Python pybedtools.example_filename函数代码示例

def test_bed_methods():
    """
    Generator that yields tests, inserting different versions of `bed` as needed
    """
    for method, send_kwargs, expected in parse_yaml(config_fn):
        ignore = ['a', 'b','abam','i']
        skip_test = False
        for i in ignore:
            if i in send_kwargs:
                skip_test = True
        if skip_test:
            continue
        if 'bed' not in send_kwargs:
            continue

        if 'files' in send_kwargs:
            send_kwargs['files'] = [pybedtools.example_filename(i) for i in send_kwargs['files']]

        if 'bams' in send_kwargs:
            send_kwargs['bams'] = [pybedtools.example_filename(i) for i in send_kwargs['bams']]

        if 'fi' in send_kwargs:
            send_kwargs['fi'] = pybedtools.example_filename(send_kwargs['fi'])

        orig_bed = pybedtools.example_bedtool(send_kwargs['bed'])

        del send_kwargs['bed']

        done = []
        for kind_bed in ('filename', 'generator', 'stream', 'gzip'):
            bed = converter[kind_bed](orig_bed)
            kind = 'i=%(kind_bed)s' % locals()
            f = partial(run, method, bed, expected, **send_kwargs)
            f.description = '%(method)s, %(kind)s, %(send_kwargs)s' % locals()
            yield (f, )

def test_intron_exon_reads():
    gff = pybedtools.example_filename('gdc.gff')
    bam = pybedtools.example_filename('gdc.bam')
    cmds = [
        'intron_exon_reads.py',
        '--gff', gff, '--bam', bam, '--processes', '2']
    out =  sp.check_output(cmds, universal_newlines=True)
    assert out == dedent(
        """\
        exon_only	3
        intron_only	3
        intron_and_exon	1
        """)


    cmds = [
        'intron_exon_reads.py',
        '--gff', gff, '--bam', bam, '--processes', '2', '--stranded']
    out =  sp.check_output(cmds, universal_newlines=True)
    assert out == dedent(
        """\
        exon_only	0
        intron_only	0
        intron_and_exon	0
        """)

def main():
    ap = argparse.ArgumentParser(description=__doc__,
                          formatter_class=argparse.RawDescriptionHelpFormatter)
    ap.add_argument('--bed', help='BED file of e.g. peaks')
    ap.add_argument('--gff', help='GFF file of e.g. annotations')
    ap.add_argument('--out', default='out.png', help='Output PNG file')
    ap.add_argument('--stranded', action='store_true',
                    help='Use strand-specific intersections')
    ap.add_argument('--include', nargs='*', help='Featuretypes to include')
    ap.add_argument('--exclude', nargs='*', help='Featuretypes to exclude')
    ap.add_argument('--thresh', type=float, help='Threshold percentage below which output will be suppressed')
    ap.add_argument('--test', action='store_true',
                    help='Run test, overwriting all other args')
    args = ap.parse_args()

    if not args.test:
        if args.include and args.exclude:
            raise ValueError('Cannot specify both --include and --exclude')

        make_pie(bed=args.bed,
                 gff=args.gff,
                 out=args.out,
                 thresh=args.thresh,
                 stranded=args.stranded,
                 include=args.include,
                 exclude=args.exclude)
    else:
        make_pie(bed=pybedtools.example_filename('gdc.bed'),
                 gff=pybedtools.example_filename('gdc.gff'),
                 stranded=True,
                 out='out.png',
                 include=['CDS',
                          'intron',
                          'five_prime_UTR',
                          'three_prime_UTR'])

def test_isBAM():
    bam = pybedtools.example_filename('x.bam')
    notabam = pybedtools.example_filename('a.bed')
    open('tiny.txt', 'w').close()
    assert pybedtools.helpers.isBAM(bam)
    assert not pybedtools.helpers.isBAM(notabam)
    assert not pybedtools.helpers.isBAM('tiny.txt')
    os.unlink('tiny.txt')

def test_issue_156():
    # NOTE: this isn't appropriate for including in the test_iter cases, since
    # that tests filenames, gzipped files, and iterators. There's no support
    # for "list of iterators" as the `b` argument. Plus, here we're not
    # concerned with the ability to handle those different input types -- just
    # that lists of filenames works.
    a = pybedtools.example_bedtool('a.bed')
    b = [pybedtools.example_filename('b.bed'),
         pybedtools.example_filename('c.gff')]
    res = str(a.intersect(b))
    assert res == fix(
        """
        chr1    59      100     feature1        0       +
        chr1    155     200     feature2        0       +
        chr1    173     200     feature2        0       +
        chr1    173     200     feature2        0       +
        chr1    100     200     feature2        0       +
        chr1    155     200     feature3        0       -
        chr1    464     500     feature3        0       -
        chr1    485     500     feature3        0       -
        chr1    173     326     feature3        0       -
        chr1    438     500     feature3        0       -
        chr1    495     500     feature3        0       -
        chr1    485     500     feature3        0       -
        chr1    173     326     feature3        0       -
        chr1    438     500     feature3        0       -
        chr1    150     269     feature3        0       -
        chr1    900     901     feature4        0       +
        chr1    900     913     feature4        0       +
        chr1    900     913     feature4        0       +
        chr1    900     950     feature4        0       +
        """), res

