estimate is performed averaging over all models. '
'This option prevents the global estimation (i.e., only '
'inferences for each model are made).'))
parser.add_argument('--compress',
action='store_true',
help='Compress large results files.')
parser.add_argument('--keep-temps',
action='store_true',
help='Keep all temporary files.')
parser.add_argument('--seed',
action='store',
type=int,
help='Random number seed to use for the analysis.')
parser.add_argument(
'--output-prefix',
action='store',
type=str,
default='',
help=('Prefix to use at beginning of output files. The default '
'is no prefix.'))
parser.add_argument(
'--data-key-path',
action='store',
type=argparse_utils.arg_is_file,
help=('The path to a `data-key.txt` file generated by a previous '
'run. This file should be found in the directory '
'`pymsbayes-output/data-key.txt`. This option '
'will override the `-o`/`--observed-configs` option, and '
'is intended to be used in combination with the '
'`--start-from` option to restart an analysis.'))
parser.add_argument(
'--start-from-simulation-index',
action='store',
type=argparse_utils.arg_is_nonnegative_int,
default=0,
help=('The simulation index at which to begin analyses. Must be '
'used in combination with either the number of simulation '
'replicates (`-r`/`--reps`) or the `--data-key-path` '
'option, and must be a positive '
'integer that is less than the number of simulation '
'replicates. This option can be useful if an analysis '
'needs to be restarted.'))
parser.add_argument(
'--start-from-observed-index',
action='store',
type=argparse_utils.arg_is_nonnegative_int,
default=0,
help=('The observed config index at which to begin analyses. '
'Can be used in combination with the `--data-key-path` '
'option to restart long-running, multi-observed-config '
'analyses'))
parser.add_argument('--dry-run',
action='store_true',
help='Do not run analyses; only process settings')
parser.add_argument('--version',
action='version',
version='%(prog)s ' + _program_info['version'],
help='Report version and exit.')
parser.add_argument('--quiet',
action='store_true',
help='Run without verbose messaging.')
parser.add_argument('--debug',
action='store_true',
help='Run in debugging mode.')
if argv == sys.argv:
args = parser.parse_args()
else:
args = parser.parse_args(argv)
##########################################################################
## handle args
from pymsbayes.utils.messaging import (LoggingControl, InfoLogger)
LoggingControl.set_logging_level("INFO")
if args.quiet:
LoggingControl.set_logging_level("WARNING")
if args.debug:
LoggingControl.set_logging_level("DEBUG")
log = LoggingControl.get_logger(__name__)
from pymsbayes.workers import (MsBayesWorker, merge_prior_files,
ObsSumStatsWorker)
from pymsbayes.teams import ABCTeam
from pymsbayes.utils.functions import (is_file, is_dir, long_division,
mk_new_dir)
from pymsbayes.utils.parsing import (get_patterns_from_prefixes,
DEFAULT_STAT_PATTERNS,
DIV_MODEL_PATTERNS, MODEL_PATTERNS,
PSI_PATTERNS, MEAN_TAU_PATTERNS,
OMEGA_PATTERNS, CV_PATTERNS,
line_count)
from pymsbayes.utils import sumresults, errors
from pymsbayes.manager import Manager
from pymsbayes.utils.tempfs import TempFileSystem
from pymsbayes.config import MsBayesConfig
from pymsbayes.utils import (GLOBAL_RNG, set_memory_trace,
MSBAYES_SORT_INDEX, ToolPathManager)
MSBAYES_SORT_INDEX.set_index(args.sort_index)
if len(args.observed_configs) != len(set(args.observed_configs)):
raise ValueError('All paths to observed config files must be unique')
if args.num_standardizing_samples > args.num_prior_samples:
args.num_standardizing_samples = args.num_prior_samples
# get full paths to tools
msbayes_path = ToolPathManager.get_tool_full_path('msbayes.pl')
dpp_msbayes_path = ToolPathManager.get_tool_full_path('dpp-msbayes.pl')
eureject_path = ToolPathManager.get_tool_full_path('eureject')
abctb_path = ToolPathManager.get_tool_full_path('ABCestimator')
