class TestSparseArray(object):
def setup_method(self, method):
self.arr_data = np.array([nan, nan, 1, 2, 3, nan, 4, 5, nan, 6])
self.arr = SparseArray(self.arr_data)
self.zarr = SparseArray([0, 0, 1, 2, 3, 0, 4, 5, 0, 6], fill_value=0)
def test_constructor_dtype(self):
arr = SparseArray([np.nan, 1, 2, np.nan])
assert arr.dtype == SparseDtype(np.float64, np.nan)
assert arr.dtype.subtype == np.float64
assert np.isnan(arr.fill_value)
arr = SparseArray([np.nan, 1, 2, np.nan], fill_value=0)
assert arr.dtype == SparseDtype(np.float64, 0)
assert arr.fill_value == 0
arr = SparseArray([0, 1, 2, 4], dtype=np.float64)
assert arr.dtype == SparseDtype(np.float64, np.nan)
assert np.isnan(arr.fill_value)
arr = SparseArray([0, 1, 2, 4], dtype=np.int64)
assert arr.dtype == SparseDtype(np.int64, 0)
assert arr.fill_value == 0
arr = SparseArray([0, 1, 2, 4], fill_value=0, dtype=np.int64)
assert arr.dtype == SparseDtype(np.int64, 0)
assert arr.fill_value == 0
arr = SparseArray([0, 1, 2, 4], dtype=None)
assert arr.dtype == SparseDtype(np.int64, 0)
assert arr.fill_value == 0
arr = SparseArray([0, 1, 2, 4], fill_value=0, dtype=None)
assert arr.dtype == SparseDtype(np.int64, 0)
assert arr.fill_value == 0
def test_constructor_dtype_str(self):
result = SparseArray([1, 2, 3], dtype='int')
expected = SparseArray([1, 2, 3], dtype=int)
tm.assert_sp_array_equal(result, expected)
def test_constructor_sparse_dtype(self):
result = SparseArray([1, 0, 0, 1], dtype=SparseDtype('int64', -1))
expected = SparseArray([1, 0, 0, 1], fill_value=-1, dtype=np.int64)
tm.assert_sp_array_equal(result, expected)
assert result.sp_values.dtype == np.dtype('int64')
def test_constructor_sparse_dtype_str(self):
result = SparseArray([1, 0, 0, 1], dtype='Sparse[int32]')
expected = SparseArray([1, 0, 0, 1], dtype=np.int32)
tm.assert_sp_array_equal(result, expected)
assert result.sp_values.dtype == np.dtype('int32')
def test_constructor_object_dtype(self):
# GH 11856
arr = SparseArray(['A', 'A', np.nan, 'B'], dtype=np.object)
assert arr.dtype == SparseDtype(np.object)
assert np.isnan(arr.fill_value)
arr = SparseArray(['A', 'A', np.nan, 'B'],
dtype=np.object,
fill_value='A')
assert arr.dtype == SparseDtype(np.object, 'A')
assert arr.fill_value == 'A'
# GH 17574
data = [False, 0, 100.0, 0.0]
arr = SparseArray(data, dtype=np.object, fill_value=False)
assert arr.dtype == SparseDtype(np.object, False)
assert arr.fill_value is False
arr_expected = np.array(data, dtype=np.object)
it = (type(x) == type(y) and x == y for x, y in zip(arr, arr_expected))
assert np.fromiter(it, dtype=np.bool).all()
@pytest.mark.parametrize("dtype", [SparseDtype(int, 0), int])
def test_constructor_na_dtype(self, dtype):
with pytest.raises(ValueError, match="Cannot convert"):
SparseArray([0, 1, np.nan], dtype=dtype)
def test_constructor_spindex_dtype(self):
arr = SparseArray(data=[1, 2], sparse_index=IntIndex(4, [1, 2]))
# XXX: Behavior change: specifying SparseIndex no longer changes the
# fill_value
expected = SparseArray([0, 1, 2, 0], kind='integer')
tm.assert_sp_array_equal(arr, expected)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
arr = SparseArray(data=[1, 2, 3],
sparse_index=IntIndex(4, [1, 2, 3]),
dtype=np.int64,
fill_value=0)
exp = SparseArray([0, 1, 2, 3], dtype=np.int64, fill_value=0)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