    res = str(a.intersect(b, wb=True, names=['B', 'C']))
    assert res == fix(
        """
        chr1	59	100	feature1	0	+	C	chr1	ucb	gene	60	269	.	-	.	ID=thaliana_1_6160_6269;match=fgenesh1_pg.C_scaffold_1000119;rname=thaliana_1_6160_6269
        chr1	155	200	feature2	0	+	B	chr1	155	200	feature5	0	-
        chr1	173	200	feature2	0	+	C	chr1	ucb	CDS	174	326	.	+	.	Parent=AT1G01010.mRNA;rname=AT1G01010
        chr1	173	200	feature2	0	+	C	chr1	ucb	mRNA	174	326	.	+	.	ID=AT1G01010.mRNA;Parent=AT1G01010;rname=AT1G01010
        chr1	100	200	feature2	0	+	C	chr1	ucb	gene	60	269	.	-	.	ID=thaliana_1_6160_6269;match=fgenesh1_pg.C_scaffold_1000119;rname=thaliana_1_6160_6269
        chr1	155	200	feature3	0	-	B	chr1	155	200	feature5	0	-
        chr1	464	500	feature3	0	-	C	chr1	ucb	gene	465	805	.	+	.	ID=thaliana_1_465_805;match=scaffold_801404.1;rname=thaliana_1_465_805
        chr1	485	500	feature3	0	-	C	chr1	ucb	CDS	486	605	.	+	.	Parent=AT1G01010.mRNA;rname=AT1G01010
        chr1	173	326	feature3	0	-	C	chr1	ucb	CDS	174	326	.	+	.	Parent=AT1G01010.mRNA;rname=AT1G01010
        chr1	438	500	feature3	0	-	C	chr1	ucb	CDS	439	630	.	+	.	Parent=AT1G01010.mRNA;rname=AT1G01010
        chr1	495	500	feature3	0	-	C	chr1	ucb	mRNA	496	576	.	+	.	ID=AT1G01010.mRNA;Parent=AT1G01010;rname=AT1G01010
        chr1	485	500	feature3	0	-	C	chr1	ucb	mRNA	486	605	.	+	.	ID=AT1G01010.mRNA;Parent=AT1G01010;rname=AT1G01010
        chr1	173	326	feature3	0	-	C	chr1	ucb	mRNA	174	326	.	+	.	ID=AT1G01010.mRNA;Parent=AT1G01010;rname=AT1G01010
        chr1	438	500	feature3	0	-	C	chr1	ucb	mRNA	439	899	.	+	.	ID=AT1G01010.mRNA;Parent=AT1G01010;rname=AT1G01010
        chr1	150	269	feature3	0	-	C	chr1	ucb	gene	60	269	.	-	.	ID=thaliana_1_6160_6269;match=fgenesh1_pg.C_scaffold_1000119;rname=thaliana_1_6160_6269
        chr1	900	901	feature4	0	+	B	chr1	800	901	feature6	0	+
        chr1	900	913	feature4	0	+	C	chr1	ucb	mRNA	631	913	.	+	.	ID=AT1G01010.mRNA;Parent=AT1G01010;rname=AT1G01010
        chr1	900	913	feature4	0	+	C	chr1	ucb	CDS	760	913	.	+	.	Parent=AT1G01010.mRNA;rname=AT1G01010
        chr1	900	950	feature4	0	+	C	chr1	ucb	CDS	706	1095	.	+	.	Parent=AT1G01010.mRNA;rname=AT1G01010
        """), res

def test_gzipped_files_can_be_intersected():
    agz = _make_temporary_gzip(pybedtools.example_filename('a.bed'))
    bgz = _make_temporary_gzip(pybedtools.example_filename('b.bed'))

    agz = pybedtools.BedTool(agz)
    bgz = pybedtools.BedTool(bgz)

    a = pybedtools.example_bedtool('a.bed')
    b = pybedtools.example_bedtool('b.bed')
    assert a.intersect(b) == agz.intersect(bgz) == a.intersect(bgz) == agz.intersect(b)

