class TestUnit(TestCase):
@given(get_labels())
def test_index_values_len(self, values):
def property_values(cls, values):
#Property: that the length of the index is the length of the (unique) values.
index = cls(values)
self.assertEqual(len(index), len(values))
self.assertEqual(len(index.values), len(values))
property_values(Index, values)
property_values(IndexGO, values)
@given(get_labels())
def test_index_values_list(self, values):
def property_values(cls, values):
index = cls(values)
# must cast both sides to the dtype, as some int to float conversions result in different floats
self.assertAlmostEqualValues(
index.values, np.array(values, dtype=index.values.dtype))
property_values(Index, values)
property_values(IndexGO, values)
@given(get_labels())
def test_index_loc_to_iloc_element(self, values):
def property_loc_to_iloc_element(cls, values):
index = cls(values)
for i, v in enumerate(values):
self.assertEqual(index.loc_to_iloc(v), i)
property_loc_to_iloc_element(Index, values)
property_loc_to_iloc_element(IndexGO, values)
@given(get_labels(min_size=1))
def test_index_loc_to_iloc_slice(self, values):
def property_loc_to_iloc_slice(cls, values):
# Property: that the key translates to the appropriate slice.
index = cls(values)
for i, v in enumerate(values):
# insure that we get teh same slice going through loc that we would get by direct iloc
if v is None:
self.assertEqual(index.loc_to_iloc(slice(v, None)),
slice(None))
else:
self.assertEqual(index.loc_to_iloc(slice(v, None)),
slice(i, None))
property_loc_to_iloc_slice(Index, values)
property_loc_to_iloc_slice(IndexGO, values)
@given(get_labels(min_size=2))
def test_index_go_append(self, values):
index = IndexGO(values[:-1])
length_start = len(index)
index.append(values[-1])
length_end = len(index)
self.assertEqual(length_start + 1, length_end)
class TestUnit(TestCase):
@given(get_array_1d2d())
def test_mloc(self, array):
x = util.mloc(array)
self.assertTrue(isinstance(x, int))
@given(get_dtype_pairs())
def test_resolve_dtype(self, dtype_pair):
x = util.resolve_dtype(*dtype_pair)
self.assertTrue(isinstance(x, np.dtype))
@given(get_dtypes(min_size=1))
def test_resolve_dtype_iter(self, dtypes):
x = util.resolve_dtype_iter(dtypes)
self.assertTrue(isinstance(x, np.dtype))
@given(get_labels(min_size=1))
def test_resolve_type_object_iter(self, objects):
x = util.resolve_type_object_iter(objects)
self.assertTrue(x in (None, str, object))
@given(get_arrays_2d_aligned_columns())
def test_concat_resolved_axis_0(self, arrays):
array = util.concat_resolved(arrays, axis=0)
self.assertEqual(array.ndim, 2)
self.assertEqual(array.dtype, util.resolve_dtype_iter((x.dtype for x in arrays)))
@given(get_arrays_2d_aligned_rows())
def test_concat_resolved_axis_1(self, arrays):
array = util.concat_resolved(arrays, axis=1)
self.assertEqual(array.ndim, 2)
self.assertEqual(array.dtype, util.resolve_dtype_iter((x.dtype for x in arrays)))
@given(get_dtype(), get_shape_1d2d(), get_value())
def test_full_or_fill(self, dtype, shape, value):
array = util.full_for_fill(dtype, shape, fill_value=value)
self.assertTrue(array.shape == shape)
if isinstance(value, (float, complex)) and np.isnan(value):
pass
else:
self.assertTrue(value in array)
class TestUnit(TestCase):
@given(sfst.get_labels()) # type: ignore
def test_get_labels(self, values: tp.Iterable[tp.Hashable]) -> None:
for value in values:
self.assertTrue(isinstance(hash(value), int))
@given(sfst.get_dtypes()) # type: ignore
def test_get_dtypes(self, dtypes: tp.Iterable[np.dtype]) -> None:
for dt in dtypes:
self.assertTrue(isinstance(dt, np.dtype))
@given(sfst.get_spacing(10)) # type: ignore
def test_get_spacing_10(self, spacing: tp.Iterable[int]) -> None:
self.assertEqual(sum(spacing), 10)
@hypo_settings(max_examples=10) # type: ignore
@given(sfst.get_shape_1d2d()) # type: ignore
def test_get_shape_1d2d(self, shape: tp.Tuple[int, ...]) -> None:
self.assertTrue(isinstance(shape, tuple))
self.assertTrue(len(shape) in (1, 2))
@hypo_settings(max_examples=10) # type: ignore
@given(sfst.get_array_1d2d()) # type: ignore
def test_get_array_1d2d(self, array: np.ndarray) -> None:
self.assertTrue(isinstance(array, np.ndarray))
self.assertTrue(array.ndim in (1, 2))
@hypo_settings(max_examples=10) # type: ignore
@given(sfst.get_arrays_2d_aligned_columns(min_size=2)) # type: ignore
def test_get_arrays_2s_aligned_columns(self, arrays: tp.Iterable[np.ndarray]) -> None:
array_iter = iter(arrays)
a1 = next(array_iter)
match = a1.shape[1]
for array in array_iter:
self.assertEqual(array.shape[1], match)
@given(sfst.get_arrays_2d_aligned_rows(min_size=2)) # type: ignore
def test_get_arrays_2s_aligned_rows(self, arrays: tp.Iterable[np.ndarray]) -> None:
array_iter = iter(arrays)
a1 = next(array_iter)
match = a1.shape[0]
for array in array_iter:
self.assertEqual(array.shape[0], match)
@hypo_settings(max_examples=10) # type: ignore
@given(sfst.get_blocks()) # type: ignore
def test_get_blocks(self, blocks: tp.Tuple[np.ndarray]) -> None:
self.assertTrue(isinstance(blocks, tuple))
for b in blocks:
self.assertTrue(isinstance(b, np.ndarray))
self.assertTrue(b.ndim in (1, 2))
@hypo_settings(max_examples=10) # type: ignore
@given(sfst.get_type_blocks()) # type: ignore
def test_get_type_blocks(self, tb: TypeBlocks) -> None:
self.assertTrue(isinstance(tb, TypeBlocks))
rows, cols = tb.shape
col_count = 0
for b in tb._blocks:
if b.ndim == 1:
self.assertEqual(len(b), rows)
col_count += 1
else:
self.assertEqual(b.ndim, 2)
self.assertEqual(b.shape[0], rows)
col_count += b.shape[1]
self.assertEqual(col_count, cols)
@hypo_settings(max_examples=10) # type: ignore
@given(sfst.get_index()) # type: ignore
def test_get_index(self, idx: Index) -> None:
self.assertTrue(isinstance(idx, Index))
self.assertEqual(len(idx), len(idx.values))
@hypo_settings(max_examples=10) # type: ignore
@given(sfst.get_index_hierarchy()) # type: ignore
def test_get_index_hierarchy(self, idx: IndexHierarchy) -> None:
self.assertTrue(isinstance(idx, IndexHierarchy))
self.assertTrue(idx.depth > 1)
self.assertEqual(len(idx), len(idx.values))
@hypo_settings(max_examples=10) # type: ignore
@given(sfst.get_series()) # type: ignore
def test_get_series(self, series: Series) -> None:
self.assertTrue(isinstance(series, Series))
self.assertEqual(len(series), len(series.values))
@hypo_settings(max_examples=10) # type: ignore
@given(sfst.get_frame()) # type: ignore
def test_get_frame(self, frame: Frame) -> None:
self.assertTrue(isinstance(frame, Frame))
self.assertEqual(frame.shape, frame.values.shape)
@hypo_settings(max_examples=10) # type: ignore
@given(sfst.get_frame(index_cls=IndexHierarchy, columns_cls=IndexHierarchy)) # type: ignore
def test_get_frame_hierarchy(self, frame: Frame) -> None:
self.assertTrue(isinstance(frame, Frame))
self.assertTrue(frame.index.depth > 1)
self.assertTrue(frame.columns.depth > 1)
self.assertEqual(frame.shape, frame.values.shape)
class TestUnit(TestCase):
@given(st.lists(sfst.get_shape_2d(), min_size=1),
sfst.get_labels(min_size=1))
def test_from_element_items(self, shapes: tp.List[tp.Tuple[int, int]],
labels: tp.Sequence[tp.Hashable]) -> None:
# use shapes to get coordinates, where the max shape + 1 is the final shape
shape = tuple(np.array(shapes).max(axis=0) + 1)
def values() -> tp.Iterator[tp.Tuple[tp.Tuple[int, int], tp.Hashable]]:
for idx, coord in enumerate(shapes):
yield coord, labels[idx % len(labels)]
post = TypeBlocks.from_element_items(values(),
shape=shape,
dtype=object)
self.assertEqual(post.shape, shape)
@given(st.integers(max_value=sfst.MAX_COLUMNS))
def test_from_zero_size_shape(self, value: int) -> None:
for shape in ((0, value), (value, 0)):
post = TypeBlocks.from_zero_size_shape(shape=shape)
self.assertEqual(post.shape, shape)
@given(sfst.get_type_blocks())
def test_basic_attributes(self, tb: TypeBlocks) -> None:
self.assertEqual(len(tb.dtypes), tb.shape[1])
self.assertEqual(len(tb.shapes), len(tb.mloc))
self.assertEqual(tb.copy().shape, tb.shape)
self.assertEqual(tb.ndim, 2)
self.assertEqual(tb.unified, len(tb.mloc) <= 1)
if tb.shape[0] > 0 and tb.shape[1] > 0:
self.assertTrue(tb.size > 0)
self.assertTrue(tb.nbytes > 0)
else:
self.assertTrue(tb.size == 0)
self.assertTrue(tb.nbytes == 0)
@given(sfst.get_type_blocks())
def test_values(self, tb: TypeBlocks) -> None:
values = tb.values
self.assertEqual(values.shape, tb.shape)
self.assertEqual(values.dtype, tb._row_dtype)
@given(sfst.get_type_blocks())
def test_axis_values(self, tb: TypeBlocks) -> None:
# this test found a flaw in axis_values when dealing with axis 1 and unified, 1D type blocks
for axis in (0, 1):
for reverse in (True, False):
post = tuple(tb.axis_values(axis=axis, reverse=reverse))
for idx, array in enumerate(post):
self.assertTrue(len(array) == tb.shape[axis])
if axis == 0 and not reverse: # colums
self.assertTrue(array.dtype == tb.dtypes[idx])