arr = SparseArray(data=[1, 2],
sparse_index=IntIndex(4, [1, 2]),
fill_value=0,
dtype=np.int64)
exp = SparseArray([0, 1, 2, 0], fill_value=0, dtype=np.int64)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
arr = SparseArray(data=[1, 2, 3],
sparse_index=IntIndex(4, [1, 2, 3]),
dtype=None,
fill_value=0)
exp = SparseArray([0, 1, 2, 3], dtype=None)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
@pytest.mark.parametrize("sparse_index", [
None,
IntIndex(1, [0]),
])
def test_constructor_spindex_dtype_scalar(self, sparse_index):
# scalar input
arr = SparseArray(data=1, sparse_index=sparse_index, dtype=None)
exp = SparseArray([1], dtype=None)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
arr = SparseArray(data=1, sparse_index=IntIndex(1, [0]), dtype=None)
exp = SparseArray([1], dtype=None)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
def test_constructor_spindex_dtype_scalar_broadcasts(self):
arr = SparseArray(data=[1, 2],
sparse_index=IntIndex(4, [1, 2]),
fill_value=0,
dtype=None)
exp = SparseArray([0, 1, 2, 0], fill_value=0, dtype=None)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
@pytest.mark.parametrize('data, fill_value', [
(np.array([1, 2]), 0),
(np.array([1.0, 2.0]), np.nan),
([True, False], False),
([pd.Timestamp('2017-01-01')], pd.NaT),
])
def test_constructor_inferred_fill_value(self, data, fill_value):
result = SparseArray(data).fill_value
if pd.isna(fill_value):
assert pd.isna(result)
else:
assert result == fill_value
@pytest.mark.parametrize('scalar,dtype',
[(False, SparseDtype(bool, False)),
(0.0, SparseDtype('float64', 0)),
(1, SparseDtype('int64', 1)),
('z', SparseDtype('object', 'z'))])
def test_scalar_with_index_infer_dtype(self, scalar, dtype):
# GH 19163
arr = SparseArray(scalar, index=[1, 2, 3], fill_value=scalar)
exp = SparseArray([scalar, scalar, scalar], fill_value=scalar)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == dtype
assert exp.dtype == dtype
@pytest.mark.parametrize("fill", [1, np.nan, 0])
def test_sparse_series_round_trip(self, kind, fill):
# see gh-13999
arr = SparseArray([np.nan, 1, np.nan, 2, 3],
kind=kind,
fill_value=fill)
res = SparseArray(SparseSeries(arr))
tm.assert_sp_array_equal(arr, res)
arr = SparseArray([0, 0, 0, 1, 1, 2],
dtype=np.int64,
kind=kind,
fill_value=fill)
res = SparseArray(SparseSeries(arr), dtype=np.int64)
tm.assert_sp_array_equal(arr, res)
res = SparseArray(SparseSeries(arr))
tm.assert_sp_array_equal(arr, res)
@pytest.mark.parametrize("fill", [True, False, np.nan])
def test_sparse_series_round_trip2(self, kind, fill):
# see gh-13999
arr = SparseArray([True, False, True, True],
dtype=np.bool,
kind=kind,
fill_value=fill)
res = SparseArray(SparseSeries(arr))
tm.assert_sp_array_equal(arr, res)
res = SparseArray(SparseSeries(arr))
tm.assert_sp_array_equal(arr, res)
def test_get_item(self):
assert np.isnan(self.arr[1])
assert self.arr[2] == 1
assert self.arr[7] == 5
assert self.zarr[0] == 0
assert self.zarr[2] == 1
assert self.zarr[7] == 5
errmsg = re.compile("bounds")
with pytest.raises(IndexError, match=errmsg):
self.arr[11]
with pytest.raises(IndexError, match=errmsg):
self.arr[-11]
assert self.arr[-1] == self.arr[len(self.arr) - 1]
def test_take_scalar_raises(self):
msg = "'indices' must be an array, not a scalar '2'."
