def list_ranks_db(rank_file=None, debug=False):
'''list all taxonomic ranks present in the NCBI taxonomy database
Parameters
----------
rank_file : str, default None
Specify the location of the rank definition and order file; by default, taxonkit uses
`~/taxonkit/ranks.txt`
debug : bool, default False
Print debugging output, e.g., system calls to `taxonkit`
Returns
-------
list
A list of taxonomic ranks.
>>> import pytaxonkit
>>> ranks = pytaxonkit.list_ranks_db()
>>> ranks[:5]
['superkingdom', 'kingdom', 'subkingdom', 'superphylum', 'phylum']
'''
arglist = ['taxonkit', 'filter', '--list-ranks']
if rank_file: # pragma: no cover
arglist.extend(['--rank-file', rank_file])
if debug:
log(*arglist)
proc = Popen(arglist, stdin=PIPE, stdout=PIPE, stderr=PIPE, universal_newlines=True)
out, err = proc.communicate(input='')
data = pandas.read_csv(StringIO(out), header=None, names=['Rank'], index_col=False)
return pylist(data.Rank)
def test_list_take(xs: PyList[int], x: int):
ys: FrozenList[int]
try:
ys = frozenlist.of_seq(xs).take(x)
assert pylist(ys) == xs[:x]
except ValueError:
assert x > len(xs)
def test_list_slice(xs: PyList[int], x: int, y: int):
expected = xs[x:y]
ys: FrozenList[int]
ys = frozenlist.of_seq(xs)[x:y]
assert pylist(ys) == expected
def filter(ids, threads=None, equal_to=None, higher_than=None, lower_than=None,
discard_norank=False, save_predictable=False, discard_root=False, root_taxid=None,
blacklist=None, rank_file=None, debug=False):
'''filter taxids by taxonomic rank (or a range of ranks)
Executes the `taxonkit filter` command to include or exclude taxa at the specified ranks.
Parameters
----------
ids : list or iterable
A list of taxids (ints or strings are ok)
threads : int
Override the default taxonkit threads setting
equal_to : str or list, default None
Keep only taxa at the specified rank(s); can be a string or a list of strings
higher_than : str, default None
Keep only taxa ranked higher than the specified rank
lower_than : str, default None
Keep only taxa ranked lower than the specified rank
discard_norank : bool, default False
Discard generic ranks without an explicit ranking order ("no rank" and "clade")
save_predictable : bool, default False
When `discard_norank=True`, do not discard some special ranks without order where the rank
of the closest higher node is still lower than rank cutoff
discard_root : bool, default False
Discard root taxon
root_taxid : int or str
override taxid of the root taxon
blacklist : list of strs
A list of ranks to exclude
rank_file : str, default None
Specify the location of the rank definition and order file; by default, taxonkit uses
`~/taxonkit/ranks.txt`
debug : bool, default False
Print debugging output, e.g., system calls to `taxonkit`
Returns
-------
list
A list of taxids passing the specified filters.
>>> import pytaxonkit
>>> taxids = [131567, 2, 1783257, 74201, 203494, 48461, 1647988, 239934, 239935, 349741]
>>> pytaxonkit.filter(taxids, blacklist=['family', 'species'])
[131567, 2, 1783257, 74201, 203494, 48461, 239934, 349741]
>>> pytaxonkit.filter(taxids, lower_than='genus')
[131567, 1783257, 239935, 349741]
'''
if higher_than is not None and lower_than is not None:
raise ValueError('cannot specify "higher_than" and "lower_than" simultaneously')
idlist = '\n'.join(map(str, ids))
arglist = ['taxonkit', 'filter']
if threads:
arglist.extend(('--threads', validate_threads(threads)))
if equal_to:
if isinstance(equal_to, (pylist, tuple)):
equal_to = ','.join(equal_to)
arglist.extend(['--equal-to', equal_to])
if higher_than:
arglist.extend(['--higher-than', higher_than])
if lower_than:
arglist.extend(['--lower-than', lower_than])
if discard_norank:
arglist.append('--discard-noranks')
if save_predictable:
arglist.append('--save-predictable-norank')
if discard_root: # pragma: no cover
arglist.append('--discard-root')
if blacklist:
arglist.extend(['--black-list', ','.join(blacklist)])
if root_taxid: # pragma: no cover
arglist.extend(['--root-taxid', str(root_taxid)])
if rank_file: # pragma: no cover
arglist.extend(['--rank-file', rank_file])
if debug:
log(*arglist)
proc = Popen(arglist, stdin=PIPE, stdout=PIPE, stderr=PIPE, universal_newlines=True)
out, err = proc.communicate(input=idlist)
data = pandas.read_csv(StringIO(out), header=None, names=['TaxID'], index_col=False)
return pylist(data.TaxID)
def test_list_skip_last(xs: PyList[int], x: int):
expected = xs[:-x]
ys: FrozenList[int]
ys = frozenlist.of_seq(xs).skip_last(x)
assert pylist(ys) == expected
def test_list_take_last(xs: PyList[int], x: int):
expected = xs[-x:]
ys: FrozenList[int]
ys = frozenlist.of_seq(xs).take_last(x)
assert pylist(ys) == expected