elif axis == 0 and reverse: # colums
self.assertTrue(array.dtype == tb.dtypes[tb.shape[1] -
1 - idx])
else:
# NOTE: only checking kinde because found cases where byte-order deviates
self.assertTrue(array.dtype.kind == tb._row_dtype.kind)
@given(sfst.get_type_blocks())
def test_element_items(self, tb: TypeBlocks) -> None:
# NOTE: this found a flaw in _extract_iloc where we tried to optimize selection with a unified array
count = 0
for k, v in tb.element_items():
count += 1
v_extract = tb.iloc[k]
self.assertEqualWithNaN(v, v_extract)
self.assertEqual(count, tb.size)
@given(sfst.get_type_blocks())
def test_reblock_signature(self, tb: TypeBlocks) -> None:
post = tuple(tb._reblock_signature())
unique_dtypes = np.unique(tb.dtypes)
# the reblock signature must be have at least as many entries as types
self.assertTrue(len(post) >= len(unique_dtypes))
# sum of column widths is qual to columns in shape
self.assertTrue(sum(p[1] for p in post), tb.shape[1])
@given(sfst.get_type_blocks(), sfst.get_type_blocks())
def test_block_compatible(self, tb1: TypeBlocks, tb2: TypeBlocks) -> None:
for axis in (None, 0, 1):
post1 = tb1.block_compatible(tb2, axis)
post2 = tb2.block_compatible(tb1, axis)
# either direction gets the same result
self.assertTrue(post1 == post2)
# if the shapes are different, they cannot be block compatible
if axis is None and tb1.shape != tb2.shape:
self.assertFalse(post1)
@given(sfst.get_type_blocks(), sfst.get_type_blocks())
def test_reblock_compatible(self, tb1: TypeBlocks,
tb2: TypeBlocks) -> None:
post1 = tb1.reblock_compatible(tb2)
post2 = tb2.reblock_compatible(tb1)
# either direction gets the same result
self.assertTrue(post1 == post2)
# if the shapes are different, they cannot be block compatible
if tb1.shape[1] != tb2.shape[1]:
self.assertFalse(post1)
@unittest.skip('pending')
def test_concatenate_blocks(self) -> None:
pass
@given(sfst.get_type_blocks())
def test_consolidate_blocks(self, tb: TypeBlocks) -> None:
tb_post = TypeBlocks.from_blocks(tb.consolidate_blocks(tb._blocks))
self.assertEqual(tb_post.shape, tb.shape)
self.assertTrue((tb_post.dtypes == tb.dtypes).all())
@given(sfst.get_type_blocks())
def test_reblock(self, tb: TypeBlocks) -> None:
tb_post = TypeBlocks.from_blocks(tb._reblock())
self.assertEqual(tb_post.shape, tb.shape)
self.assertTrue((tb_post.dtypes == tb.dtypes).all())
@given(sfst.get_type_blocks())
def test_consolidate(self, tb: TypeBlocks) -> None:
tb_post = tb.consolidate()
self.assertEqual(tb_post.shape, tb.shape)
self.assertTrue((tb_post.dtypes == tb.dtypes).all())
@unittest.skip('pending')
def test_resize_blocks(self) -> None:
pass
@unittest.skip('pending')
def test_group(self) -> None:
pass
@unittest.skip('pending')
def test_ufunc_axis_skipna(self) -> None:
pass
@given(sfst.get_type_blocks())
def test_display(self, tb: TypeBlocks) -> None:
post = tb.display()
self.assertTrue(len(post) > 0)
@unittest.skip('pending')
def test_cols_to_slice(self) -> None:
pass
@unittest.skip('pending')
def test_indices_to_contiguous_pairs(self) -> None:
pass
@unittest.skip('pending')
def test_key_to_block_slices(self) -> None:
pass
@unittest.skip('pending')
def test_mask_blocks(self) -> None:
pass
@unittest.skip('pending')
def test_astype_blocks(self) -> None:
pass
@unittest.skip('pending')
def test_shift_blocks(self) -> None:
pass
@given(sfst.get_type_blocks())
def test_assign_blocks_from_keys(self, tb1: TypeBlocks) -> None:
# assigning a single value from a list of column keys
for i in range(tb1.shape[1]):
tb2 = TypeBlocks.from_blocks(
tb1._assign_from_iloc_by_unit(column_key=[i], value=300))
self.assertTrue(tb1.shape == tb2.shape)
# no more than one type should be changed
self.assertTrue((tb1.dtypes != tb2.dtypes).sum() <= 1)
# assigning a single value from a list of row keys
for i in range(tb1.shape[0]):
tb3 = TypeBlocks.from_blocks(
tb1._assign_from_iloc_by_unit(row_key=[i], value=300))
self.assertTrue(tb1.shape == tb3.shape)
self.assertTrue(tb3.iloc[i, 0] == 300)
# column slices to the end
for i in range(tb1.shape[1]):
tb4 = TypeBlocks.from_blocks(
tb1._assign_from_iloc_by_unit(column_key=slice(i, None),
value=300))
self.assertTrue(tb1.shape == tb4.shape)
# we have as many or more blocks
self.assertTrue(len(tb4.shapes) >= len(tb1.shapes))
@unittest.skip('pending')
def test_assign_blocks_from_boolean_blocks(self) -> None:
pass
@unittest.skip('pending')
def test_slice_blocks(self) -> None:
pass
@unittest.skip('pending')
