def test_from_dask_array_compat_numpy_array_1d():
x = da.ones(10, chunks=3)
d1 = from_dask_array(x) # dask
assert isinstance(d1, dd.Series)
assert (d1.compute().values == x.compute()).all()
assert d1.name is None
d2 = from_array(x.compute()) # numpy
assert isinstance(d1, dd.Series)
assert (d2.compute().values == x.compute()).all()
assert d2.name is None
d1 = from_dask_array(x, columns='name') # dask
assert isinstance(d1, dd.Series)
assert (d1.compute().values == x.compute()).all()
assert d1.name == 'name'
d2 = from_array(x.compute(), columns='name') # numpy
assert isinstance(d1, dd.Series)
assert (d2.compute().values == x.compute()).all()
assert d2.name == 'name'
# passing list via columns results in DataFrame
d1 = from_dask_array(x, columns=['name']) # dask
assert isinstance(d1, dd.DataFrame)
assert (d1.compute().values == x.compute()).all()
tm.assert_index_equal(d1.columns, pd.Index(['name']))
d2 = from_array(x.compute(), columns=['name']) # numpy
assert isinstance(d1, dd.DataFrame)
assert (d2.compute().values == x.compute()).all()
tm.assert_index_equal(d2.columns, pd.Index(['name']))
def test_from_dask_array_compat_numpy_array_1d():
x = da.ones(10, chunks=3)
d1 = from_dask_array(x) # dask
assert isinstance(d1, dd.Series)
assert (d1.compute().values == x.compute()).all()
assert d1.name is None
d2 = from_array(x.compute()) # numpy
assert isinstance(d1, dd.Series)
assert (d2.compute().values == x.compute()).all()
assert d2.name is None
d1 = from_dask_array(x, columns='name') # dask
assert isinstance(d1, dd.Series)
assert (d1.compute().values == x.compute()).all()
assert d1.name == 'name'
d2 = from_array(x.compute(), columns='name') # numpy
assert isinstance(d1, dd.Series)
assert (d2.compute().values == x.compute()).all()
assert d2.name == 'name'
# passing list via columns results in DataFrame
d1 = from_dask_array(x, columns=['name']) # dask
assert isinstance(d1, dd.DataFrame)
assert (d1.compute().values == x.compute()).all()
tm.assert_index_equal(d1.columns, pd.Index(['name']))
d2 = from_array(x.compute(), columns=['name']) # numpy
assert isinstance(d1, dd.DataFrame)
assert (d2.compute().values == x.compute()).all()
tm.assert_index_equal(d2.columns, pd.Index(['name']))
def test_Series_from_dask_array():
x = da.ones(10, chunks=4)
ser = from_dask_array(x, 'a')
assert ser.name == 'a'
assert list(ser.divisions) == [0, 4, 8, 10]
assert (ser.compute(get=get_sync).values == x.compute(get=get_sync)).all()
ser = from_dask_array(x)
assert ser.name is None
def test_Series_from_dask_array():
x = da.ones(10, chunks=4)
ser = from_dask_array(x, 'a')
assert ser.name == 'a'
assert list(ser.divisions) == [0, 4, 8, 9]
assert (ser.compute(get=get_sync).values == x.compute(get=get_sync)).all()
ser = from_dask_array(x)
assert ser.name is None
# dd.from_array should re-route to from_dask_array
ser2 = dd.from_array(x)
assert eq(ser, ser2)
def test_Series_from_dask_array():
x = da.ones(10, chunks=4)
ser = from_dask_array(x, "a")
assert ser.name == "a"
assert list(ser.divisions) == [0, 4, 8, 9]
assert (ser.compute(get=get_sync).values == x.compute(get=get_sync)).all()
ser = from_dask_array(x)
assert ser.name is None
# dd.from_array should re-route to from_dask_array
ser2 = dd.from_array(x)
assert eq(ser, ser2)
def test_from_dask_array_raises():
x = da.ones((3, 3, 3), chunks=2)
pytest.raises(ValueError, lambda: from_dask_array(x))
x = da.ones((10, 3), chunks=(3, 3))
