How to use pyranges - 10 common examples

def hyp14():

    c = """chr1      0    1      +"""

    return PyRanges(pd.read_table(StringIO(c), sep="\s+", header=None, names="Chromosome Start End Strand".split()))

def hyp8():

    c = """chr1      0    1      +"""

    return PyRanges(pd.read_table(StringIO(c), sep="\s+", header=None, names="Chromosome Start End Strand".split()))

def expected_result_previous_bed_opposite_stranded(names):

    c = """chr1 8 9 h 0 + 6 7 f 0 - 2
chr1 5 7 h 0 - 1 2 f 0 + 4"""

    df = pd.read_table(StringIO(c), sep=" ", header=None, names="Chromosome  Start  End  Name Score Strand Start_b  End_b  Name_b Score_b Strand_b Distance".split())
    print(df)

    return PyRanges(df)

def test_init(gr, strand):

    c, s, e, strands = gr

    if strand:
        pr.PyRanges(chromosomes=c, starts=s, ends=e, strands=strands)
    else:
        pr.PyRanges(chromosomes=c, starts=s, ends=e)

gr2.df.to_csv(f2, sep="\t", header=False, index=False)

        cmd = join_command.format(bedtools_strand, f1, f2)
        print(cmd)
        result = subprocess.check_output(cmd, shell=True, executable="/bin/bash").decode()

        bedtools_df = pd.read_table(StringIO(result), header=None, squeeze=True, names="Chromosome Start End Name Score Strand Chromosome_b Start_b End_b Name_b Score_b Strand_b Overlap".split(), dtype={"Chromosome": "category", "Strand": "category"} )
        bedtools_df = bedtools_df.drop(["Overlap", "Chromosome_b"], 1)

    print("gr\n", gr)
    print("gr2\n", gr2)

    result = gr.join(gr2, strandedness=strandedness)

    print("result\n", result)
    print("bedtools\n", PyRanges(bedtools_df))

    if result.df.empty:
        assert bedtools_df.empty
    else:
        assert_df_equal(result.df, bedtools_df)

def test_read_gtf():

    gr = pr.read_gtf("tests/test_data/ensembl.gtf", full=True)
    assert len(gr.columns) == 28

    df = gr.df
    transcript = df.iloc[1]
    assert transcript['tag'] == 'basic'

    exon = df[df['exon_id'] == 'ENSE00003812156'].iloc[0]
    assert exon['tag'] == 'basic'

    gr = pr.read_gtf("tests/test_data/ensembl.gtf",
                     full=True, duplicate_attr=True)
    assert len(gr.columns) == 28

    df = gr.df
    transcript = df.iloc[1]
    assert transcript['tag'] == 'basic'

    exon = df[df['exon_id'] == 'ENSE00003812156'].iloc[0]
    assert exon['tag'] == 'CCDS,basic'
    # assert list(gr.df.columns[:4]) == "Chromosome Start End Strand".split()

def test_stranded():
    cpg = pr.data.cpg()
    exons = pr.data.exons()

    j = cpg.join(exons)

    assert j.stranded

    j.Strand = "."

    assert not j.stranded

    j.Strand = np.random.choice("+ -".split(), size=len(j))

    assert j.stranded

    for _, df in j:
        assert len(df.Strand.drop_duplicates()) == 1

@settings(
    max_examples=max_examples,
    deadline=deadline,
    suppress_health_check=HealthCheck.all())
@given(gr=df_data())  # pylint: disable=no-value-for-parameter
def test_init(gr, strand):

    c, s, e, strands = gr

    if strand:
        pr.PyRanges(chromosomes=c, starts=s, ends=e, strands=strands)
    else:
        pr.PyRanges(chromosomes=c, starts=s, ends=e)


chipseq = pr.data.chipseq()


@settings(
    max_examples=max_examples,
    deadline=deadline,
    suppress_health_check=HealthCheck.all())
@given(selector=selector())  # pylint: disable=no-value-for-parameter
def test_getitem(selector):

    # have these weird returns to avoid being flagged as unused code
    if len(selector) == 3:
        a, b, c = selector
        return chipseq[a, b, c]
    elif len(selector) == 2:
        a, b = selector
        return chipseq[a, b]

def test_stranded():
    cpg = pr.data.cpg()
    exons = pr.data.exons()

    j = cpg.join(exons)

    assert j.stranded

    j.Strand = "."

    assert not j.stranded

    j.Strand = np.random.choice("+ -".split(), size=len(j))

    assert j.stranded

    for _, df in j:
        assert len(df.Strand.drop_duplicates()) == 1

def expected_result_unstranded():

 c = """Chromosome Start End Name Score Strand Start_b End_b Name_b Score_b Strand_b Distance
0 chr1 3 6 h 0 + 6 7 f 0 - 1
1 chr1 5 7 h 0 - 6 7 f 0 - 0"""

 return PyRanges(pd.read_table(StringIO(c), sep=" "))