with pytest.raises(ValueError, match=msg):
self.arr.take(2)
def test_take(self):
exp = SparseArray(np.take(self.arr_data, [2, 3]))
tm.assert_sp_array_equal(self.arr.take([2, 3]), exp)
exp = SparseArray(np.take(self.arr_data, [0, 1, 2]))
tm.assert_sp_array_equal(self.arr.take([0, 1, 2]), exp)
def test_take_fill_value(self):
data = np.array([1, np.nan, 0, 3, 0])
sparse = SparseArray(data, fill_value=0)
exp = SparseArray(np.take(data, [0]), fill_value=0)
tm.assert_sp_array_equal(sparse.take([0]), exp)
exp = SparseArray(np.take(data, [1, 3, 4]), fill_value=0)
tm.assert_sp_array_equal(sparse.take([1, 3, 4]), exp)
def test_take_negative(self):
exp = SparseArray(np.take(self.arr_data, [-1]))
tm.assert_sp_array_equal(self.arr.take([-1]), exp)
exp = SparseArray(np.take(self.arr_data, [-4, -3, -2]))
tm.assert_sp_array_equal(self.arr.take([-4, -3, -2]), exp)
def test_bad_take(self):
with pytest.raises(IndexError, match="bounds"):
self.arr.take([11])
def test_take_filling(self):
# similar tests as GH 12631
sparse = SparseArray([np.nan, np.nan, 1, np.nan, 4])
result = sparse.take(np.array([1, 0, -1]))
expected = SparseArray([np.nan, np.nan, 4])
tm.assert_sp_array_equal(result, expected)
# XXX: test change: fill_value=True -> allow_fill=True
result = sparse.take(np.array([1, 0, -1]), allow_fill=True)
expected = SparseArray([np.nan, np.nan, np.nan])
tm.assert_sp_array_equal(result, expected)
# allow_fill=False
result = sparse.take(np.array([1, 0, -1]),
allow_fill=False,
fill_value=True)
expected = SparseArray([np.nan, np.nan, 4])
tm.assert_sp_array_equal(result, expected)
msg = "Invalid value in 'indices'"
with pytest.raises(ValueError, match=msg):
sparse.take(np.array([1, 0, -2]), allow_fill=True)
with pytest.raises(ValueError, match=msg):
sparse.take(np.array([1, 0, -5]), allow_fill=True)
with pytest.raises(IndexError):
sparse.take(np.array([1, -6]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]), allow_fill=True)
def test_take_filling_fill_value(self):
# same tests as GH 12631
sparse = SparseArray([np.nan, 0, 1, 0, 4], fill_value=0)
result = sparse.take(np.array([1, 0, -1]))
expected = SparseArray([0, np.nan, 4], fill_value=0)
tm.assert_sp_array_equal(result, expected)
# fill_value
result = sparse.take(np.array([1, 0, -1]), allow_fill=True)
# XXX: behavior change.
# the old way of filling self.fill_value doesn't follow EA rules.
# It's supposed to be self.dtype.na_value (nan in this case)
expected = SparseArray([0, np.nan, np.nan], fill_value=0)
tm.assert_sp_array_equal(result, expected)
# allow_fill=False
result = sparse.take(np.array([1, 0, -1]),
allow_fill=False,
fill_value=True)
expected = SparseArray([0, np.nan, 4], fill_value=0)
tm.assert_sp_array_equal(result, expected)
msg = ("Invalid value in 'indices'.")
with pytest.raises(ValueError, match=msg):
sparse.take(np.array([1, 0, -2]), allow_fill=True)
with pytest.raises(ValueError, match=msg):
sparse.take(np.array([1, 0, -5]), allow_fill=True)
with pytest.raises(IndexError):
sparse.take(np.array([1, -6]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]), fill_value=True)
def test_take_filling_all_nan(self):
sparse = SparseArray([np.nan, np.nan, np.nan, np.nan, np.nan])
# XXX: did the default kind from take change?
result = sparse.take(np.array([1, 0, -1]))
expected = SparseArray([np.nan, np.nan, np.nan], kind='block')
tm.assert_sp_array_equal(result, expected)
result = sparse.take(np.array([1, 0, -1]), fill_value=True)
expected = SparseArray([np.nan, np.nan, np.nan], kind='block')
tm.assert_sp_array_equal(result, expected)
with pytest.raises(IndexError):
sparse.take(np.array([1, -6]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]), fill_value=True)
def test_set_item(self):
def setitem():
self.arr[5] = 3
def setslice():
self.arr[1:5] = 2
with pytest.raises(TypeError, match="item assignment"):
setitem()
with pytest.raises(TypeError, match="item assignment"):
setslice()
def test_constructor_from_too_large_array(self):
with pytest.raises(TypeError, match="expected dimension <= 1 data"):
SparseArray(np.arange(10).reshape((2, 5)))
def test_constructor_from_sparse(self):
res = SparseArray(self.zarr)
assert res.fill_value == 0
assert_almost_equal(res.sp_values, self.zarr.sp_values)
def test_constructor_copy(self):
cp = SparseArray(self.arr, copy=True)
cp.sp_values[:3] = 0
assert not (self.arr.sp_values[:3] == 0).any()
not_copy = SparseArray(self.arr)
not_copy.sp_values[:3] = 0
assert (self.arr.sp_values[:3] == 0).all()
def test_constructor_bool(self):
# GH 10648
data = np.array([False, False, True, True, False, False])
arr = SparseArray(data, fill_value=False, dtype=bool)
assert arr.dtype == SparseDtype(bool)
tm.assert_numpy_array_equal(arr.sp_values, np.array([True, True]))