pytest.raises(ValueError, lambda: from_dask_array(x)) # no columns
# Not enough columns
pytest.raises(ValueError, lambda: from_dask_array(x, columns=['a']))
try:
from_dask_array(x, columns=['hello'])
except Exception as e:
assert 'hello' in str(e)
assert '3' in str(e)
def test_from_dask_array_raises():
x = da.ones((3, 3, 3), chunks=2)
pytest.raises(ValueError, lambda: from_dask_array(x))
x = da.ones((10, 3), chunks=(3, 3))
pytest.raises(ValueError, lambda: from_dask_array(x)) # no columns
# Not enough columns
pytest.raises(ValueError, lambda: from_dask_array(x, columns=["a"]))
try:
from_dask_array(x, columns=["hello"])
except Exception as e:
assert "hello" in str(e)
assert "3" in str(e)
def test_DataFrame_from_dask_array():
x = da.ones((10, 3), chunks=(4, 2))
df = from_dask_array(x, ['a', 'b', 'c'])
assert list(df.columns) == ['a', 'b', 'c']
assert list(df.divisions) == [0, 4, 8, 10]
assert (df.compute(get=get_sync).values == x.compute(get=get_sync)).all()
def test_DataFrame_from_dask_array():
x = da.ones((10, 3), chunks=(4, 2))
df = from_dask_array(x, ['a', 'b', 'c'])
assert list(df.columns) == ['a', 'b', 'c']
assert list(df.divisions) == [0, 4, 8, 9]
assert (df.compute(get=get_sync).values == x.compute(get=get_sync)).all()
# dd.from_array should re-route to from_dask_array
df2 = dd.from_array(x, columns=['a', 'b', 'c'])
assert df2.columns == df.columns
assert df2.divisions == df.divisions
def test_DataFrame_from_dask_array():
x = da.ones((10, 3), chunks=(4, 2))
df = from_dask_array(x, ["a", "b", "c"])
assert list(df.columns) == ["a", "b", "c"]
assert list(df.divisions) == [0, 4, 8, 9]
assert (df.compute(get=get_sync).values == x.compute(get=get_sync)).all()
# dd.from_array should re-route to from_dask_array
df2 = dd.from_array(x, columns=["a", "b", "c"])
assert df2.columns == df.columns
assert df2.divisions == df.divisions
def test_from_dask_array_compat_numpy_array():
x = da.ones((3, 3, 3), chunks=2)
with pytest.raises(ValueError):
from_dask_array(x) # dask
with pytest.raises(ValueError):
from_array(x.compute()) # numpy
x = da.ones((10, 3), chunks=(3, 3))
d1 = from_dask_array(x) # dask
assert isinstance(d1, dd.DataFrame)
assert (d1.compute().values == x.compute()).all()
tm.assert_index_equal(d1.columns, pd.Index([0, 1, 2]))
d2 = from_array(x.compute()) # numpy
assert isinstance(d1, dd.DataFrame)
assert (d2.compute().values == x.compute()).all()
tm.assert_index_equal(d2.columns, pd.Index([0, 1, 2]))
with pytest.raises(ValueError):
from_dask_array(x, columns=['a']) # dask
with pytest.raises(ValueError):
from_array(x.compute(), columns=['a']) # numpy
d1 = from_dask_array(x, columns=['a', 'b', 'c']) # dask
assert isinstance(d1, dd.DataFrame)
assert (d1.compute().values == x.compute()).all()
tm.assert_index_equal(d1.columns, pd.Index(['a', 'b', 'c']))
d2 = from_array(x.compute(), columns=['a', 'b', 'c']) # numpy
assert isinstance(d1, dd.DataFrame)
assert (d2.compute().values == x.compute()).all()
tm.assert_index_equal(d2.columns, pd.Index(['a', 'b', 'c']))
def test_DataFrame_from_dask_array():
x = da.ones((10, 3), chunks=(4, 2))
df = from_dask_array(x, ['a', 'b', 'c'])
assert isinstance(df, dd.DataFrame)
tm.assert_index_equal(df.columns, pd.Index(['a', 'b', 'c']))
assert list(df.divisions) == [0, 4, 8, 9]
assert (df.compute(get=get_sync).values == x.compute(get=get_sync)).all()
# dd.from_array should re-route to from_dask_array
df2 = dd.from_array(x, columns=['a', 'b', 'c'])