def test_extract_array(self) -> None:
pass
@unittest.skip('pending')
def test_extract(self) -> None:
pass
@unittest.skip('pending')
def test_extract_iloc(self) -> None:
pass
@unittest.skip('pending')
def test_extract_iloc_mask(self) -> None:
pass
@unittest.skip('pending')
def test_extract_iloc_assign(self) -> None:
pass
@given(sfst.get_type_blocks(min_rows=1, min_columns=1))
def test_drop(self, tb: TypeBlocks) -> None:
for row in range(tb.shape[0]):
tb_post1 = tb.drop(row)
self.assertTrue(tb_post1.shape[0] == tb.shape[0] - 1)
if tb.shape[0] > 2:
for start in range(1, tb.shape[0]):
tb_post2 = tb.drop(slice(start, None))
self.assertTrue(tb_post2.shape[0] == start)
for col in range(tb.shape[1]):
tb_post3 = tb.drop((None, col))
self.assertTrue(tb_post3.shape[1] == tb.shape[1] - 1)
if tb.shape[1] > 2:
for start in range(1, tb.shape[1]):
tb_post4 = tb.drop((None, slice(start, None)))
self.assertTrue(tb_post4.shape[1] == start)
@unittest.skip('pending')
def test_getitem(self) -> None:
pass
@unittest.skip('pending')
def test_ufunc_unary_operator(self) -> None:
pass
@unittest.skip('pending')
def test_block_shape_slices(self) -> None:
pass
@unittest.skip('pending')
def test_ufunc_binary_operator(self) -> None:
pass
@unittest.skip('pending')
def test_transpose(self) -> None:
pass
@unittest.skip('pending')
def test_isna(self) -> None:
pass
@unittest.skip('pending')
def test_notna(self) -> None:
pass
@unittest.skip('pending')
def test_fillna_leading(self) -> None:
pass
@unittest.skip('pending')
def test_fillna_trailing(self) -> None:
pass
@unittest.skip('pending')
def test_fillna_forward(self) -> None:
pass
@unittest.skip('pending')
def test_fillna_backward(self) -> None:
pass
@unittest.skip('pending')
def test_dropna_to_keep_locations(self) -> None:
pass
@unittest.skip('pending')
def test_fillna(self) -> None:
pass
@given(sfst.get_type_blocks_aligned_array())
def test_append(
self, tb_aligned_array: tp.Tuple[TypeBlocks, np.ndarray]) -> None:
tb, aa = tb_aligned_array
shape_original = tb.shape
tb.append(aa)
if aa.ndim == 1:
self.assertEqual(tb.shape[1], shape_original[1] + 1)
else:
self.assertEqual(tb.shape[1], shape_original[1] + aa.shape[1])
@given(sfst.get_type_blocks_aligned_type_blocks(min_size=2, max_size=2))
def test_extend(self, tbs: tp.Sequence[TypeBlocks]) -> None:
front = tbs[0]
back = tbs[1]
shape_original = front.shape
# extend with type blocks
front.extend(back)
self.assertEqual(
front.shape,
(shape_original[0], shape_original[1] + back.shape[1]))
# extend with iterable of arrays
front.extend(back._blocks)
self.assertEqual(
front.shape,
(shape_original[0], shape_original[1] + back.shape[1] * 2))
class TestUnit(TestCase):
@given(get_array_1d2d()) # type: ignore
def test_mloc(self, array: np.ndarray) -> None:
x = util.mloc(array)
self.assertTrue(isinstance(x, int))
@given(get_array_1d2d()) # type: ignore
def test_shape_filter(self, shape: np.ndarray) -> None:
self.assertTrue(len(util.shape_filter(shape)), 2)
@given(get_dtype_pairs()) # type: ignore
def test_resolve_dtype(self, dtype_pair: tp.Tuple[np.dtype,
np.dtype]) -> None:
x = util.resolve_dtype(*dtype_pair)
self.assertTrue(isinstance(x, np.dtype))
@given(get_dtypes(min_size=1)) # type: ignore
def test_resolve_dtype_iter(self, dtypes: tp.Iterable[np.dtype]) -> None:
x = util.resolve_dtype_iter(dtypes)
self.assertTrue(isinstance(x, np.dtype))
@given(get_labels(min_size=1)) # type: ignore
def test_resolve_type_iter(self, objects: tp.Iterable[object]) -> None:
known_types = set(
(None, type(None), bool, str, object, int, float, complex,
datetime.date, datetime.datetime, fractions.Fraction))
resolved, has_tuple, values_post = util.resolve_type_iter(objects)
self.assertTrue(resolved in known_types)
@given(get_arrays_2d_aligned_columns()) # type: ignore
def test_concat_resolved_axis_0(self, arrays: tp.List[np.ndarray]) -> None:
array = util.concat_resolved(arrays, axis=0)
self.assertEqual(array.ndim, 2)
self.assertEqual(array.dtype,
util.resolve_dtype_iter((x.dtype for x in arrays)))
@given(get_arrays_2d_aligned_rows()) # type: ignore
def test_concat_resolved_axis_1(self, arrays: tp.List[np.ndarray]) -> None:
array = util.concat_resolved(arrays, axis=1)
self.assertEqual(array.ndim, 2)
self.assertEqual(array.dtype,
util.resolve_dtype_iter((x.dtype for x in arrays)))
@given(get_dtype(), get_shape_1d2d(), get_value()) # type: ignore
def test_full_or_fill(self, dtype: np.dtype,
