def test_onehot_fit_handle_unknown(client):
X = DataFrame({'chars': ['a', 'b'], 'int': [0, 2]})
Y = DataFrame({'chars': ['c', 'b'], 'int': [0, 2]})
X = dask_cudf.from_cudf(X, npartitions=2)
enc = OneHotEncoder(handle_unknown='error', categories=Y)
with pytest.raises(KeyError):
enc.fit(X)
enc = OneHotEncoder(handle_unknown='ignore', categories=Y)
enc.fit(X)
def test_onehot_transform_handle_unknown(client):
X = DataFrame({'chars': ['a', 'b'], 'int': [0, 2]})
Y = DataFrame({'chars': ['c', 'b'], 'int': [0, 2]})
X = dask_cudf.from_cudf(X, npartitions=2)
Y = dask_cudf.from_cudf(Y, npartitions=2)
enc = OneHotEncoder(handle_unknown='error', sparse=False)
enc = enc.fit(X)
with pytest.raises(KeyError):
enc.transform(Y).compute()
enc = OneHotEncoder(handle_unknown='ignore', sparse=False)
enc = enc.fit(X)
ohe = enc.transform(Y)
ref = cp.array([[0., 0., 1., 0.], [0., 1., 0., 1.]])
cp.testing.assert_array_equal(ohe.compute(), ref)
def test_onehot_inverse_transform_handle_unknown(client):
X = DataFrame({'chars': ['a', 'b'], 'int': [0, 2]})
X = dask_cudf.from_cudf(X, npartitions=2)
Y_ohe = cp.array([[0., 0., 1., 0.], [0., 1., 0., 1.]])
Y_ohe = da.from_array(Y_ohe)
enc = OneHotEncoder(handle_unknown='ignore')
enc = enc.fit(X)
df = enc.inverse_transform(Y_ohe)
ref = DataFrame({'chars': [None, 'b'], 'int': [0, 2]})
assert_frame_equal(df.compute().to_pandas(), ref.to_pandas())