def test_onehot_inverse_transform(client, drop):
df = DataFrame({'g': ['M', 'F', 'F'], 'i': [1, 3, 2]})
X = dask_cudf.from_cudf(df, npartitions=2)
enc = OneHotEncoder(drop=drop)
ohe = enc.fit_transform(X)
inv = enc.inverse_transform(ohe)
assert_frame_equal(inv.compute().to_pandas(), df.to_pandas())
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())
def test_onehot_drop_idx_first(client):
X_ary = [['c', 2, 'a'], ['b', 2, 'b']]
X = DataFrame({'chars': ['c', 'b'], 'int': [2, 2], 'letters': ['a', 'b']})
ddf = dask_cudf.from_cudf(X, npartitions=2)
enc = OneHotEncoder(sparse=False, drop='first')
sk_enc = SkOneHotEncoder(sparse=False, drop='first')
ohe = enc.fit_transform(ddf)
ref = sk_enc.fit_transform(X_ary)
cp.testing.assert_array_equal(ohe.compute(), ref)
inv = enc.inverse_transform(ohe)
assert_frame_equal(inv.compute().to_pandas(), X.to_pandas())
def test_onehot_drop_one_of_each(cluster):
client = Client(cluster)
X_ary = [['c', 2, 'a'], ['b', 2, 'b']]
X = DataFrame({'chars': ['c', 'b'], 'int': [2, 2], 'letters': ['a', 'b']})
ddf = dask_cudf.from_cudf(X, npartitions=2)
drop = dict({'chars': 'b', 'int': 2, 'letters': 'b'})
enc = OneHotEncoder(sparse=False, drop=drop)
sk_enc = SkOneHotEncoder(sparse=False, drop=['b', 2, 'b'])
ohe = enc.fit_transform(ddf)
ref = sk_enc.fit_transform(X_ary)
cp.testing.assert_array_equal(ohe.compute(), ref)
inv = enc.inverse_transform(ohe)
assert_frame_equal(inv.compute().to_pandas(), X.to_pandas())
client.close()
def test_onehot_random_inputs(client, drop, as_array, sparse, n_samples):
X, ary = generate_inputs_from_categories(n_samples=n_samples,
as_array=as_array)
if as_array:
dX = da.from_array(X)
else:
dX = dask_cudf.from_cudf(X, npartitions=1)
enc = OneHotEncoder(sparse=sparse, drop=drop, categories='auto')
sk_enc = SkOneHotEncoder(sparse=sparse, drop=drop, categories='auto')
ohe = enc.fit_transform(dX)
ref = sk_enc.fit_transform(ary)
if sparse:
cp.testing.assert_array_equal(ohe.compute().toarray(), ref.toarray())
else:
cp.testing.assert_array_equal(ohe.compute(), ref)
inv_ohe = enc.inverse_transform(ohe)
assert_inverse_equal(inv_ohe.compute(), dX.compute())