本文整理汇总了Python中xarray.Dataset.to_dask_dataframe方法的典型用法代码示例。如果您正苦于以下问题：Python Dataset.to_dask_dataframe方法的具体用法？Python Dataset.to_dask_dataframe怎么用？Python Dataset.to_dask_dataframe使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类xarray.Dataset的用法示例。
在下文中一共展示了Dataset.to_dask_dataframe方法的7个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: test_to_dask_dataframe
# 需要导入模块: from xarray import Dataset [as 别名]
# 或者: from xarray.Dataset import to_dask_dataframe [as 别名]
def test_to_dask_dataframe(self):
# Test conversion of Datasets to dask DataFrames
x = da.from_array(np.random.randn(10), chunks=4)
y = np.arange(10, dtype='uint8')
t = list('abcdefghij')
ds = Dataset(OrderedDict([('a', ('t', x)),
('b', ('t', y)),
('t', ('t', t))]))
expected_pd = pd.DataFrame({'a': x,
'b': y},
index=pd.Index(t, name='t'))
# test if 1-D index is correctly set up
expected = dd.from_pandas(expected_pd, chunksize=4)
actual = ds.to_dask_dataframe(set_index=True)
# test if we have dask dataframes
assert isinstance(actual, dd.DataFrame)
# use the .equals from pandas to check dataframes are equivalent
assert_frame_equal(expected.compute(), actual.compute())
# test if no index is given
expected = dd.from_pandas(expected_pd.reset_index(drop=False),
chunksize=4)
actual = ds.to_dask_dataframe(set_index=False)
assert isinstance(actual, dd.DataFrame)
assert_frame_equal(expected.compute(), actual.compute())示例2: test_to_dask_dataframe_no_coordinate
# 需要导入模块: from xarray import Dataset [as 别名]
# 或者: from xarray.Dataset import to_dask_dataframe [as 别名]
def test_to_dask_dataframe_no_coordinate(self):
x = da.from_array(np.random.randn(10), chunks=4)
ds = Dataset({'x': ('dim_0', x)})
expected = ds.compute().to_dataframe().reset_index()
actual = ds.to_dask_dataframe()
assert isinstance(actual, dd.DataFrame)
assert_frame_equal(expected, actual.compute())
expected = ds.compute().to_dataframe()
actual = ds.to_dask_dataframe(set_index=True)
assert isinstance(actual, dd.DataFrame)
assert_frame_equal(expected, actual.compute())示例3: test_to_dask_dataframe_dim_order
# 需要导入模块: from xarray import Dataset [as 别名]
# 或者: from xarray.Dataset import to_dask_dataframe [as 别名]
def test_to_dask_dataframe_dim_order(self):
values = np.array([[1, 2], [3, 4]], dtype=np.int64)
ds = Dataset({'w': (('x', 'y'), values)}).chunk(1)
expected = ds['w'].to_series().reset_index()
actual = ds.to_dask_dataframe(dim_order=['x', 'y'])
assert isinstance(actual, dd.DataFrame)
assert_frame_equal(expected, actual.compute())
expected = ds['w'].T.to_series().reset_index()
actual = ds.to_dask_dataframe(dim_order=['y', 'x'])
assert isinstance(actual, dd.DataFrame)
assert_frame_equal(expected, actual.compute())
with raises_regex(ValueError, 'does not match the set of dimensions'):
ds.to_dask_dataframe(dim_order=['x'])示例4: test_to_dask_dataframe_2D_set_index
# 需要导入模块: from xarray import Dataset [as 别名]
# 或者: from xarray.Dataset import to_dask_dataframe [as 别名]
def test_to_dask_dataframe_2D_set_index(self):
# This will fail until dask implements MultiIndex support
w = da.from_array(np.random.randn(2, 3), chunks=(1, 2))
ds = Dataset({'w': (('x', 'y'), w)})
ds['x'] = ('x', np.array([0, 1], np.int64))
ds['y'] = ('y', list('abc'))
expected = ds.compute().to_dataframe()
actual = ds.to_dask_dataframe(set_index=True)
assert isinstance(actual, dd.DataFrame)
assert_frame_equal(expected, actual.compute())示例5: test_to_dask_dataframe_coordinates
# 需要导入模块: from xarray import Dataset [as 别名]
# 或者: from xarray.Dataset import to_dask_dataframe [as 别名]
def test_to_dask_dataframe_coordinates(self):
# Test if coordinate is also a dask array
x = da.from_array(np.random.randn(10), chunks=4)
t = da.from_array(np.arange(10) * 2, chunks=4)
ds = Dataset(OrderedDict([('a', ('t', x)),
('t', ('t', t))]))
expected_pd = pd.DataFrame({'a': x},
index=pd.Index(t, name='t'))
expected = dd.from_pandas(expected_pd, chunksize=4)
actual = ds.to_dask_dataframe(set_index=True)
assert isinstance(actual, dd.DataFrame)
assert_frame_equal(expected.compute(), actual.compute())示例6: test_to_dask_dataframe_not_daskarray
# 需要导入模块: from xarray import Dataset [as 别名]
# 或者: from xarray.Dataset import to_dask_dataframe [as 别名]
def test_to_dask_dataframe_not_daskarray(self):
# Test if DataArray is not a dask array
x = np.random.randn(10)
y = np.arange(10, dtype='uint8')
t = list('abcdefghij')
ds = Dataset(OrderedDict([('a', ('t', x)),
('b', ('t', y)),
('t', ('t', t))]))
expected = pd.DataFrame({'a': x, 'b': y},
index=pd.Index(t, name='t'))
actual = ds.to_dask_dataframe(set_index=True)
assert isinstance(actual, dd.DataFrame)
assert_frame_equal(expected, actual.compute())示例7: test_to_dask_dataframe_2D
# 需要导入模块: from xarray import Dataset [as 别名]
# 或者: from xarray.Dataset import to_dask_dataframe [as 别名]
def test_to_dask_dataframe_2D(self):
# Test if 2-D dataset is supplied
w = da.from_array(np.random.randn(2, 3), chunks=(1, 2))
ds = Dataset({'w': (('x', 'y'), w)})
ds['x'] = ('x', np.array([0, 1], np.int64))
ds['y'] = ('y', list('abc'))
# dask dataframes do not (yet) support multiindex,
# but when it does, this would be the expected index:
exp_index = pd.MultiIndex.from_arrays(
[[0, 0, 0, 1, 1, 1], ['a', 'b', 'c', 'a', 'b', 'c']],
names=['x', 'y'])
expected = pd.DataFrame({'w': w.reshape(-1)},
index=exp_index)
# so for now, reset the index
expected = expected.reset_index(drop=False)
actual = ds.to_dask_dataframe(set_index=False)
assert isinstance(actual, dd.DataFrame)
assert_frame_equal(expected, actual.compute())