shape: tp.Union[tp.Tuple[int], tp.Tuple[int, int]],
value: object) -> None:
array = util.full_for_fill(dtype, shape, fill_value=value)
self.assertTrue(array.shape == shape)
if isinstance(value, (float, complex)) and np.isnan(value):
pass
else:
self.assertTrue(value in array)
@given(get_dtype()) # type: ignore
def test_dtype_to_na(self, dtype: util.DtypeSpecifier) -> None:
post = util.dtype_to_na(dtype)
self.assertTrue(post in {0, False, None, '', np.nan, util.NAT})
@given(get_array_1d2d(dtype_group=DTGroup.NUMERIC)) # type: ignore
def test_ufunc_axis_skipna(self, array: np.ndarray) -> None:
has_na = util.isna_array(array).any()
for nt in UFUNC_AXIS_SKIPNA.values():
ufunc = nt.ufunc
ufunc_skipna = nt.ufunc_skipna
# dtypes = nt.dtypes
# composable = nt.composable
# doc = nt.doc_header
# size_one_unity = nt.size_one_unity
with np.errstate(over='ignore', under='ignore', divide='ignore'):
post = util.ufunc_axis_skipna(array=array,
skipna=True,
axis=0,
ufunc=ufunc,
ufunc_skipna=ufunc_skipna)
if array.ndim == 2:
self.assertTrue(post.ndim == 1)
@given(get_array_1d2d()) # type: ignore
def test_ufunc_unique(self, array: np.ndarray) -> None:
post = util.ufunc_unique(array, axis=0)
self.assertTrue(len(post) <= array.shape[0])
@given(get_array_1d(min_size=1), st.integers()) # type: ignore
def test_roll_1d(self, array: np.ndarray, shift: int) -> None:
post = util.roll_1d(array, shift)
self.assertEqual(len(post), len(array))
self.assertEqualWithNaN(array[-(shift % len(array))], post[0])
@given(get_array_2d(min_rows=1, min_columns=1),
st.integers()) # type: ignore
def test_roll_2d(self, array: np.ndarray, shift: int) -> None:
for axis in (0, 1):
post = util.roll_2d(array, shift=shift, axis=axis)
self.assertEqual(post.shape, array.shape)
start = -(shift % array.shape[axis])
if axis == 0:
a = array[start]
b = post[0]
else:
a = array[:, start]
b = post[:, 0]
self.assertAlmostEqualValues(a, b)
@given(get_array_1d(dtype_group=DTGroup.OBJECT)) # type: ignore
def test_iterable_to_array_a(self, array: np.ndarray) -> None:
values = array.tolist()
post, _ = util.iterable_to_array(values)
self.assertAlmostEqualValues(post, values)
# explicitly giving object dtype
post, _ = util.iterable_to_array(values, dtype=util.DTYPE_OBJECT)
self.assertAlmostEqualValues(post, values)
@given(get_labels()) # type: ignore
def test_iterable_to_array_b(self, labels: tp.Iterable[tp.Any]) -> None:
post, _ = util.iterable_to_array(labels)
self.assertAlmostEqualValues(post, labels)
self.assertTrue(isinstance(post, np.ndarray))
@given(st.slices(10)) # type: ignore #pylint: disable=E1120
def test_slice_to_ascending_slice(self, key: slice) -> None:
post_key = util.slice_to_ascending_slice(key, size=10)
self.assertEqual(set(range(*key.indices(10))),
set(range(*post_key.indices(10))))
# to_datetime64
# to_timedelta64
# key_to_datetime_key
@given(get_array_1d2d()) # type: ignore
def test_array_to_groups_and_locations(self, array: np.ndarray) -> None:
groups, locations = util.array_to_groups_and_locations(array, 0)
if len(array) > 0:
self.assertTrue(len(groups) >= 1)
# always 1dm locations
self.assertTrue(locations.ndim == 1)
self.assertTrue(len(np.unique(locations)) == len(groups))
@given(get_array_1d2d()) # type: ignore
def test_isna_array(self, array: np.ndarray) -> None:
post = util.isna_array(array)
self.assertTrue(post.dtype == bool)
values = np.ravel(array)
count_na = sum(util.isna_element(x) for x in values)
self.assertTrue(np.ravel(post).sum() == count_na)
@given(get_array_1d(dtype_group=DTGroup.BOOL)) # type: ignore
def test_binary_transition(self, array: np.ndarray) -> None:
post = util.binary_transition(array)
# could be 32 via result of np.nonzero
self.assertTrue(post.dtype in (np.int32, np.int64))
# if no True in original array, result will be empty
if array.sum() == 0:
self.assertTrue(len(post) == 0)
# if all True, result is empty
elif array.sum() == len(array):
self.assertTrue(len(post) == 0)
else:
# the post selection shold always be indices that are false
self.assertTrue(array[post].sum() == 0)
@given(get_array_1d2d()) # type: ignore
def test_array_to_duplicated(self, array: np.ndarray) -> None:
if array.ndim == 2:
for axis in (0, 1):
post = util.array_to_duplicated(array, axis=axis)
if axis == 0:
unique_count = len(set(tuple(x) for x in array))
else:
unique_count = len(
set(tuple(array[:, i]) for i in range(array.shape[1])))
if unique_count < array.shape[axis]:
self.assertTrue(post.sum() > 0)
else:
post = util.array_to_duplicated(array)
# if not all value are unique, we must have some duplicated
if len(set(array)) < len(array):
self.assertTrue(post.sum() > 0)
self.assertTrue(post.dtype == bool)
@given(get_array_1d2d()) # type: ignore
def test_array_shift(self, array: np.ndarray) -> None:
for shift in (-1, 1):
for wrap in (True, False):
tests = []
post1 = util.array_shift(array=array,
shift=shift,
axis=0,
wrap=wrap)
tests.append(post1)
if array.ndim == 2:
post2 = util.array_shift(array=array,
shift=shift,
axis=1,
wrap=wrap)
tests.append(post2)
for post in tests:
self.assertTrue(array.shape == post.shape)
# type is only always maintained if we are wrapping
if wrap:
self.assertTrue(array.dtype == post.dtype)
@given(st.lists(get_array_1d(), min_size=2, max_size=2)) # type: ignore
def test_union1d(self, arrays: tp.Sequence[np.ndarray]) -> None:
post = util.union1d(arrays[0], arrays[1], assume_unique=False)
self.assertTrue(post.ndim == 1)
# nan values in complex numbers make direct comparison tricky
self.assertTrue(len(post) == len(set(arrays[0]) | set(arrays[1])))
# complex results are tricky to compare after forming sets
if (post.dtype.kind not in ('O', 'M', 'm', 'c', 'f')
and not np.isnan(post).any()):
self.assertTrue(set(post) == (set(arrays[0]) | set(arrays[1])))
@given(st.lists(get_array_1d(), min_size=2, max_size=2)) # type: ignore
def test_intersect1d(self, arrays: tp.Sequence[np.ndarray]) -> None:
post = util.intersect1d(arrays[0], arrays[1], assume_unique=False)
self.assertTrue(post.ndim == 1)
# nan values in complex numbers make direct comparison tricky
self.assertTrue(len(post) == len(set(arrays[0]) & set(arrays[1])))
if (post.dtype.kind not in ('O', 'M', 'm', 'c', 'f')
and not np.isnan(post).any()):
self.assertTrue(set(post) == (set(arrays[0]) & set(arrays[1])))
@given(get_arrays_2d_aligned_columns(min_size=2,
max_size=2)) # type: ignore
def test_union2d(self, arrays: tp.Sequence[np.ndarray]) -> None:
post = util.union2d(arrays[0], arrays[1], assume_unique=False)
if post.dtype == object:
self.assertTrue(post.ndim == 1)
else:
self.assertTrue(post.ndim == 2)
self.assertTrue(
len(post) == len(
set(util.array2d_to_tuples(arrays[0]))
| set(util.array2d_to_tuples(arrays[1]))))
@given(get_arrays_2d_aligned_columns(min_size=2,
max_size=2)) # type: ignore
def test_intersect2d(self, arrays: tp.Sequence[np.ndarray]) -> None:
post = util.intersect2d(arrays[0], arrays[1], assume_unique=False)
if post.dtype == object:
self.assertTrue(post.ndim == 1)
else:
self.assertTrue(post.ndim == 2)
self.assertTrue(
len(post) == len(
set(util.array2d_to_tuples(arrays[0]))
& set(util.array2d_to_tuples(arrays[1]))))
@given(get_arrays_2d_aligned_columns()) # type: ignore
def test_array_set_ufunc_many(self,
arrays: tp.Sequence[np.ndarray]) -> None:
for union in (True, False):
post = util.ufunc_set_iter(arrays, union=union)
if post.dtype == object:
# returned object arrays might be 2D or 1D of tuples
self.assertTrue(post.ndim in (1, 2))
else:
self.assertTrue(post.ndim == 2)
class TestUnit(TestCase):
@given(get_array_1d2d()) # type: ignore
def test_mloc(self, array: np.ndarray) -> None:
x = util.mloc(array)
self.assertTrue(isinstance(x, int))
@given(get_dtype_pairs()) # type: ignore
def test_resolve_dtype(self, dtype_pair: tp.Tuple[np.dtype, np.dtype]) -> None:
x = util.resolve_dtype(*dtype_pair)
self.assertTrue(isinstance(x, np.dtype))
@given(get_dtypes(min_size=1)) # type: ignore
def test_resolve_dtype_iter(self, dtypes: tp.Iterable[np.dtype]) -> None:
x = util.resolve_dtype_iter(dtypes)
self.assertTrue(isinstance(x, np.dtype))
@given(get_labels(min_size=1)) # type: ignore
def test_resolve_type_iter(self, objects: tp.Iterable[object]) -> None:
known_types = set((
None,
type(None),
bool,
str,
object,
int,
float,
complex,
datetime.date,
datetime.datetime,
fractions.Fraction
))
resolved, has_tuple, values_post = util.resolve_type_iter(objects)
self.assertTrue(resolved in known_types)
@given(get_arrays_2d_aligned_columns()) # type: ignore
def test_concat_resolved_axis_0(self, arrays: tp.List[np.ndarray]) -> None:
array = util.concat_resolved(arrays, axis=0)
self.assertEqual(array.ndim, 2)
self.assertEqual(array.dtype, util.resolve_dtype_iter((x.dtype for x in arrays)))
@given(get_arrays_2d_aligned_rows()) # type: ignore
def test_concat_resolved_axis_1(self, arrays: tp.List[np.ndarray]) -> None:
array = util.concat_resolved(arrays, axis=1)
