def test_labelencoder_unfitted(client):
""" Try calling `.transform()` without fitting first
"""
df = dask_cudf.from_cudf(cudf.Series(np.random.choice(10, (10, ))),
npartitions=len(client.has_what()))
le = LabelEncoder()
with pytest.raises(NotFittedError):
le.transform(df).compute()
def test_unfitted_inverse_transform(client):
""" Try calling `.inverse_transform()` without fitting first
"""
tmp = cudf.Series(np.random.choice(10, (10, )))
df = dask_cudf.from_cudf(tmp, npartitions=len(client.has_what()))
le = LabelEncoder()
with pytest.raises(NotFittedError):
le.transform(df)
def test_labelencoder_unseen(client):
""" Try encoding a value that was not present during fitting
"""
df = dask_cudf.from_cudf(cudf.Series(np.random.choice(10, (10, ))),
npartitions=len(client.has_what()))
le = LabelEncoder().fit(df)
assert le._fitted
with pytest.raises(KeyError):
tmp = dask_cudf.from_cudf(cudf.Series([-100, -120]),
npartitions=len(client.has_what()))
le.transform(tmp).compute()
def test_labelencoder_transform(length, cardinality, client):
""" Try fitting and then encoding a small subset of the df
"""
tmp = cudf.Series(np.random.choice(cardinality, (length, )))
df = dask_cudf.from_cudf(tmp, npartitions=len(client.has_what()))
le = LabelEncoder().fit(df)
assert le._fitted
encoded = le.transform(df)
df_arr = df.compute().to_numpy()
df_arr = _arr_to_similarity_mat(df_arr)
encoder_arr = cp.asnumpy(encoded.compute().to_numpy())
encoded_arr = _arr_to_similarity_mat(encoder_arr)
assert ((encoded_arr == encoded_arr.T) == (df_arr == df_arr.T)).all()