# Behavior change: np.asarray densifies.
# tm.assert_numpy_array_equal(arr.sp_values, np.asarray(arr))
tm.assert_numpy_array_equal(arr.sp_index.indices,
np.array([2, 3], np.int32))
for dense in [arr.to_dense(), arr.values]:
assert dense.dtype == bool
tm.assert_numpy_array_equal(dense, data)
def test_constructor_bool_fill_value(self):
arr = SparseArray([True, False, True], dtype=None)
assert arr.dtype == SparseDtype(np.bool)
assert not arr.fill_value
arr = SparseArray([True, False, True], dtype=np.bool)
assert arr.dtype == SparseDtype(np.bool)
assert not arr.fill_value
arr = SparseArray([True, False, True], dtype=np.bool, fill_value=True)
assert arr.dtype == SparseDtype(np.bool, True)
assert arr.fill_value
def test_constructor_float32(self):
# GH 10648
data = np.array([1., np.nan, 3], dtype=np.float32)
arr = SparseArray(data, dtype=np.float32)
assert arr.dtype == SparseDtype(np.float32)
tm.assert_numpy_array_equal(arr.sp_values,
np.array([1, 3], dtype=np.float32))
# Behavior change: np.asarray densifies.
# tm.assert_numpy_array_equal(arr.sp_values, np.asarray(arr))
tm.assert_numpy_array_equal(arr.sp_index.indices,
np.array([0, 2], dtype=np.int32))
for dense in [arr.to_dense(), arr.values]:
assert dense.dtype == np.float32
tm.assert_numpy_array_equal(dense, data)
def test_astype(self):
# float -> float
arr = SparseArray([None, None, 0, 2])
result = arr.astype("Sparse[float32]")
expected = SparseArray([None, None, 0, 2], dtype=np.dtype('float32'))
tm.assert_sp_array_equal(result, expected)
dtype = SparseDtype("float64", fill_value=0)
result = arr.astype(dtype)
expected = SparseArray._simple_new(
np.array([0., 2.], dtype=dtype.subtype), IntIndex(4, [2, 3]),
dtype)
tm.assert_sp_array_equal(result, expected)
dtype = SparseDtype("int64", 0)
result = arr.astype(dtype)
expected = SparseArray._simple_new(np.array([0, 2], dtype=np.int64),
IntIndex(4, [2, 3]), dtype)
tm.assert_sp_array_equal(result, expected)
arr = SparseArray([0, np.nan, 0, 1], fill_value=0)
with pytest.raises(ValueError, match='NA'):
arr.astype('Sparse[i8]')
def test_astype_bool(self):
a = pd.SparseArray([1, 0, 0, 1], dtype=SparseDtype(int, 0))
result = a.astype(bool)
expected = SparseArray([True, 0, 0, True], dtype=SparseDtype(bool, 0))
tm.assert_sp_array_equal(result, expected)
# update fill value
result = a.astype(SparseDtype(bool, False))
expected = SparseArray([True, False, False, True],
dtype=SparseDtype(bool, False))
tm.assert_sp_array_equal(result, expected)
def test_astype_all(self, any_real_dtype):
vals = np.array([1, 2, 3])
arr = SparseArray(vals, fill_value=1)
typ = np.dtype(any_real_dtype)
res = arr.astype(typ)
assert res.dtype == SparseDtype(typ, 1)
assert res.sp_values.dtype == typ
tm.assert_numpy_array_equal(np.asarray(res.values), vals.astype(typ))
def test_set_fill_value(self):
arr = SparseArray([1., np.nan, 2.], fill_value=np.nan)
arr.fill_value = 2
assert arr.fill_value == 2
arr = SparseArray([1, 0, 2], fill_value=0, dtype=np.int64)