self.assertEqual(array.ndim, 2)
self.assertEqual(array.dtype, util.resolve_dtype_iter((x.dtype for x in arrays)))
@given(get_dtype(), get_shape_1d2d(), get_value()) # type: ignore
def test_full_or_fill(self,
dtype: np.dtype,
shape: tp.Union[tp.Tuple[int], tp.Tuple[int, int]],
value: object) -> None:
array = util.full_for_fill(dtype, shape, fill_value=value)
self.assertTrue(array.shape == shape)
if isinstance(value, (float, complex)) and np.isnan(value):
pass
else:
self.assertTrue(value in array)
@given(get_dtype()) # type: ignore
def test_dtype_to_na(self, dtype: util.DtypeSpecifier) -> None:
post = util.dtype_to_na(dtype)
self.assertTrue(post in {0, False, None, '', np.nan, util.NAT})
@given(get_array_1d(min_size=1, dtype_group=DTGroup.NUMERIC)) # type: ignore
def test_ufunc_skipna_1d(self, array: np.ndarray) -> None:
has_na = util.isna_array(array).any()
for ufunc, ufunc_skipna, dtype in UFUNC_AXIS_SKIPNA.values():
with np.errstate(over='ignore', under='ignore'):
v1 = ufunc_skipna(array)
# this should return a single value
self.assertFalse(isinstance(v1, np.ndarray))
if has_na:
v2 = ufunc(array)
self.assertFalse(isinstance(v2, np.ndarray))
@given(get_array_1d2d()) # type: ignore
def test_ufunc_unique(self, array: np.ndarray) -> None:
post = util.ufunc_unique(array, axis=0)
self.assertTrue(len(post) <= array.shape[0])
@given(get_array_1d(min_size=1), st.integers()) # type: ignore
def test_roll_1d(self, array: np.ndarray, shift: int) -> None:
post = util.roll_1d(array, shift)
self.assertEqual(len(post), len(array))
self.assertEqualWithNaN(array[-(shift % len(array))], post[0])
@given(get_array_2d(min_rows=1, min_columns=1), st.integers()) # type: ignore
def test_roll_2d(self, array: np.ndarray, shift: int) -> None:
for axis in (0, 1):
post = util.roll_2d(array, shift=shift, axis=axis)
self.assertEqual(post.shape, array.shape)
start = -(shift % array.shape[axis])
if axis == 0:
a = array[start]
b = post[0]
else:
a = array[:, start]
b = post[:, 0]
self.assertAlmostEqualValues(a, b)
@given(get_array_1d(dtype_group=DTGroup.OBJECT)) # type: ignore
def test_iterable_to_array_a(self, array: np.ndarray) -> None:
values = array.tolist()
post, _ = util.iterable_to_array(values)
self.assertAlmostEqualValues(post, values)
# explicitly giving object dtype
post, _ = util.iterable_to_array(values, dtype=util.DTYPE_OBJECT)
self.assertAlmostEqualValues(post, values)
@given(get_labels()) # type: ignore
def test_iterable_to_array_b(self, labels: tp.Iterable[tp.Any]) -> None:
post, _ = util.iterable_to_array(labels)
self.assertAlmostEqualValues(post, labels)
self.assertTrue(isinstance(post, np.ndarray))
@given(st.slices(10)) # type: ignore
def test_slice_to_ascending_slice(self, key: slice) -> None:
post_key = util.slice_to_ascending_slice(key, size=10)
self.assertEqual(
set(range(*key.indices(10))),
set(range(*post_key.indices(10)))
)
# to_datetime64
# to_timedelta64
# key_to_datetime_key
@given(get_array_1d2d()) # type: ignore
def test_array_to_groups_and_locations(self, array: np.ndarray) -> None:
groups, locations = util.array_to_groups_and_locations(array, 0)
if len(array) > 0:
self.assertTrue(len(groups) >= 1)
# always 1dm locations
self.assertTrue(locations.ndim == 1)
self.assertTrue(len(np.unique(locations)) == len(groups))
@given(get_array_1d2d()) # type: ignore
def test_isna_array(self, array: np.ndarray) -> None:
post = util.isna_array(array)
self.assertTrue(post.dtype == bool)
values = np.ravel(array)
count_na = sum(util.isna_element(x) for x in values)
self.assertTrue(np.ravel(post).sum() == count_na)
@given(get_array_1d(dtype_group=DTGroup.BOOL)) # type: ignore
def test_binary_transition(self, array: np.ndarray) -> None:
post = util.binary_transition(array)
# could be 32 via result of np.nonzero
self.assertTrue(post.dtype in (np.int32, np.int64))
# if no True in original array, result will be empty
if array.sum() == 0:
self.assertTrue(len(post) == 0)
# if all True, result is empty
elif array.sum() == len(array):
self.assertTrue(len(post) == 0)
else:
# the post selection shold always be indices that are false
self.assertTrue(array[post].sum() == 0)
class TestUnit(TestCase):
@given(get_labels())
def test_index_values_len(self, values: tp.Sequence[tp.Hashable]) -> None:
def property_values(cls: tp.Type[Index],
values: tp.Sequence[tp.Hashable]) -> None:
#Property: that the length of the index is the length of the (unique) values.
