def new_nexus_without_sites(nexus_obj, sites_to_remove):
"""
Returns a new NexusReader instance with the sites in
`sites_to_remove` removed.
:param nexus_obj: A `NexusReader` instance
:type nexus_obj: NexusReader
:param sites_to_remove: A list of site numbers
:type sites_to_remove: List
:return: A NexusWriter instance
:raises AssertionError: if nexus_obj is not a nexus
:raises NexusFormatException: if nexus_obj does not have a `data` block
"""
# make new nexus
nexout = NexusWriter()
nexout.add_comment(
"Removed %d sites: %s" %
(len(sites_to_remove), ",".join(["%s" % s for s in sites_to_remove])))
new_sitepos = 0
for sitepos in range(nexus_obj.data.nchar):
if sitepos in sites_to_remove:
continue # skip!
for taxon, data in nexus_obj.data:
nexout.add(taxon, new_sitepos, data[sitepos])
new_sitepos += 1
return nexout
def new_nexus_without_sites(nexus_obj, sites_to_remove):
"""
Returns a new NexusReader instance with the sites in
`sites_to_remove` removed.
:param nexus_obj: A `NexusReader` instance
:type nexus_obj: NexusReader
:param sites_to_remove: A list of site numbers
:type sites_to_remove: List
:return: A NexusWriter instance
:raises AssertionError: if nexus_obj is not a nexus
:raises NexusFormatException: if nexus_obj does not have a `data` block
"""
check_for_valid_NexusReader(nexus_obj, required_blocks=['data'])
# make new nexus
nexout = NexusWriter()
nexout.add_comment(
"Removed %d sites: %s" %
(len(sites_to_remove), ",".join(["%s" % s for s in sites_to_remove]))
)
new_sitepos = 0
for sitepos in range(nexus_obj.data.nchar):
if sitepos in sites_to_remove:
continue # skip!
for taxon, data in nexus_obj.data:
nexout.add(taxon, new_sitepos, data[sitepos])
new_sitepos += 1
return nexout
def shufflenexus(nexus_obj, resample=False):
"""
Shuffles the characters between each taxon to create a new nexus
:param nexus_obj: A `NexusReader` instance
:type nexus_obj: NexusReader
:param resample: The number of characters to resample. If set to False,
then the number of characters will equal the number of characters
in the original data file.
:type resample: Integer
:return: A shuffled NexusReader instance
:raises AssertionError: if nexus_obj is not a nexus
:raises ValueError: if resample is not False or a positive Integer
:raises NexusFormatException: if nexus_obj does not have a `data` block
"""
check_for_valid_NexusReader(nexus_obj, required_blocks=['data'])
if resample is False:
resample = nexus_obj.data.nchar
try:
resample = int(resample)
except ValueError:
raise ValueError('resample must be a positive integer or False!')
if resample < 1:
raise ValueError('resample must be a positive integer or False!')
newnexus = NexusWriter()
newnexus.add_comment(
"Randomised Nexus generated from %s" % nexus_obj.filename
)
for i in range(resample):
# pick existing character
character = randrange(0, nexus_obj.data.nchar)
chars = nexus_obj.data.characters[character]
site_values = [chars[taxon] for taxon in nexus_obj.data.taxa]
shuffle(site_values)
for taxon in nexus_obj.data.taxa:
newnexus.add(taxon, i, site_values.pop(0))
return newnexus
def shufflenexus(nexus_obj, resample=False):
"""
Shuffles the characters between each taxon to create a new nexus
:param nexus_obj: A `NexusReader` instance
:type nexus_obj: NexusReader
:param resample: The number of characters to resample. If set to False,
then the number of characters will equal the number of characters
in the original data file.
:type resample: Integer
:return: A shuffled NexusReader instance
:raises AssertionError: if nexus_obj is not a nexus
:raises ValueError: if resample is not False or a positive Integer
:raises NexusFormatException: if nexus_obj does not have a `data` block
"""
check_for_valid_NexusReader(nexus_obj, required_blocks=['data'])
if resample is False:
resample = nexus_obj.data.nchar
try:
resample = int(resample)
except ValueError:
raise ValueError('resample must be a positive integer or False!')
if resample < 1:
raise ValueError('resample must be a positive integer or False!')
newnexus = NexusWriter()
newnexus.add_comment("Randomised Nexus generated from %s" %
nexus_obj.filename)
for i in range(resample):
# pick existing character
character = randrange(0, nexus_obj.data.nchar)
chars = nexus_obj.data.characters[character]
site_values = [chars[taxon] for taxon in nexus_obj.data.taxa]
shuffle(site_values)
for taxon in nexus_obj.data.taxa:
newnexus.add(taxon, i, site_values.pop(0))
return newnexus
def combine_nexuses(nexuslist):
"""
Combines a list of NexusReader instances into a single nexus
:param nexuslist: A list of NexusReader instances
:type nexuslist: List
:return: A NexusWriter instance
:raises TypeError: if nexuslist is not a list of NexusReader instances
:raises IOError: if unable to read an file in nexuslist
:raises NexusFormatException: if a nexus file does not have a `data` block
"""
out = NexusWriter()
charpos = 0
for nex_id, nex in enumerate(nexuslist, 1):
check_for_valid_NexusReader(nex, required_blocks=['data'])
if hasattr(nex, 'short_filename'):
nexus_label = os.path.splitext(nex.short_filename)[0]
elif hasattr(nex, 'label'):
nexus_label = nex.label
else:
nexus_label = str(nex_id)
out.add_comment(
"%d - %d: %s" %
(charpos, charpos + nex.data.nchar - 1, nexus_label)
)
for site_idx, site in enumerate(sorted(nex.data.characters), 0):
data = nex.data.characters.get(site)
charpos += 1
# work out character label
charlabel = nex.data.charlabels.get(site_idx, site_idx + 1)
label = '%s.%s' % (nexus_label, charlabel)
for taxon, value in data.items():
out.add(taxon, label, value)
return out
def combine_nexuses(nexuslist):
"""
Combines a list of NexusReader instances into a single nexus
:param nexuslist: A list of NexusReader instances
:type nexuslist: List
:return: A NexusWriter instance
:raises TypeError: if nexuslist is not a list of NexusReader instances
:raises IOError: if unable to read an file in nexuslist
:raises NexusFormatException: if a nexus file does not have a `data` block
"""
out = NexusWriter()
charpos = 0
for nex_id, nex in enumerate(nexuslist, 1):
check_for_valid_NexusReader(nex, required_blocks=['data'])
if hasattr(nex, 'short_filename'):
nexus_label = os.path.splitext(nex.short_filename)[0]
else:
nexus_label = str(nex_id)
out.add_comment("%d - %d: %s" %
(charpos, charpos + nex.data.nchar - 1, nexus_label))
for site_idx, site in enumerate(sorted(nex.data.characters), 0):
data = nex.data.characters.get(site)
charpos += 1
# work out character label
charlabel = nex.data.charlabels.get(site_idx, site_idx + 1)
label = '%s.%s' % (nexus_label, charlabel)
for taxon, value in data.items():
out.add(taxon, label, value)
return out