# vet prior-configs option
using_previous_priors = False
previous_prior_dir = None
if (len(args.prior_configs) == 1) and (is_dir(args.prior_configs[0])):
previous_prior_dir = args.prior_configs.pop(0)
previous_priors = glob.glob(
os.path.join(previous_prior_dir, '*-prior-sample.txt'))
previous_sums = glob.glob(
os.path.join(previous_prior_dir, '*-means-and-std-devs.txt'))
if (not previous_priors) or (not previous_sums):
raise ValueError(
'directory {0!r} specified with `prior-configs` '
'option does not contain necessary prior and summary '
'files'.format(args.prior_configs[0]))
using_previous_priors = True
else:
for path in args.prior_configs:
if not is_file(path):
raise ValueError(
'prior config {0!r} is not a file'.format(path))
if len(args.prior_configs) != len(set(args.prior_configs)):
raise ValueError('All paths to prior config files must be unique')
if not args.output_dir:
args.output_dir = os.path.dirname(args.observed_configs[0])
base_dir = mk_new_dir(os.path.join(args.output_dir, 'pymsbayes-results'))
if not args.temp_dir:
args.temp_dir = base_dir
info_path = os.path.join(base_dir, args.output_prefix + \
'pymsbayes-info.txt')
info = InfoLogger(info_path)
info.write('[pymsbayes]'.format(base_dir))
info.write('\tversion = {version}'.format(**_program_info))
info.write('\toutput_directory = {0}'.format(base_dir))
temp_fs = TempFileSystem(parent=args.temp_dir, prefix='temp-files-')
base_temp_dir = temp_fs.base_dir
info.write('\ttemp_directory = {0}'.format(base_temp_dir))
info.write('\tsort_index = {0}'.format(MSBAYES_SORT_INDEX.current_value()))
info.write('\tsimulation_reps = {0}'.format(args.reps))
stat_patterns = DEFAULT_STAT_PATTERNS
if args.stat_prefixes:
for i in range(len(args.stat_prefixes)):
if not args.stat_prefixes[i].endswith('.'):
args.stat_prefixes[i] += '.'
stat_patterns = get_patterns_from_prefixes(args.stat_prefixes,
ignore_case=True)
if not args.bandwidth:
args.bandwidth = 2 / float(args.num_posterior_samples)
if not args.seed:
args.seed = random.randint(1, 999999999)
GLOBAL_RNG.seed(args.seed)
if args.data_key_path:
observed_map = sumresults.parse_data_key_file(args.data_key_path)
observed_paths = [observed_map[k] for k in sorted(observed_map.keys())]
else:
observed_dir = mk_new_dir(
os.path.join(base_dir, 'observed-summary-stats'))
observed_paths = [os.path.join(observed_dir, args.output_prefix + \
'observed-{0}.txt'.format(i+1)) for i in range(len(
args.observed_configs))]
info.write('\tseed = {0}'.format(args.seed))
info.write('\tnum_processors = {0}'.format(args.np))
info.write('\tnum_prior_samples = {0}'.format(args.num_prior_samples))
info.write('\tnum_standardizing_samples = {0}'.format(
args.num_standardizing_samples))
info.write('\tbandwidth = {0}'.format(args.bandwidth))
info.write('\tposterior_quantiles = {0}'.format(
args.num_posterior_quantiles))
info.write('\tposterior_sample_size = {0}'.format(
args.num_posterior_samples))
info.write('\tstat_patterns = {0}'.format(', '.join(
[p.pattern for p in stat_patterns])))
# vet observed configs
ref_config_path = args.observed_configs[0]
ref_config = MsBayesConfig(ref_config_path)
all_config_paths = []
num_taxon_pairs = ref_config.npairs
assert num_taxon_pairs > 0
for config in args.observed_configs:
all_config_paths.append(config)
if not ref_config.equal_sample_table(config):
if not args.keep_temps:
temp_fs.purge()
raise errors.SampleTableError(
'sample tables in config {0!r} and {1!r} differ; '
'all sample tables must be the same.'.format(
ref_config_path, config))
info.write('\tnum_taxon_pairs = {0}'.format(num_taxon_pairs))
info.write('\tdry_run = {0}'.format(args.dry_run))
info.write('\t[[tool_paths]]')
info.write('\t\tdpp_msbayes = {0}'.format(dpp_msbayes_path))
info.write('\t\tmsbayes = {0}'.format(msbayes_path))
info.write('\t\teureject = {0}'.format(eureject_path))
info.write('\t\tabcestimator = {0}'.format(abctb_path))
info.write('\t[[observed_configs]]')
