def read_parameters(self, input_dir):
""" Read a directory full of tree files, matching them up to the
already loaded alignments """
pbar = setup_progressbar("Loading parameters", len(self.records))
pbar.start()
for i, rec in enumerate(self.records):
hook = os.path.join(input_dir, '{}.json*'.format(rec.name))
filename = glob.glob(hook)
try:
with fileIO.freader(filename[0]) as infile:
d = json.load(infile, parse_int=True)
rec.parameters.construct_from_dict(d)
except IOError, IndexError:
continue
finally:
def read_parameters(self, input_dir):
""" Read a directory full of tree files, matching them up to the
already loaded alignments """
pbar = setup_progressbar("Loading parameters", len(self.records))
pbar.start()
for i, rec in enumerate(self.records):
hook = os.path.join(input_dir, '{}.json*'.format(rec.name))
filename = glob.glob(hook)
try:
with fileIO.freader(filename[0]) as infile:
d = json.load(infile, parse_int=True)
rec.parameters.construct_from_dict(d)
except IOError, IndexError:
continue
finally:
def read_from_file(cls, infile, taxon_set=None):
with fileIO.freader(infile) as reader:
s = reader.read()
return cls.gen_from_text(s, taxon_set=taxon_set)
def read_from_file(cls, infile, taxon_set=None):
with fileIO.freader(infile) as reader:
s = reader.read()
return cls.gen_from_text(s, taxon_set=taxon_set)
def read_alignments(self, input_dir, file_format, header_grep=None, compression=None):
""" Get list of alignment files from an input directory *.fa, *.fas and
*.phy files only
Stores in self.files """
optioncheck(compression, [None, 'gz', 'bz2'])
if file_format == 'fasta':
extensions = ['fa', 'fas', 'fasta']
elif file_format == 'phylip':
extensions = ['phy']
else:
extensions = []
if compression:
extensions = ['.'.join([x, compression]) for x in extensions]
files = fileIO.glob_by_extensions(input_dir, extensions)
files.sort(key=SORT_KEY)
self._input_files = files
records = []
pbar = setup_progressbar("Loading files", len(files), simple_progress=True)
pbar.start()
for i, f in enumerate(files):
if compression is not None:
with fileIO.TempFile() as tmpfile:
with fileIO.freader(f, compression) as reader, fileIO.fwriter(tmpfile) as writer:
for line in reader:
writer.write(line)
try:
record = Alignment(tmpfile, file_format, True)
except RuntimeError:
record = Alignment(tmpfile, file_format, False)
else:
try:
record = Alignment(f, file_format, True)
except RuntimeError:
record = Alignment(f, file_format, False)
if header_grep:
try:
datatype = 'dna' if record.is_dna() else 'protein'
record = Alignment([(header_grep(x), y) for (x, y) in record.get_sequences()], datatype)
except TypeError:
raise TypeError("Couldn't apply header_grep to header\n"
"alignment number={}, name={}\n"
"header_grep={}".format(i, fileIO.strip_extensions(f), header_grep))
except RuntimeError:
print('RuntimeError occurred processing alignment number={}, name={}'
.format(i, fileIO.strip_extensions(f)))
raise
record.name = (fileIO.strip_extensions(f))
records.append(record)
pbar.update(i)
pbar.finish()
return records
def read_alignments(self,
input_dir,
file_format,
header_grep=None,
compression=None):
""" Get list of alignment files from an input directory *.fa, *.fas and
*.phy files only
Stores in self.files """
optioncheck(compression, [None, 'gz', 'bz2'])
if file_format == 'fasta':
extensions = ['fa', 'fas', 'fasta']
elif file_format == 'phylip':
extensions = ['phy']
else:
extensions = []
if compression:
extensions = ['.'.join([x, compression]) for x in extensions]
files = fileIO.glob_by_extensions(input_dir, extensions)
files.sort(key=SORT_KEY)
self._input_files = files
records = []
pbar = setup_progressbar("Loading files",
len(files),
simple_progress=True)
pbar.start()
for i, f in enumerate(files):
if compression is not None:
with fileIO.TempFile() as tmpfile:
with fileIO.freader(f,
compression) as reader, fileIO.fwriter(
tmpfile) as writer:
for line in reader:
writer.write(line)
try:
record = Alignment(tmpfile, file_format, True)
except RuntimeError:
record = Alignment(tmpfile, file_format, False)
else:
try:
record = Alignment(f, file_format, True)
except RuntimeError:
record = Alignment(f, file_format, False)
if header_grep:
try:
datatype = 'dna' if record.is_dna() else 'protein'
record = Alignment([(header_grep(x), y)
for (x, y) in record.get_sequences()],
datatype)
except TypeError:
raise TypeError("Couldn't apply header_grep to header\n"
"alignment number={}, name={}\n"
"header_grep={}".format(
i, fileIO.strip_extensions(f),
header_grep))
except RuntimeError:
print(
'RuntimeError occurred processing alignment number={}, name={}'
.format(i, fileIO.strip_extensions(f)))
raise
record.name = (fileIO.strip_extensions(f))
records.append(record)
pbar.update(i)
pbar.finish()
return records