def test_gzip():
    # make new gzipped files on the fly
    agz = pybedtools.BedTool._tmp()
    bgz = pybedtools.BedTool._tmp()
    os.system('gzip -c %s > %s' % (pybedtools.example_filename('a.bed'), agz))
    os.system('gzip -c %s > %s' % (pybedtools.example_filename('b.bed'), bgz))
    agz = pybedtools.BedTool(agz)
    bgz = pybedtools.BedTool(bgz)
    assert agz.file_type == bgz.file_type == 'bed'
    a = pybedtools.example_bedtool('a.bed')
    b = pybedtools.example_bedtool('b.bed')
    assert a.intersect(b) == agz.intersect(bgz) == a.intersect(bgz) == agz.intersect(b)

def test_links():
    # have to be careful about the path, since it is embedded in the HTML
    # output -- so make a copy of the example file, and delete when done.
    os.system('cp %s a.links.bed' % pybedtools.example_filename('a.bed'))
    a = pybedtools.BedTool('a.links.bed')
    a = a.links()
    exp = open(pybedtools.example_filename('a.links.html')).read()
    obs = open(a.links_html).read()
    print exp
    print obs
    assert exp == obs
    os.unlink('a.links.bed')

def test_issue_218():
    from pybedtools.helpers import set_bedtools_path, get_bedtools_path
    from pybedtools import BedTool

    orig_path = get_bedtools_path()

    # As pointed out in #222, example_bedtool behaves differently from BedTool.
    # example_bedtool is defined in pybedtools.bedtool but pybedtools.BedTool
    # is imported in pybedtools.__init__. So check various constructors here.
    for constructor in (
        lambda x: pybedtools.example_bedtool(x),
        lambda x: pybedtools.BedTool(pybedtools.example_filename(x)),
        lambda x: pybedtools.bedtool.BedTool(pybedtools.example_filename(x)),

        # NOTE: we likely need recursive reloading (like IPython.deepreload)
        # for this to work:
        #
        # lambda x: BedTool(pybedtools.example_filename(x)),
    ):

        x = constructor('x.bed')
        x.sort()
        assert "Original BEDTools help" in pybedtools.bedtool.BedTool.sort.__doc__
        assert "Original BEDTools help" in x.sort.__doc__

        set_bedtools_path('nonexistent')

        # Calling BEDTools with non-existent path, but the docstring should not
        # have been changed.
        with pytest.raises(OSError):
            x.sort()
        assert "Original BEDTools help" in x.sort.__doc__

        # The class's docstring should have been reset though.
        assert pybedtools.bedtool.BedTool.sort.__doc__ is None

        # Creating a new BedTool object now that bedtools is not on the path
        # should detect that, adding a method that raises
        # NotImplementedError...
        y = constructor('x.bed')
        with pytest.raises(NotImplementedError):
            y.sort()

        # ...and correspondingly no docstring
        assert y.sort.__doc__ is None
        assert pybedtools.bedtool.BedTool.sort.__doc__ is None

        # Reset the path, and ensure the resetting works
        set_bedtools_path()
        z = constructor('x.bed')
        z.sort()

def test_issue_178():
    # Compatibility between py2/py3: py27 does not have FileNotFoundError, so
    # set it to IOError (which does exist) for this function.
    try:
        FileNotFoundError
    except NameError:
        FileNotFoundError = IOError

    try:
        fn = pybedtools.example_filename('gdc.othersort.bam')
        pybedtools.contrib.bigwig.bam_to_bigwig(fn, genome='dm3', output='tmp.bw')
        x = pybedtools.contrib.bigwig.bigwig_to_bedgraph('tmp.bw')
        assert x == fix(
            '''
            chr2L   70      75      1
            chr2L   140     145     1
            chr2L   150     155     1
            chr2L   160     165     1
            chr2L   210     215     1
            chrX    10      15      1
            chrX    70      75      1
            chrX    140     145     1
            ''')
        os.unlink('tmp.bw')

    # If bedGraphToBigWig is not on the path, see
    # https://github.com/daler/pybedtools/issues/227
    except FileNotFoundError:
        pass

def test_gzipped_files_are_iterable_as_normal():
    agz = _make_temporary_gzip(pybedtools.example_filename('a.bed'))
    agz = pybedtools.BedTool(agz)
    a = pybedtools.example_bedtool('a.bed')
    for i in agz:
        print(i)
    assert_list_equal(list(a), list(agz))

def test_cat():
    a = pybedtools.example_bedtool('a.bed')
    b = pybedtools.example_bedtool('b.bed')
    b_fn = pybedtools.example_filename('b.bed')
    assert a.cat(b) == a.cat(b_fn)
    expected =  fix("""
    chr1 1   500
    chr1 800 950
    """)
    assert a.cat(b) == expected

    a = pybedtools.example_bedtool('a.bed')
    b = pybedtools.example_bedtool('b.bed')
    c = a.cat(b, postmerge=False)
    assert len(a) + len(b) == len(c), (len(a), len(b), len(c))

