def test_groupwise():
from sklearn.preprocessing import scale
coord_1 = ["a"] * 51 + ["b"] * 49
coord_2 = list(range(10)) * 10
X_ds = xr.Dataset(
{"var_1": (["sample", "feature"], np.random.random((100, 10)))},
coords={
"sample": range(100),
"feature": range(10),
"coord_1": (["sample"], coord_1),
"coord_2": (["sample"], coord_2),
},
)
# test wrapped sklearn estimator
preprocess(X_ds, scale, groupby="coord_1")
# test newly defined estimator
Xt_ds2, estimator = split(
X_ds,
new_dim="split_sample",
new_len=5,
groupby="coord_1",
keep_coords_as="initial_sample",
return_estimator=True,
)
assert Xt_ds2.var_1.shape == (19, 10, 5)
Xt_ds2 = estimator.inverse_transform(Xt_ds2)
assert Xt_ds2.var_1.shape == (95, 10)
def test_groupwise():
from sklearn.preprocessing import scale
coord_1 = ['a']*51 + ['b']*49
coord_2 = list(range(10))*10
X_ds = xr.Dataset(
{'var_1': (['sample', 'feature'], np.random.random((100, 10)))},
coords={'sample': range(100), 'feature': range(10),
'coord_1': (['sample'], coord_1),
'coord_2': (['sample'], coord_2)}
)
# test wrapped sklearn estimator
Xt_ds = preprocess(X_ds, scale, groupby='coord_1')
# test newly defined estimator
Xt_ds2, estimator = split(
X_ds, new_dim='split_sample', new_len=5, groupby='coord_1',
keep_coords_as='initial_sample', return_estimator=True
)
assert Xt_ds2.var_1.shape == (19, 10, 5)
Xt_ds2 = estimator.inverse_transform(Xt_ds2)
assert Xt_ds2.var_1.shape == (95, 10)
def test_split():
# test on DataArray with number of samples multiple of new length
X_da = xr.DataArray(
np.random.random((100, 10)),
coords={
"sample": range(100),
"feature": range(10),
"coord_1": (["sample", "feature"], np.tile("Test", (100, 10))),
},
dims=("sample", "feature"),
)
estimator = Splitter(
new_dim="split_sample",
new_len=5,
reduce_index="subsample",
axis=1,
keep_coords_as="sample_coord",
)
Xt_da = estimator.fit_transform(X_da)
assert Xt_da.shape == (20, 5, 10)
npt.assert_allclose(Xt_da[0, :, 0], X_da[:5, 0])
Xit_da = estimator.inverse_transform(Xt_da)
xrt.assert_allclose(X_da, Xit_da)
# test on Dataset with number of samples NOT multiple of new length
X_ds = xr.Dataset(
{"var_1": (["sample", "feature"], np.random.random((100, 10)))},
coords={
"sample": range(100),
"feature": range(10)
},
)
Xt_ds = split(
X_ds,
new_dim="split_sample",
new_len=7,
reduce_index="head",
axis=1,
new_index_func=None,
)
assert Xt_ds["var_1"].shape == (14, 7, 10)
npt.assert_allclose(Xt_ds.var_1[0, :, 0], X_ds.var_1[:7, 0])
def test_split():
# test on DataArray with number of samples multiple of new length
X_da = xr.DataArray(np.random.random((100, 10)),
coords={
'sample':
range(100),
'feature':
range(10),
'coord_1':
(['sample', 'feature'], np.tile('Test', (100, 10)))
},
dims=('sample', 'feature'))
estimator = Splitter(new_dim='split_sample',
new_len=5,
reduce_index='subsample',
axis=1,
keep_coords_as='sample_coord')
Xt_da = estimator.fit_transform(X_da)
assert Xt_da.shape == (20, 5, 10)
npt.assert_allclose(Xt_da[0, :, 0], X_da[:5, 0])
Xit_da = estimator.inverse_transform(Xt_da)
xrt.assert_allclose(X_da, Xit_da)
# test on Dataset with number of samples NOT multiple of new length
X_ds = xr.Dataset(
{'var_1': (['sample', 'feature'], np.random.random((100, 10)))},
coords={
'sample': range(100),
'feature': range(10)
})
Xt_ds = split(X_ds,
new_dim='split_sample',
new_len=7,
reduce_index='head',
axis=1,
new_index_func=None)
assert Xt_ds['var_1'].shape == (14, 7, 10)
npt.assert_allclose(Xt_ds.var_1[0, :, 0], X_ds.var_1[:7, 0])