for i, cfg in enumerate(args.observed_configs):
info.write('\t\t{0} = {1}'.format(
i + 1, os.path.relpath(cfg, os.path.dirname(info_path))))
abc_team = ABCTeam(
temp_fs=temp_fs,
observed_stats_files=observed_paths,
num_taxon_pairs=num_taxon_pairs,
config_paths=args.prior_configs,
previous_prior_dir=previous_prior_dir,
num_prior_samples=args.num_prior_samples,
num_processors=args.np,
num_standardizing_samples=args.num_standardizing_samples,
num_posterior_samples=args.num_posterior_samples,
num_posterior_density_quantiles=args.num_posterior_quantiles,
batch_size=args.prior_batch_size,
output_dir=base_dir,
output_prefix=args.output_prefix,
prior_temp_dir=args.staging_dir,
rng=GLOBAL_RNG,
report_parameters=True,
stat_patterns=stat_patterns,
eureject_exe_path=eureject_path,
abctoolbox_exe_path=abctb_path,
msbayes_exe_path=None,
abctoolbox_bandwidth=args.bandwidth,
omega_threshold=0.01,
cv_threshold=0.01,
compress=args.compress,
reporting_frequency=args.reporting_frequency,
keep_temps=args.keep_temps,
global_estimate_only=False,
global_estimate=not args.no_global_estimate,
generate_prior_samples_only=args.generate_samples_only,
start_from_simulation_index=args.start_from_simulation_index,
start_from_observed_index=args.start_from_observed_index)
models_to_configs = {}
configs_to_models = {}
for k, v in abc_team.models.iteritems():
models_to_configs[k] = v
configs_to_models[v] = k
cfg = MsBayesConfig(v)
all_config_paths.append(v)
# vet prior configs
if not ref_config.equal_sample_table(cfg):
if not args.keep_temps:
temp_fs.purge()
raise errors.SampleTableError(
'sample tables in config {0!r} and {1!r} differ; '
'all sample tables must be the same.'.format(
ref_config_path, v))
info.write('\t[[observed_paths]]')
for i in sorted(abc_team.observed_stats_paths.iterkeys()):
info.write('\t\t{0} = {1}'.format(
i,
os.path.relpath(abc_team.observed_stats_paths[i],
os.path.dirname(info_path))))
info.write('\t[[prior_configs]]')
for i in sorted(abc_team.models.iterkeys()):
info.write('\t\t{0} = {1}'.format(
i, os.path.relpath(abc_team.models[i],
os.path.dirname(info_path))))
##########################################################################
## begin analysis --- get observed summary stats
set_memory_trace() # start logging memory profile
start_time = datetime.datetime.now()
if args.data_key_path:
log.info('Using provided summary statitics...')
elif not args.dry_run:
obs_temp_dir = base_temp_dir
if args.staging_dir:
obs_temp_dir = args.staging_dir
observed_temp_fs = TempFileSystem(parent=obs_temp_dir,
prefix='observed-temps-')
if args.reps < 1:
log.info('Calculating summary statistics from sequence data...')
obs_workers = []
for i, cfg in enumerate(args.observed_configs):
ss_worker = ObsSumStatsWorker(temp_fs=observed_temp_fs,
config_path=cfg,
output_path=observed_paths[i],
schema='abctoolbox',
stat_patterns=stat_patterns)
obs_workers.append(ss_worker)
obs_workers = Manager.run_workers(workers=obs_workers,
num_processors=args.np)
# re-vet all configs to see if some were changed by obsSumStats.pl
new_ref_config = ref_config
ref_modified = False
# new ref because if all configs were updated all is good
if not ref_config.equal_sample_table(ref_config_path):
ref_modified = True
new_ref_config = MsBayesConfig(ref_config_path)
log.warning("""
The alignment lengths in config
{0!r}
have been corrected for sites with *any* ambiguous bases and/or gaps by
obsSumStats.pl.
""".format(ref_config_path))
for config in all_config_paths:
if not new_ref_config.equal_sample_table(config):
corrected_config = config
if ref_modified:
corrected_config = ref_config_path
if not args.keep_temps:
observed_temp_fs.purge()
temp_fs.purge()
raise errors.SampleTableError("""
The sample tables in configs
{0!r}
and
{1!r}
differ because obsSumStats.pl modified alignment lengths in config
{2!r}
to correct for sites in the alignments with *any* ambiguous bases and/or gaps.