    print c
    assert c == fix("""
    chr1	1	100	feature1	0	+
    chr1	100	200	feature2	0	+
    chr1	150	500	feature3	0	-
    chr1	900	950	feature4	0	+
    chr1	155	200	feature5	0	-
    chr1	800	901	feature6	0	+
    """)

def test_getting_example_beds():
    assert 'a.bed' in pybedtools.list_example_files()

    a_fn = pybedtools.example_filename('a.bed')
    assert a_fn == os.path.join(testdir, 'data', 'a.bed')

    a = pybedtools.example_bedtool('a.bed')
    assert a.fn == os.path.join(testdir, 'data', 'a.bed')

    # complain appropriately if nonexistent paths are asked for
    e = FileNotFoundError if six.PY3 else ValueError
    with pytest.raises(e):
        pybedtools.example_filename('nonexistent')
    with pytest.raises(e):
        pybedtools.example_bedtool('nonexistent')
    with pytest.raises(e):
        pybedtools.set_tempdir('nonexistent')

def main():
    """
    Make a pie chart of features overlapping annotations (e.g., peaks in
    introns, exons, etc)
    """
    ap = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
    ap.add_argument("--bed", help="BED file of e.g. peaks")
    ap.add_argument("--gff", help="GFF file of e.g. annotations")
    ap.add_argument("--out", default="out.png", help="Output PNG file")
    ap.add_argument("--stranded", action="store_true", help="Use strand-specific intersections")
    ap.add_argument("--include", nargs="*", help="Featuretypes to include")
    ap.add_argument("--exclude", nargs="*", help="Featuretypes to exclude")
    ap.add_argument("--thresh", type=float, help="Threshold percentage below which output will be " "suppressed")
    ap.add_argument(
        "--test",
        action="store_true",
        help="Run test, overwriting all other args. Result will " 'be "out.png" in current directory.',
    )
    args = ap.parse_args()

    if not (args.bed and args.gff) and not args.test:
        ap.print_help()
        sys.exit(1)

    if not args.test:
        if args.include and args.exclude:
            raise ValueError("Cannot specify both --include and --exclude")

        make_pie(
            bed=args.bed,
            gff=args.gff,
            out=args.out,
            thresh=args.thresh,
            stranded=args.stranded,
            include=args.include,
            exclude=args.exclude,
        )
    else:
        make_pie(
            bed=pybedtools.example_filename("gdc.bed"),
            gff=pybedtools.example_filename("gdc.gff"),
            stranded=True,
            out="out.png",
            include=["exon", "CDS", "intron", "five_prime_UTR", "three_prime_UTR"],
        )

def _classifier():

    c = Classifier(
            bed=pybedtools.example_filename('gdc.bed'),
            annotations=pybedtools.example_filename('gdc.gff'))
    c.classify()

    bed = pybedtools.example_bedtool('gdc.bed')

    assert c.class_counts == {
            frozenset(['UTR', 'exon', 'mRNA', 'CDS', 'tRNA', 'gene']): 1,
            frozenset(['intron', 'gene', 'mRNA']): 3,
            frozenset([]): 1,
            frozenset(['gene', 'exon', 'mRNA', 'CDS']): 2,
            frozenset(['exon', 'mRNA', 'CDS', 'tRNA', 'intron', 'gene']): 1}

    assert c.feature_classes == {
            bed[0]: set(['.']),
            bed[1]: set(['gene', 'exon', 'mRNA', 'CDS']),
            bed[2]: set(['intron', 'gene', 'mRNA']),
            bed[3]: set(['intron', 'gene', 'mRNA']),
            bed[4]: set(['tRNA', 'UTR', 'exon', 'mRNA', 'CDS', 'gene']),
            bed[5]: set(['gene', 'exon', 'mRNA', 'CDS']),
            bed[6]: set(['intron', 'gene', 'mRNA']),
            bed[7]: set(['tRNA', 'intron', 'exon', 'mRNA', 'CDS', 'gene']),
            }

    print('use these indexes for debugging')
    for i, f in enumerate(bed):
        print(i, f)

    for k, v in list(c.class_features.items()):
        print(k)
        for i in v:
            print('\t' + str(i))

    assert c.class_features == {
            frozenset([]): [bed[0]],
            frozenset(['intron', 'gene', 'mRNA']): [bed[6], bed[2], bed[3]],
            frozenset(['gene', 'exon', 'mRNA', 'CDS']): [bed[5], bed[1]],
            frozenset(['UTR', 'exon', 'mRNA', 'CDS', 'tRNA', 'gene']): [bed[4]],
            frozenset(['exon', 'mRNA', 'CDS', 'tRNA', 'intron', 'gene']): [bed[7]],
            }