def test_dataframes(loop):
dfs = [pd.DataFrame({'x': np.random.random(100),
'y': np.random.random(100)},
index=list(range(i, i + 100)))
for i in range(0, 100*10, 100)]
with cluster() as (c, [a, b]):
with Executor(('127.0.0.1', c['port']), loop=loop) as e:
remote_dfs = e.map(lambda x: x, dfs)
rdf = futures_to_dask_dataframe(remote_dfs, divisions=True)
name = 'foo'
ldf = dd.DataFrame({(name, i): df for i, df in enumerate(dfs)},
name, dfs[0].columns,
list(range(0, 1000, 100)) + [999])
assert rdf.divisions == ldf.divisions
tm.assert_frame_equal(rdf.compute(get=e.get),
ldf.compute(get=dask.get))
exprs = [lambda df: df.x.mean(),
lambda df: df.y.std(),
lambda df: df.assign(z=df.x + df.y).drop_duplicates(),
lambda df: df.index,
lambda df: df.x,
lambda df: df.x.cumsum(),
lambda df: df.loc[50:75]]
for f in exprs:
local = f(ldf).compute(get=dask.get)
remote = f(rdf).compute(get=e.get)
assert_equal(local, remote)
def test_futures_to_dask_dataframe(loop):
with cluster() as (c, [a, b]):
with Executor(('127.0.0.1', c['port']), loop=loop) as e:
remote_dfs = e.map(lambda x: x, dfs)
ddf = futures_to_dask_dataframe(remote_dfs, divisions=True)
assert isinstance(ddf, dd.DataFrame)
assert ddf.x.sum().compute(get=e.get) == sum([df.x.sum() for df in dfs])
def test_futures_to_dask_dataframe(loop):
with cluster() as (c, [a, b]):
with Executor(('127.0.0.1', c['port']), loop=loop) as e:
remote_dfs = e.map(lambda x: x, dfs)
ddf = futures_to_dask_dataframe(remote_dfs, divisions=True)
assert isinstance(ddf, dd.DataFrame)
assert ddf.x.sum().compute(get=e.get) == sum(
[df.x.sum() for df in dfs])
def test_futures_to_dask_dataframe():
dfs = [pd.DataFrame({'x': [1, 2, 3]}, index=[0, 10, 20]),
pd.DataFrame({'x': [4, 5, 6]}, index=[30, 40, 50]),
pd.DataFrame({'x': [7, 8, 9]}, index=[60, 70, 80])]
with cluster() as (c, [a, b]):
with Executor(('127.0.0.1', c['port'])) as e:
remote_dfs = e.map(lambda x: x, dfs)
ddf = futures_to_dask_dataframe(e, remote_dfs, divisions=True)
assert isinstance(ddf, dd.DataFrame)
assert ddf.x.sum().compute(get=e.get) == sum([df.x.sum() for df in dfs])
def test_futures_to_dask_dataframe(loop):
with cluster() as (s, [a, b]):
with Client(s['address'], loop=loop) as c:
remote_dfs = c.map(lambda x: x, dfs)
ddf = futures_to_dask_dataframe(remote_dfs, divisions=True)
assert isinstance(ddf, dd.DataFrame)
assert ddf.x.sum().compute(get=c.get) == sum([df.x.sum() for df in dfs])
ddf2 = futures_to_collection(remote_dfs, divisions=True)
assert type(ddf) == type(ddf2)
assert ddf.dask == ddf2.dask
def test_futures_to_dask_dataframe(loop):
with cluster() as (c, [a, b]):
with Client(('127.0.0.1', c['port']), loop=loop) as c:
remote_dfs = c.map(lambda x: x, dfs)
ddf = futures_to_dask_dataframe(remote_dfs, divisions=True)
assert isinstance(ddf, dd.DataFrame)
assert ddf.x.sum().compute(get=c.get) == sum([df.x.sum() for df in dfs])
ddf2 = futures_to_collection(remote_dfs, divisions=True)
assert type(ddf) == type(ddf2)
assert ddf.dask == ddf2.dask
