def load_tree(filename, format=None, underscore_unmunge=False):
"""Constructor for tree.
Parameters
----------
filename : str
a file path containing a newick or xml formatted tree.
format : str
either newick, xml or cogent3 json, default is newick
underscore_unmunge : bool
replace underscores with spaces in all names read, i.e. "sp_name"
becomes "sp name".
Notes
-----
Underscore unmunging is turned off by default, although it is part
of the Newick format.
Returns
-------
PhyloNode
"""
file_format, _ = get_format_suffixes(filename)
if file_format == "json":
return load_from_json(filename, (TreeNode, PhyloNode))
with open_(filename) as tfile:
treestring = tfile.read()
if format is None and filename.endswith(".xml"):
format = "xml"
return make_tree(treestring,
format=format,
underscore_unmunge=underscore_unmunge)
def load_aligned_seqs(
filename,
format=None,
array_align=True,
moltype=None,
label_to_name=None,
parser_kw=None,
info=None,
**kw,
):
"""
loads aligned sequences from file
Parameters
----------
filename : str
path to sequence file
format : str
sequence file format, if not specified tries to guess from the path suffix
moltype
the moltype, eg DNA, PROTEIN, 'dna', 'protein'
array_align : bool
if True, returns ArrayAlignment, otherwise an annotatable Alignment
label_to_name
function for converting original name into another name.
parser_kw : dict
optional arguments for the parser
Returns
-------
``ArrayAlignment`` or ``Alignment`` instance
"""
file_format, _ = get_format_suffixes(filename)
if file_format == "json":
return load_from_json(filename, (Alignment, ArrayAlignment))
format = format or file_format
if not format:
msg = "could not determined file format, set using the format argument"
raise ValueError(msg)
parser_kw = parser_kw or {}
for other_kw in ("constructor_kw", "kw"):
other_kw = kw.pop(other_kw, None) or {}
kw.update(other_kw)
data = list(FromFilenameParser(filename, format, **parser_kw))
return make_aligned_seqs(
data,
array_align=array_align,
label_to_name=label_to_name,
moltype=moltype,
source=filename,
info=info,
**kw,
)
def load_table(
filename,
sep=None,
reader=None,
digits=4,
space=4,
title="",
missing_data="",
max_width=1e100,
index_name=None,
legend="",
column_templates=None,
static_column_types=False,
limit=None,
format="simple",
skip_inconsistent=False,
**kwargs,
):
"""
Parameters
----------
filename
path to file containing a tabular data
sep
the delimiting character between columns
reader
a parser for reading filename. This approach assumes the first
row returned by the reader will be the header row.
static_column_types
if True, and reader is None, identifies columns
with a numeric/bool data types from the first non-header row.
This assumes all subsequent entries in that column are of the same type.
Default is False.
digits
floating point resolution
space
number of spaces between columns or a string
title
as implied
missing_data
character assigned if a row has no entry for a column
max_width
maximum column width for printing
index_name
column name with values to be used as row identifiers and keys
for slicing. All column values must be unique.
legend
table legend
column_templates
dict of column headings
or a function that will handle the formatting.
limit
exits after this many lines. Only applied for non pickled data
file types.
format
output format when using str(Table)
skip_inconsistent
skips rows that have different length to header row
"""
import pathlib
if not any(isinstance(filename, t) for t in (str, pathlib.PurePath)):
raise TypeError(
"filename must be string or Path, perhaps you want make_table()")
if "index" in kwargs:
deprecated("argument", "index", "index_name", "2021.11")
index_name = kwargs.pop("index", index_name)
sep = sep or kwargs.pop("delimiter", None)
file_format, compress_format = get_format_suffixes(filename)
if file_format == "json":
return load_from_json(filename, (_Table, ))
elif file_format in ("pickle", "pkl"):
f = open_(filename, mode="rb")
loaded_table = pickle.load(f)
f.close()
r = _Table()
r.__setstate__(loaded_table)
return r
if reader:
with open_(filename, newline=None) as f:
data = [row for row in reader(f)]
header = data[0]
data = {column[0]: column[1:] for column in zip(*data)}
else:
if file_format == "csv":
sep = sep or ","
elif file_format == "tsv":
sep = sep or "\t"
header, rows, loaded_title, legend = load_delimited(filename,
sep=sep,
limit=limit,
**kwargs)
if skip_inconsistent:
num_fields = len(header)
rows = [r for r in rows if len(r) == num_fields]
else:
lengths = set(map(len, [header] + rows))
if len(lengths) != 1:
msg = f"inconsistent number of fields {lengths}"
raise ValueError(msg)
title = title or loaded_title
data = {column[0]: column[1:] for column in zip(header, *rows)}
for key, value in data.items():
data[key] = cast_str_to_array(value, static_type=static_column_types)
return make_table(
header=header,
data=data,
digits=digits,
title=title,
column_templates=column_templates,
space=space,
missing_data=missing_data,
max_width=max_width,
index_name=index_name,
legend=legend,
format=format,
)
