def test_enforce_dtypes():
blocks = [[b'aa,bb\n1,1.0\n2.2.0', b'10,20\n30,40'],
[b'aa,bb\n1,1.0\n2.2.0', b'10,20\n30,40']]
head = pd.read_csv(BytesIO(blocks[0][0]), header=0)
dfs = read_csv_from_bytes(blocks, b'aa,bb\n', head, {}, collection=False)
dfs = dask.compute(*dfs, get=get_sync)
assert all(df.dtypes.to_dict() == head.dtypes.to_dict() for df in dfs)
def test_blocked():
blocks = []
for k in sorted(files):
b = files[k]
lines = b.split(b'\n')
blocks.append([b'\n'.join(bs) for bs in partition_all(2, lines)])
df = read_csv_from_bytes(blocks, header, expected.head(), {})
eq(df.compute().reset_index(drop=True),
expected.reset_index(drop=True),
check_dtype=False)
expected2 = expected[['name', 'id']]
df = read_csv_from_bytes(blocks, header, expected2.head(),
{'usecols': ['name', 'id']})
eq(df.compute().reset_index(drop=True),
expected2.reset_index(drop=True),
check_dtype=False)
def test_kwargs():
blocks = [files[k] for k in sorted(files)]
blocks = [[b] for b in blocks]
kwargs = {'usecols': ['name', 'id']}
head = bytes_read_csv(files['2014-01-01.csv'], b'', kwargs)
df = read_csv_from_bytes(blocks, header, head, kwargs, collection=True)
assert list(df.columns) == ['name', 'id']
result = df.compute()
assert (result.columns == df.columns).all()
def test_enforce_columns():
blocks = [[b'aa,bb\n1,1.0\n2.2.0', b'10,20\n30,40'],
[b'AA,bb\n1,1.0\n2.2.0', b'10,20\n30,40']]
head = pd.read_csv(BytesIO(blocks[0][0]), header=0)
with pytest.raises(ValueError):
dfs = read_csv_from_bytes(blocks,
b'aa,bb\n',
head, {},
collection=False,
enforce=True)
dask.compute(*dfs, get=get_sync)
def test_read_csv_simple():
blocks = [[files[k]] for k in sorted(files)]
kwargs = {}
head = bytes_read_csv(files['2014-01-01.csv'], b'', {})
df = read_csv_from_bytes(blocks, header, head, kwargs, collection=True)
assert isinstance(df, dd.DataFrame)
assert list(df.columns) == ['name', 'amount', 'id']
values = read_csv_from_bytes(blocks,
header,
head,
kwargs,
collection=False)
assert isinstance(values, list)
assert len(values) == 3
assert all(hasattr(item, 'dask') for item in values)
result = df.amount.sum().compute(get=get_sync)
assert result == (100 + 200 + 300 + 400 + 500 + 600)