index = cls(values)
self.assertEqual(len(index), len(values))
self.assertEqual(len(index.values), len(values))
property_values(Index, values)
property_values(IndexGO, values)
@given(get_labels())
def test_index_values_list(self, values: tp.Sequence[tp.Hashable]) -> None:
def property_values(cls: tp.Type[Index],
values: tp.Iterable[tp.Hashable]) -> None:
index = cls(values)
# must cast both sides to the dtype, as some int to float conversions result in different floats
self.assertAlmostEqualValues(
index.values, np.array(values, dtype=index.values.dtype))
property_values(Index, values)
property_values(IndexGO, values)
@given(get_labels())
def test_index_loc_to_iloc_element(
self, values: tp.Sequence[tp.Hashable]) -> None:
def property_loc_to_iloc_element(
cls: tp.Type[Index], values: tp.Iterable[tp.Hashable]) -> None:
index = cls(values)
for i, v in enumerate(values):
self.assertEqual(index._loc_to_iloc(v), i)
property_loc_to_iloc_element(Index, values)
property_loc_to_iloc_element(IndexGO, values)
@given(get_labels(min_size=1))
def test_index_loc_to_iloc_slice(self,
values: tp.Sequence[tp.Hashable]) -> None:
def property_loc_to_iloc_slice(
cls: tp.Type[Index], values: tp.Iterable[tp.Hashable]) -> None:
# Property: that the key translates to the appropriate slice.
index = cls(values)
for i, v in enumerate(values):
# insure that we get teh same slice going through loc that we would get by direct iloc
if v is None:
self.assertEqual(index._loc_to_iloc(slice(v, None)),
slice(None)) #type: ignore [unreachable]
else:
self.assertEqual(index._loc_to_iloc(slice(v, None)),
slice(i, None))
property_loc_to_iloc_slice(Index, values)
property_loc_to_iloc_slice(IndexGO, values)
@given(get_labels(min_size=2))
def test_index_go_append(self, values: tp.Sequence[tp.Hashable]) -> None:
index = IndexGO(values[:-1])
length_start = len(index)
index.append(values[-1])
length_end = len(index)
self.assertEqual(length_start + 1, length_end)
@given(get_labels(min_size=1))
def test_index_isin(self, labels: tp.Sequence[tp.Hashable]) -> None:
index = Index(labels)
self.assertTrue(index.isin((labels[0], ))[0])
#---------------------------------------------------------------------------
@given(get_index_any())
def test_index_display(self, index: Index) -> None:
d1 = index.display()
self.assertTrue(len(d1) > 0)
d2 = index.display_tall()
self.assertTrue(len(d2) > 0)
d3 = index.display_wide()
self.assertTrue(len(d3) > 0)
@given(get_index_any())
def test_index_to_series(self, index: Index) -> None:
s1 = index.to_series()
self.assertEqual(len(s1), len(index))
#---------------------------------------------------------------------------
@given(get_index_any())
def test_index_iloc_map_a(self, index: Index) -> None:
# We can't handle NaNs
if any(map(isna_element, index.values)):
return
np.random.seed(0)
ilocs = np.arange(len(index)) # Need new array, will shuffle in-place
np.random.shuffle(ilocs)
other = tp.cast(Index, index.iloc[ilocs])
expected = index.iter_label().apply(other._loc_to_iloc)
post = index._index_iloc_map(other)
self.assertEqual(post.tolist(), expected.tolist())
class TestUnit(TestCase):
@given(get_labels()) # type: ignore
def test_index_values_len(self, values: tp.Sequence[tp.Hashable]) -> None:
def property_values(cls: tp.Type[Index],
values: tp.Sequence[tp.Hashable]) -> None:
#Property: that the length of the index is the length of the (unique) values.
index = cls(values)
self.assertEqual(len(index), len(values))
self.assertEqual(len(index.values), len(values))
property_values(Index, values)
property_values(IndexGO, values)
@given(get_labels()) # type: ignore
def test_index_values_list(self, values: tp.Sequence[tp.Hashable]) -> None:
def property_values(cls: tp.Type[Index],
values: tp.Iterable[tp.Hashable]) -> None:
index = cls(values)
# must cast both sides to the dtype, as some int to float conversions result in different floats
self.assertAlmostEqualValues(
index.values, np.array(values, dtype=index.values.dtype))
property_values(Index, values)
property_values(IndexGO, values)
@given(get_labels()) # type: ignore
def test_index_loc_to_iloc_element(
self, values: tp.Sequence[tp.Hashable]) -> None:
def property_loc_to_iloc_element(
cls: tp.Type[Index], values: tp.Iterable[tp.Hashable]) -> None:
index = cls(values)
for i, v in enumerate(values):
self.assertEqual(index.loc_to_iloc(v), i)
property_loc_to_iloc_element(Index, values)
property_loc_to_iloc_element(IndexGO, values)
@given(get_labels(min_size=1)) # type: ignore
def test_index_loc_to_iloc_slice(self,
values: tp.Sequence[tp.Hashable]) -> None:
def property_loc_to_iloc_slice(
cls: tp.Type[Index], values: tp.Iterable[tp.Hashable]) -> None:
# Property: that the key translates to the appropriate slice.
index = cls(values)
for i, v in enumerate(values):
# insure that we get teh same slice going through loc that we would get by direct iloc
if v is None:
self.assertEqual(index.loc_to_iloc(slice(v, None)),
slice(None))
else:
self.assertEqual(
index.loc_to_iloc(slice(v, None)), slice(i, None)
) # type: ignore # https://github.com/python/typeshed/pull/3024
property_loc_to_iloc_slice(Index, values)
property_loc_to_iloc_slice(IndexGO, values)
@given(get_labels(min_size=2)) # type: ignore
def test_index_go_append(self, values: tp.Sequence[tp.Hashable]) -> None:
index = IndexGO(values[:-1])
length_start = len(index)
index.append(values[-1])
length_end = len(index)
self.assertEqual(length_start + 1, length_end)
@given(get_labels(min_size=1)) # type: ignore
def test_index_isin(self, labels: tp.Sequence[tp.Hashable]) -> None:
index = Index(labels)
self.assertTrue(index.isin((labels[0], ))[0])
