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 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_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 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 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 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