assert isinstance(df, dd.DataFrame)
tm.assert_index_equal(df2.columns, df.columns)
assert df2.divisions == df.divisions
def test_DataFrame_from_dask_array():
x = da.ones((10, 3), chunks=(4, 2))
df = from_dask_array(x, ['a', 'b', 'c'])
assert isinstance(df, dd.DataFrame)
tm.assert_index_equal(df.columns, pd.Index(['a', 'b', 'c']))
assert list(df.divisions) == [0, 4, 8, 9]
assert (df.compute(get=get_sync).values == x.compute(get=get_sync)).all()
# dd.from_array should re-route to from_dask_array
df2 = dd.from_array(x, columns=['a', 'b', 'c'])
assert isinstance(df, dd.DataFrame)
tm.assert_index_equal(df2.columns, df.columns)
assert df2.divisions == df.divisions
def test_from_dask_array_compat_numpy_array():
x = da.ones((3, 3, 3), chunks=2)
msg = r"from_array does not input more than 2D array, got array with shape \(3, 3, 3\)"
with tm.assertRaisesRegexp(ValueError, msg):
from_dask_array(x) # dask
with tm.assertRaisesRegexp(ValueError, msg):
from_array(x.compute()) # numpy
x = da.ones((10, 3), chunks=(3, 3))
d1 = from_dask_array(x) # dask
assert isinstance(d1, dd.DataFrame)
assert (d1.compute().values == x.compute()).all()
tm.assert_index_equal(d1.columns, pd.Index([0, 1, 2]))
d2 = from_array(x.compute()) # numpy
assert isinstance(d1, dd.DataFrame)
assert (d2.compute().values == x.compute()).all()
tm.assert_index_equal(d2.columns, pd.Index([0, 1, 2]))
msg = r"""Length mismatch: Expected axis has 3 elements, new values have 1 elements"""
with tm.assertRaisesRegexp(ValueError, msg):
from_dask_array(x, columns=['a']) # dask
with tm.assertRaisesRegexp(ValueError, msg):
from_array(x.compute(), columns=['a']) # numpy
d1 = from_dask_array(x, columns=['a', 'b', 'c']) # dask
assert isinstance(d1, dd.DataFrame)
assert (d1.compute().values == x.compute()).all()
tm.assert_index_equal(d1.columns, pd.Index(['a', 'b', 'c']))
d2 = from_array(x.compute(), columns=['a', 'b', 'c']) # numpy
assert isinstance(d1, dd.DataFrame)
assert (d2.compute().values == x.compute()).all()
tm.assert_index_equal(d2.columns, pd.Index(['a', 'b', 'c']))
def test_from_dask_array_compat_numpy_array():
x = da.ones((3, 3, 3), chunks=2)
msg = r"from_array does not input more than 2D array, got array with shape \(3, 3, 3\)"
with tm.assertRaisesRegexp(ValueError, msg):
from_dask_array(x) # dask
with tm.assertRaisesRegexp(ValueError, msg):
from_array(x.compute()) # numpy
x = da.ones((10, 3), chunks=(3, 3))
d1 = from_dask_array(x) # dask
assert isinstance(d1, dd.DataFrame)
assert (d1.compute().values == x.compute()).all()
tm.assert_index_equal(d1.columns, pd.Index([0, 1, 2]))
d2 = from_array(x.compute()) # numpy
assert isinstance(d1, dd.DataFrame)
assert (d2.compute().values == x.compute()).all()
tm.assert_index_equal(d2.columns, pd.Index([0, 1, 2]))
msg = r"""Length mismatch: Expected axis has 3 elements, new values have 1 elements"""
with tm.assertRaisesRegexp(ValueError, msg):
from_dask_array(x, columns=['a']) # dask
with tm.assertRaisesRegexp(ValueError, msg):
from_array(x.compute(), columns=['a']) # numpy
d1 = from_dask_array(x, columns=['a', 'b', 'c']) # dask
assert isinstance(d1, dd.DataFrame)
assert (d1.compute().values == x.compute()).all()
tm.assert_index_equal(d1.columns, pd.Index(['a', 'b', 'c']))
d2 = from_array(x.compute(), columns=['a', 'b', 'c']) # numpy
assert isinstance(d1, dd.DataFrame)
assert (d2.compute().values == x.compute()).all()
tm.assert_index_equal(d2.columns, pd.Index(['a', 'b', 'c']))
