How to use the kipoiseq.dataloaders.sequence.SeqIntervalDl function in kipoiseq

def test_seq_dataset_reshape(alphabet_axis, dummy_axis, example_kwargs):
    seq_len, alphabet_len = 3, 4

    kwargs = example_kwargs
    kwargs['auto_resize_len'] = seq_len
    kwargs['alphabet_axis'] = alphabet_axis
    kwargs['dummy_axis'] = dummy_axis

    dummy_axis_int = dummy_axis
    if dummy_axis is None:
        dummy_axis_int = -2

    if (alphabet_axis == dummy_axis_int) or (alphabet_axis == -1) or (dummy_axis_int == -1) or \
            (alphabet_axis >= 3) or (dummy_axis_int >= 3) or ((alphabet_axis >= 2) and (dummy_axis is None)):
        with pytest.raises(Exception):
            seq_dataset = SeqIntervalDl(**kwargs)
        return None

    seq_dataset = SeqIntervalDl(**kwargs)

    # test the single sample works
    reshaped = seq_dataset[0]['inputs']
    for i in range(len(reshaped.shape)):
        if i == dummy_axis:
            assert reshaped.shape[i] == 1
        elif i == alphabet_axis:
            assert reshaped.shape[i] == alphabet_len
        else:
            assert reshaped.shape[i] == seq_len

def test_min_props():
    # minimal set of properties that need to be specified on the object
    min_set_props = ["output_schema", "type", "defined_as", "info", "args", "dependencies", "postprocessing",
                     "source", "source_dir"]

    for Dl in [StringSeqIntervalDl, SeqIntervalDl]:
        props = dir(Dl)
        assert all([el in props for el in min_set_props])

kwargs = example_kwargs
    kwargs['auto_resize_len'] = seq_len
    kwargs['alphabet_axis'] = alphabet_axis
    kwargs['dummy_axis'] = dummy_axis

    dummy_axis_int = dummy_axis
    if dummy_axis is None:
        dummy_axis_int = -2

    if (alphabet_axis == dummy_axis_int) or (alphabet_axis == -1) or (dummy_axis_int == -1) or \
            (alphabet_axis >= 3) or (dummy_axis_int >= 3) or ((alphabet_axis >= 2) and (dummy_axis is None)):
        with pytest.raises(Exception):
            seq_dataset = SeqIntervalDl(**kwargs)
        return None

    seq_dataset = SeqIntervalDl(**kwargs)

    # test the single sample works
    reshaped = seq_dataset[0]['inputs']
    for i in range(len(reshaped.shape)):
        if i == dummy_axis:
            assert reshaped.shape[i] == 1
        elif i == alphabet_axis:
            assert reshaped.shape[i] == alphabet_len
        else:
            assert reshaped.shape[i] == seq_len

def test_seq_dataset(intervals_file, fasta_file):
    dl = SeqIntervalDl(intervals_file, fasta_file)
    ret_val = dl[0]

    assert np.all(ret_val['inputs'] == one_hot_dna("GT"))
    assert isinstance(ret_val["inputs"], np.ndarray)
    assert ret_val["inputs"].shape == (2, 4)

def test_var_eff_pred_varseq(tmpdir):
    model_name = "DeepSEA/variantEffects"
    if INSTALL_REQ:
        install_model_requirements(model_name, "kipoi", and_dataloaders=True)
    #
    model = kipoi.get_model(model_name, source="kipoi")
    # The preprocessor
    Dataloader = SeqIntervalDl
    #
    dataloader_arguments = {"intervals_file": "example_files/intervals.bed",
                            "fasta_file": "example_files/hg38_chr22.fa",
                            "required_seq_len": 1000, "alphabet_axis": 1, "dummy_axis": 2, "label_dtype": str}
    dataloader_arguments = {k: model.source_dir + "/" + v if isinstance(v, str) else v for k, v in
                            dataloader_arguments.items()}

    vcf_path = "tests/data/variants.vcf"
    out_vcf_fpath = str(tmpdir.mkdir("variants_generated", ).join("out.vcf"))
    #
    vcf_path = kipoi_veff.ensure_tabixed_vcf(vcf_path)
    model_info = kipoi_veff.ModelInfoExtractor(model, Dataloader)
    writer = kipoi_veff.VcfWriter(
        model, vcf_path, out_vcf_fpath, standardise_var_id=True)
    vcf_to_region = kipoi_veff.SnvCenteredRg(model_info)
    res = sp.predict_snvs(model, Dataloader, vcf_path, dataloader_args=dataloader_arguments,

def test_deepsea():
    model = kipoi.get_model("DeepSEA/variantEffects")
    mie = ModelInfoExtractor(model, SeqIntervalDl)