def test_imputer_sparse(
sparse_int_dataset,
strategy, # noqa: F811
missing_values):
X_np, X = sparse_int_dataset
if X.format == 'csr':
pytest.skip("Skipping CSR matrices")
X_sp = X_np.tocsc()
if np.isnan(missing_values):
# Adding nan when missing value is nan
random_loc = np.random.choice(X.nnz, int(X.nnz * 0.1), replace=False)
X_sp.data[random_loc] = np.nan
X = X.copy()
X.data[random_loc] = np.nan
fill_value = np.random.randint(10, size=1)[0]
imputer = cuSimpleImputer(copy=True,
missing_values=missing_values,
strategy=strategy,
fill_value=fill_value)
t_X = imputer.fit_transform(X)
assert type(t_X) == type(X)
imputer = skSimpleImputer(copy=True,
missing_values=missing_values,
strategy=strategy,
fill_value=fill_value)
sk_t_X = imputer.fit_transform(X_sp)
assert_allclose(t_X, sk_t_X)
def test__repr__():
assert cuStandardScaler().__repr__() == 'StandardScaler()'
assert cuMinMaxScaler().__repr__() == 'MinMaxScaler()'
assert cuMaxAbsScaler().__repr__() == 'MaxAbsScaler()'
assert cuNormalizer().__repr__() == 'Normalizer()'
assert cuBinarizer().__repr__() == 'Binarizer()'
assert cuPolynomialFeatures().__repr__() == 'PolynomialFeatures()'
assert cuSimpleImputer().__repr__() == 'SimpleImputer()'
assert cuRobustScaler().__repr__() == 'RobustScaler()'
assert cuKBinsDiscretizer().__repr__() == 'KBinsDiscretizer()'
def test_imputer(int_dataset, strategy, missing_values): # noqa: F811
X_np, X = int_dataset
fill_value = np.random.randint(10, size=1)[0]
imputer = cuSimpleImputer(copy=True, missing_values=missing_values,
strategy=strategy, fill_value=fill_value)
t_X = imputer.fit_transform(X)
assert type(t_X) == type(X)
imputer = skSimpleImputer(copy=True, missing_values=missing_values,
strategy=strategy, fill_value=fill_value)
sk_t_X = imputer.fit_transform(X_np)
assert_allclose(t_X, sk_t_X)
def test_imputer(int_dataset, strategy, missing_values, # noqa: F811
add_indicator):
zero_filled, one_filled, nan_filled = int_dataset
if missing_values == 0:
X_np, X = zero_filled
elif missing_values == 1:
X_np, X = one_filled
else:
X_np, X = nan_filled
fill_value = np.random.randint(10, size=1)[0]
imputer = cuSimpleImputer(copy=True, missing_values=missing_values,
strategy=strategy, fill_value=fill_value,
add_indicator=add_indicator)
t_X = imputer.fit_transform(X)
assert type(t_X) == type(X)
imputer = skSimpleImputer(copy=True, missing_values=missing_values,
strategy=strategy, fill_value=fill_value,
add_indicator=add_indicator)
sk_t_X = imputer.fit_transform(X_np)
assert_allclose(t_X, sk_t_X)