Please make sure the sample tables in all configs will be the same after
correcting alignment lengths for sites that contain *any* ambiguous bases
and/or gaps. You can do this by copying and pasting the sample table in
{2!r}
that has been corrected by obsSumStats.pl into the other configs that were not
corrected.
""".format(ref_config_path, config, corrected_config))
else:
log.info('Simulating summary statistics from observed configs...')
num_observed_workers = min([args.reps, args.np])
if args.reps <= args.np:
observed_batch_size = 1
remainder = 0
else:
observed_batch_size, remainder = long_division(
args.reps, args.np)
msbayes_workers = []
for idx, cfg in enumerate(args.observed_configs):
observed_model_idx = configs_to_models.get(cfg, None)
schema = 'abctoolbox'
for i in range(num_observed_workers):
worker = MsBayesWorker(temp_fs=observed_temp_fs,
sample_size=observed_batch_size,
config_path=cfg,
model_index=observed_model_idx,
report_parameters=True,
schema=schema,
include_header=True,
stat_patterns=stat_patterns,
write_stats_file=False,
staging_dir=None,
tag=idx)
msbayes_workers.append(worker)
if remainder > 0:
worker = MsBayesWorker(temp_fs=observed_temp_fs,
sample_size=remainder,
config_path=cfg,
model_index=observed_model_idx,
report_parameters=True,
schema=schema,
include_header=True,
stat_patterns=stat_patterns,
write_stats_file=False,
staging_dir=None,
tag=idx)
msbayes_workers.append(worker)
# run parallel msbayes processes
msbayes_workers = Manager.run_workers(workers=msbayes_workers,
num_processors=args.np)
workers = dict(
zip(range(len(args.observed_configs)),
[[] for i in range(len(args.observed_configs))]))
for w in msbayes_workers:
workers[w.tag].append(w)
# merge simulated observed data into one file
for i in range(len(args.observed_configs)):
merge_prior_files([w.prior_path for w in workers[i]],
observed_paths[i])
lc = line_count(observed_paths[i], ignore_headers=True)
if lc != args.reps:
if not args.keep_temps:
temp_fs.purge()
raise Exception(
'The number of observed simulations ({0}) '
'generated for observed config {1!r} and output to '
'file {2!r} does not match the number of reps '
'({3})'.format(lc, args.observed_configs[i],
observed_paths[i], args.reps))
if not args.keep_temps:
log.debug('purging observed temps...')
observed_temp_fs.purge()
##########################################################################
## Begin ABC analyses
if not args.dry_run:
abc_team.run()
stop_time = datetime.datetime.now()
log.info('Done!')
info.write('\t[[run_stats]]', log.info)
info.write('\t\tstart_time = {0}'.format(str(start_time)), log.info)
info.write('\t\tstop_time = {0}'.format(str(stop_time)), log.info)
info.write('\t\ttotal_duration = {0}'.format(str(stop_time - start_time)),
log.info)
if not args.keep_temps:
log.debug('purging temps...')
temp_fs.purge()
def main_cli():
description = '{name} {version}'.format(**_program_info)
parser = argparse.ArgumentParser(
description=description,
formatter_class=argparse_utils.SmartHelpFormatter)
parser.add_argument(
'-c',
'--config',
type=argparse_utils.arg_is_config,
required=True,
help=('msBayes config file to be used to generate saturation '
'plot.'))
parser.add_argument(
'-n',
'--num-prior-samples',
action='store',
type=int,
default=1000,
help=('The number of prior samples to simulate for the '
'saturation plot.'))
parser.add_argument(
'--np',
action='store',
type=int,
default=multiprocessing.cpu_count(),
help=('The maximum number of processes to run in parallel. The '
'default is the number of CPUs available on the machine.'))
parser.add_argument(
'-o',
'--output-dir',
action='store',
type=argparse_utils.arg_is_dir,
help=('The directory in which all output files will be written. '
'The default is to use the directory of the first observed '
'config file.'))
parser.add_argument(
'--temp-dir',
action='store',
type=argparse_utils.arg_is_dir,
help=('A directory to temporarily stage files. The default is to '
'use the output directory.'))
