def test_safe_indexing_1d_array_error(X_constructor):
# check that we are raising an error if the array-like passed is 1D and
# we try to index on the 2nd dimension
X = list(range(5))
if X_constructor == 'array':
X_constructor = np.asarray(X)
elif X_constructor == 'series':
pd = pytest.importorskip("pandas")
X_constructor = pd.Series(X)
err_msg = "'X' should be a 2D NumPy array, 2D sparse matrix or pandas"
with pytest.raises(ValueError, match=err_msg):
_safe_indexing(X_constructor, [0, 1], axis=1)
def test_safe_indexing_1d_container_mask(array_type, indices_type):
indices = [False] + [True] * 2 + [False] * 6
array = _convert_container([1, 2, 3, 4, 5, 6, 7, 8, 9], array_type)
indices = _convert_container(indices, indices_type)
subset = _safe_indexing(array, indices, axis=0)
assert_allclose_dense_sparse(subset, _convert_container([2, 3],
array_type))
def test_safe_indexing_1d_container(array_type, indices_type):
indices = [1, 2]
if indices_type == 'slice' and isinstance(indices[1], int):
indices[1] += 1
array = _convert_container([1, 2, 3, 4, 5, 6, 7, 8, 9], array_type)
indices = _convert_container(indices, indices_type)
subset = _safe_indexing(array, indices, axis=0)
assert_allclose_dense_sparse(subset, _convert_container([2, 3],
array_type))
def test_safe_indexing_2d_scalar_axis_1(array_type, expected_output_type,
indices):
columns_name = ['col_0', 'col_1', 'col_2']
array = _convert_container([[1, 2, 3], [4, 5, 6], [7, 8, 9]], array_type,
columns_name)
if isinstance(indices, str) and array_type != 'dataframe':
err_msg = ("Specifying the columns using strings is only supported "
"for pandas DataFrames")
with pytest.raises(ValueError, match=err_msg):
_safe_indexing(array, indices, axis=1)
else:
subset = _safe_indexing(array, indices, axis=1)
expected_output = [3, 6, 9]
if expected_output_type == 'sparse':
# sparse matrix are keeping the 2D shape
expected_output = [[3], [6], [9]]
expected_array = _convert_container(expected_output,
expected_output_type)
assert_allclose_dense_sparse(subset, expected_array)
def test_safe_indexing_2d_mask(array_type, indices_type, axis,
expected_subset):
columns_name = ['col_0', 'col_1', 'col_2']
array = _convert_container([[1, 2, 3], [4, 5, 6], [7, 8, 9]], array_type,
columns_name)
indices = [False, True, True]
indices = _convert_container(indices, indices_type)
subset = _safe_indexing(array, indices, axis=axis)
assert_allclose_dense_sparse(
subset, _convert_container(expected_subset, array_type))
def test_safe_indexing_2d_container_axis_1(array_type, indices_type, indices):
# validation of the indices
# we make a copy because indices is mutable and shared between tests
indices_converted = copy(indices)
if indices_type == 'slice' and isinstance(indices[1], int):
indices_converted[1] += 1
columns_name = ['col_0', 'col_1', 'col_2']
array = _convert_container([[1, 2, 3], [4, 5, 6], [7, 8, 9]], array_type,
columns_name)
indices_converted = _convert_container(indices_converted, indices_type)
if isinstance(indices[0], str) and array_type != 'dataframe':
err_msg = ("Specifying the columns using strings is only supported "
"for pandas DataFrames")
with pytest.raises(ValueError, match=err_msg):
_safe_indexing(array, indices_converted, axis=1)
else:
subset = _safe_indexing(array, indices_converted, axis=1)
assert_allclose_dense_sparse(
subset, _convert_container([[2, 3], [5, 6], [8, 9]], array_type))
def test_check_fit_params(indices):
X = np.random.randn(4, 2)
fit_params = {
'list': [1, 2, 3, 4],
'array': np.array([1, 2, 3, 4]),
'sparse-col': sp.csc_matrix([1, 2, 3, 4]).T,
'sparse-row': sp.csc_matrix([1, 2, 3, 4]),
'scalar-int': 1,
'scalar-str': 'xxx',
'None': None,
}
result = _check_fit_params(X, fit_params, indices)
indices_ = indices if indices is not None else list(range(X.shape[0]))
for key in ['sparse-row', 'scalar-int', 'scalar-str', 'None']:
assert result[key] is fit_params[key]
assert result['list'] == _safe_indexing(fit_params['list'], indices_)
assert_array_equal(result['array'],
_safe_indexing(fit_params['array'], indices_))
assert_allclose_dense_sparse(
result['sparse-col'], _safe_indexing(fit_params['sparse-col'],
indices_))
def test_safe_indexing_2d_read_only_axis_1(array_read_only, indices_read_only,
array_type, indices_type, axis,
expected_array):
array = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
if array_read_only:
array.setflags(write=False)
array = _convert_container(array, array_type)
indices = np.array([1, 2])
if indices_read_only:
indices.setflags(write=False)
indices = _convert_container(indices, indices_type)
subset = _safe_indexing(array, indices, axis=axis)
assert_allclose_dense_sparse(
subset, _convert_container(expected_array, array_type))
def test_safe_indexing_container_axis_0_unsupported_type():
indices = ["col_1", "col_2"]
array = [[1, 2, 3], [4, 5, 6], [7, 8, 9]]
err_msg = "String indexing is not supported with 'axis=0'"
with pytest.raises(ValueError, match=err_msg):
_safe_indexing(array, indices, axis=0)
def test_safe_indexing_error_axis(axis):
with pytest.raises(ValueError, match="'axis' should be either 0"):
_safe_indexing(X_toy, [0, 1], axis=axis)
def test_safe_indexing_pandas_no_matching_cols_error():
pd = pytest.importorskip('pandas')
err_msg = "No valid specification of the columns."
X = pd.DataFrame(X_toy)
with pytest.raises(ValueError, match=err_msg):
_safe_indexing(X, [1.0], axis=1)
def test_safe_indexing_None_axis_0(array_type):
X = _convert_container([[1, 2, 3], [4, 5, 6], [7, 8, 9]], array_type)
X_subset = _safe_indexing(X, None, axis=0)
assert_allclose_dense_sparse(X_subset, X)
def test_safe_indexing_1d_scalar(array_type):
array = _convert_container([1, 2, 3, 4, 5, 6, 7, 8, 9], array_type)
indices = 2
subset = _safe_indexing(array, indices, axis=0)
assert subset == 3
def test_safe_indexing_2d_scalar_axis_0(array_type, expected_output_type):
array = _convert_container([[1, 2, 3], [4, 5, 6], [7, 8, 9]], array_type)
indices = 2
subset = _safe_indexing(array, indices, axis=0)
expected_array = _convert_container([7, 8, 9], expected_output_type)
assert_allclose_dense_sparse(subset, expected_array)
