def test_take(self):
a = np.rec.array(variant_table_data, dtype=variant_table_dtype)
vt = VariantChunkedTable(a)
# take variants not in original order
# not supported for carrays
indices = [2, 0]
with assert_raises(NotImplementedError):
vt.take(indices)
def test_slice_types(self):
ra = np.rec.array(variant_table_data, dtype=variant_table_dtype)
vt = VariantChunkedTable(ra)
# row slice
s = vt[1:]
self.assertNotIsInstance(s, VariantChunkedTable)
self.assertIsInstance(s, VariantTable)
# row index
s = vt[0]
self.assertNotIsInstance(s, VariantChunkedTable)
self.assertNotIsInstance(s, VariantTable)
self.assertIsInstance(s, (np.record, np.void, tuple))
# col access
s = vt['CHROM']
self.assertNotIsInstance(s, VariantChunkedTable)
self.assertNotIsInstance(s, VariantTable)
self.assertIsInstance(s, chunked.ChunkedArrayWrapper)
# bad access
with assert_raises(IndexError):
# noinspection PyStatementEffect
vt[:, 0]
def test_constructor(self):
# missing data arg
with self.assertRaises(TypeError):
# noinspection PyArgumentList
VariantChunkedTable()
# recarray
ra = np.rec.array(variant_table_data, dtype=variant_table_dtype)
vt = VariantChunkedTable(ra)
eq(5, len(vt))
aeq(ra, vt)
# dict
d = {n: ra[n] for n in variant_table_names}
vt = VariantChunkedTable(d, names=variant_table_names)
eq(5, len(vt))
aeq(ra, vt)
def test_hdf5_to_zarr(self):
# https://github.com/cggh/scikit-allel/issues/353
chrom = [b'chr1', b'chr1', b'chr2', b'chr2', b'chr3']
pos = [2, 7, 3, 9, 6]
dp = [35, 12, 78, 22, 99]
qd = [4.5, 6.7, 1.2, 4.4, 2.8]
ac = [(1, 2), (3, 4), (5, 6), (7, 8), (9, 10)]
with h5py.File('callset.h5', mode='w') as h5f:
h5g = h5f.create_group('/3L/variants')
h5g.create_dataset('CHROM', data=chrom, chunks=True)
h5g.create_dataset('POS', data=pos, chunks=True)
h5g.create_dataset('DP', data=dp, chunks=True)
h5g.create_dataset('QD', data=qd, chunks=True)
h5g.create_dataset('AC', data=ac, chunks=True)
callset = h5py.File('callset.h5', mode='r')
vt = VariantChunkedTable(callset['/3L/variants'],
names=['CHROM', 'POS', 'AC', 'QD', 'DP'])
vs = vt.eval('DP > 15')[:]
v = vt.compress(vs, axis=0)
assert isinstance(v, VariantChunkedTable)
assert isinstance(v.values, ZarrTable)
def test_zarr_group(self):
z = zarr.group()
z.create_dataset('chrom', data=['1', '2', '3'])
z.create_dataset('pos', data=[2, 4, 6])
vt = VariantChunkedTable(z)
assert isinstance(vt.values, zarr.Group)
def setup_instance(self, data, **kwargs):
data = chunked.storage_registry['default'].table(data)
return VariantChunkedTable(data, **kwargs)