parser.add_argument(
'-s',
'--stat-prefixes',
nargs='*',
type=str,
default=['pi', 'pi.net', 'wattTheta', 'tajD.denom'],
help=('Prefixes of summary statistics to use in the analyses. '
'The prefixes should be separated by spaces. '
'Default: `-s pi pi.net wattTheta tajD.denom`.'))
parser.add_argument('--sort-index',
action='store',
type=int,
default=0,
choices=range(12),
help=argparse_utils.get_sort_index_help_message())
parser.add_argument('--compress',
action='store_true',
help='Compress plot data file.')
parser.add_argument('--keep-temps',
action='store_true',
help='Keep all temporary files.')
parser.add_argument('--seed',
action='store',
type=int,
help='Random number seed to use for the analysis.')
parser.add_argument('--version',
action='version',
version='%(prog)s ' + _program_info['version'],
help='Report version and exit.')
parser.add_argument('--quiet',
action='store_true',
help='Run without verbose messaging.')
parser.add_argument('--debug',
action='store_true',
help='Run in debugging mode.')
args = parser.parse_args()
##########################################################################
## handle args
from pymsbayes.utils.messaging import (LoggingControl, InfoLogger)
LoggingControl.set_logging_level("INFO")
if args.quiet:
LoggingControl.set_logging_level("WARNING")
if args.debug:
LoggingControl.set_logging_level("DEBUG")
log = LoggingControl.get_logger(__name__)
from pymsbayes.workers import MsBayesWorker
from pymsbayes.utils.parsing import (get_patterns_from_prefixes,
DEFAULT_STAT_PATTERNS,
get_dict_from_spreadsheets,
dict_line_iter)
from pymsbayes.manager import Manager
from pymsbayes.utils.tempfs import TempFileSystem
from pymsbayes.utils import probability, stats
from pymsbayes.utils.functions import long_division
from pymsbayes.config import MsBayesConfig
from pymsbayes.utils import GLOBAL_RNG, MSBAYES_SORT_INDEX, ToolPathManager
from pymsbayes.fileio import process_file_arg
from pymsbayes import plotting
MSBAYES_SORT_INDEX.set_index(args.sort_index)
# get full paths to tools
msbayes_path = ToolPathManager.get_tool_full_path('msbayes.pl')
dpp_msbayes_path = ToolPathManager.get_tool_full_path('dpp-msbayes.pl')
if not args.output_dir:
args.output_dir = os.path.dirname(args.config)
info = InfoLogger(os.path.join(args.output_dir, 'pymsbayes-info.txt'))
sample_path = os.path.join(args.output_dir, 'prior-sample.txt')
if args.compress:
sample_path += '.gz'
if not args.temp_dir:
args.temp_dir = args.output_dir
temp_fs = TempFileSystem(parent=args.temp_dir, prefix='temp-files-')
args.stat_prefixes = [s.rstrip('.') for s in args.stat_prefixes]
stat_patterns = get_patterns_from_prefixes(
[s + '.' for s in args.stat_prefixes], ignore_case=True)
if not args.seed:
args.seed = random.randint(1, 999999999)
GLOBAL_RNG.seed(args.seed)
compress_level = None
if args.compress:
compress_level = 9
cfg = MsBayesConfig(args.config)
num_taxon_pairs = cfg.npairs
info.write('[pymsbayes]', log.info)
info.write('\tprogram_name = {name}'.format(**_program_info), log.info)
info.write('\tversion = {version}'.format(**_program_info), log.info)
info.write('\tinvocation = {0!r}'.format(' '.join(sys.argv)), log.info)
info.write('\toutput_directory = {0!r}'.format(args.output_dir), log.info)
info.write('\ttemp_directory = {0!r}'.format(temp_fs.base_dir), log.info)
info.write('\tsort_index = {0}'.format(MSBAYES_SORT_INDEX.current_value()),
log.info)
info.write(
'\tstat_patterns = {0!r}'.format(', '.join(
[p.pattern for p in stat_patterns])), log.info)
info.write('\tseed = {0}'.format(args.seed), log.info)
info.write('\tnum_prior_samples = {0}'.format(args.num_prior_samples),
log.info)
info.write('\tsample_path = {0!r}'.format(sample_path), log.info)
info.write('\t[[tool_paths]]', log.info)
info.write('\t\tdpp_msbayes = {0}'.format(dpp_msbayes_path), log.info)
info.write('\t\tmsbayes = {0}'.format(msbayes_path), log.info)
info.write('\t[[config]]', log.debug)
info.write('{0}'.format(str(cfg)), log.debug)
##########################################################################
## begin analysis --- generate samples
start_time = datetime.datetime.now()
if args.np > args.num_prior_samples:
args.np = args.num_prior_samples
batch_size, remainder = long_division(args.num_prior_samples, args.np)
schema = 'abctoolbox'
workers = []
for i in range(args.np):
sample_size = batch_size
if i == (args.np - 1):
sample_size += remainder
w = MsBayesWorker(temp_fs=temp_fs,
sample_size=sample_size,
config_path=args.config,
report_parameters=True,
schema=schema,
include_header=True,
stat_patterns=stat_patterns,
write_stats_file=False)
workers.append(w)
log.info('Generating samples...')
workers = Manager.run_workers(workers=workers, num_processors=args.np)
log.info('Parsing samples...')
sample = get_dict_from_spreadsheets([w.prior_path for w in workers])
log.info('Writing prior samples...')
out, close = process_file_arg(sample_path,
'w',
compresslevel=compress_level)
for row in dict_line_iter(sample, sep='\t'):
out.write(row)
if close:
out.close()
log.info('Creating plots...')
if not plotting.MATPLOTLIB_AVAILABLE:
log.warning(
'`matplotlib` could not be imported, so the plot can not be\n'
'produced. The data to create the plot can be found in:\n\t'
'{0!r}'.format(sample_path))
sys.exit(1)
for stat_pattern in stat_patterns:
found = False
for stat, values in sample.iteritems():
if stat_pattern.match(stat):
values = [float(v) for v in values]
found = True
plot_path = os.path.join(args.output_dir,
'plot-{0}.pdf'.format(stat))
summary = stats.get_summary(values)
s = r'mean = {0:.4f} ({1:.4f}-{2:.4f})'.format(
summary['mean'], summary['qi_95'][0], summary['qi_95'][1])
hd = plotting.HistData(x=values,
normed=True,
bins=20,
histtype='bar',
align='mid',
orientation='vertical',
zorder=0)
hist = plotting.ScatterPlot(hist_data_list=[hd], right_text=s)
hist.left_text_size = 12.0
hist.right_text_size = 12.0
xticks = [i for i in hist.ax.get_xticks()]
xtick_labels = [i for i in xticks]
yticks = [i for i in hist.ax.get_yticks()]
ytick_labels = [i for i in yticks]
if len(xtick_labels) >= 8:
for i in range(1, len(xtick_labels), 2):
xtick_labels[i] = ''
if len(ytick_labels) >= 8:
for i in range(1, len(ytick_labels), 2):
ytick_labels[i] = ''
xticks_obj = plotting.Ticks(ticks=xticks,
labels=xtick_labels,
horizontalalignment='center')
yticks_obj = plotting.Ticks(ticks=yticks, labels=ytick_labels)
hist.xticks_obj = xticks_obj
hist.yticks_obj = yticks_obj
plot_grid = plotting.PlotGrid(subplots=[hist],
num_columns=1,
label_schema=None,
title=stat,
title_size=14.0,
title_top=False,
y_title='Density',
y_title_position=0.001,
y_title_size=14.0,
height=4.0,
width=6.0,
auto_height=False)
plot_grid.auto_adjust_margins = False
plot_grid.margin_left = 0.04
plot_grid.margin_bottom = 0.04
plot_grid.margin_right = 1.0
plot_grid.margin_top = 0.97
plot_grid.reset_figure()
plot_grid.savefig(plot_path)
if not found:
raise Exception('stat pattern {0!r} not found in simulated stats:'
'\n\t{1}'.format(stat_pattern,
', '.join(sample.keys())))
stop_time = datetime.datetime.now()
log.info('Done!')
info.write('\t[[run_stats]]', log.info)
info.write('\t\tstart_time = {0}'.format(str(start_time)), log.info)
info.write('\t\tstop_time = {0}'.format(str(stop_time)), log.info)
info.write('\t\ttotal_duration = {0}'.format(str(stop_time - start_time)),
log.info)
if not args.keep_temps:
log.debug('purging temps...')
temp_fs.purge()