arr.fill_value = 2
assert arr.fill_value == 2
# XXX: this seems fine? You can construct an integer
# sparsearray with NaN fill value, why not update one?
# coerces to int
# msg = "unable to set fill_value 3\\.1 to int64 dtype"
# with pytest.raises(ValueError, match=msg):
arr.fill_value = 3.1
assert arr.fill_value == 3.1
# msg = "unable to set fill_value nan to int64 dtype"
# with pytest.raises(ValueError, match=msg):
arr.fill_value = np.nan
assert np.isnan(arr.fill_value)
arr = SparseArray([True, False, True], fill_value=False, dtype=np.bool)
arr.fill_value = True
assert arr.fill_value
# coerces to bool
# msg = "unable to set fill_value 0 to bool dtype"
# with pytest.raises(ValueError, match=msg):
arr.fill_value = 0
assert arr.fill_value == 0
# msg = "unable to set fill_value nan to bool dtype"
# with pytest.raises(ValueError, match=msg):
arr.fill_value = np.nan
assert np.isnan(arr.fill_value)
@pytest.mark.parametrize("val", [[1, 2, 3], np.array([1, 2]), (1, 2, 3)])
def test_set_fill_invalid_non_scalar(self, val):
arr = SparseArray([True, False, True], fill_value=False, dtype=np.bool)
msg = "fill_value must be a scalar"
with pytest.raises(ValueError, match=msg):
arr.fill_value = val
def test_copy_shallow(self):
arr2 = self.arr.copy(deep=False)
assert arr2.sp_values is self.arr.sp_values
assert arr2.sp_index is self.arr.sp_index
def test_values_asarray(self):
assert_almost_equal(self.arr.values, self.arr_data)
assert_almost_equal(self.arr.to_dense(), self.arr_data)
@pytest.mark.parametrize('data,shape,dtype',
[([0, 0, 0, 0, 0], (5, ), None),
([], (0, ), None), ([0], (1, ), None),
(['A', 'A', np.nan, 'B'], (4, ), np.object)])
def test_shape(self, data, shape, dtype):
# GH 21126
out = SparseArray(data, dtype=dtype)
assert out.shape == shape
@pytest.mark.parametrize("vals", [
[np.nan, np.nan, np.nan, np.nan, np.nan],
[1, np.nan, np.nan, 3, np.nan],
[1, np.nan, 0, 3, 0],
])
@pytest.mark.parametrize("method", ["to_dense", "get_values"])
@pytest.mark.parametrize("fill_value", [None, 0])
def test_dense_repr(self, vals, fill_value, method):
vals = np.array(vals)
arr = SparseArray(vals, fill_value=fill_value)
dense_func = getattr(arr, method)
res = dense_func()
tm.assert_numpy_array_equal(res, vals)
def test_getitem(self):
def _checkit(i):
assert_almost_equal(self.arr[i], self.arr.values[i])
for i in range(len(self.arr)):
_checkit(i)
_checkit(-i)
def test_getitem_arraylike_mask(self):
arr = SparseArray([0, 1, 2])
result = arr[[True, False, True]]
expected = SparseArray([0, 2])
tm.assert_sp_array_equal(result, expected)
def test_getslice(self):
result = self.arr[:-3]
exp = SparseArray(self.arr.values[:-3])
tm.assert_sp_array_equal(result, exp)
result = self.arr[-4:]
exp = SparseArray(self.arr.values[-4:])
tm.assert_sp_array_equal(result, exp)
# two corner cases from Series
result = self.arr[-12:]
exp = SparseArray(self.arr)
tm.assert_sp_array_equal(result, exp)
result = self.arr[:-12]
exp = SparseArray(self.arr.values[:0])
tm.assert_sp_array_equal(result, exp)
def test_getslice_tuple(self):
dense = np.array([np.nan, 0, 3, 4, 0, 5, np.nan, np.nan, 0])
sparse = SparseArray(dense)
res = sparse[4:, ]
exp = SparseArray(dense[4:, ])
tm.assert_sp_array_equal(res, exp)
sparse = SparseArray(dense, fill_value=0)
res = sparse[4:, ]
exp = SparseArray(dense[4:, ], fill_value=0)
tm.assert_sp_array_equal(res, exp)
with pytest.raises(IndexError):
sparse[4:, :]
with pytest.raises(IndexError):
# check numpy compat
dense[4:, :]
def test_boolean_slice_empty(self):
arr = pd.SparseArray([0, 1, 2])
res = arr[[False, False, False]]
assert res.dtype == arr.dtype
@pytest.mark.parametrize(
"op", ["add", "sub", "mul", "truediv", "floordiv", "pow"])
def test_binary_operators(self, op):
op = getattr(operator, op)
data1 = np.random.randn(20)
data2 = np.random.randn(20)
data1[::2] = np.nan
data2[::3] = np.nan
arr1 = SparseArray(data1)
arr2 = SparseArray(data2)
data1[::2] = 3
data2[::3] = 3
farr1 = SparseArray(data1, fill_value=3)
farr2 = SparseArray(data2, fill_value=3)
def _check_op(op, first, second):
res = op(first, second)
exp = SparseArray(op(first.values, second.values),
fill_value=first.fill_value)
assert isinstance(res, SparseArray)
assert_almost_equal(res.values, exp.values)
res2 = op(first, second.values)
assert isinstance(res2, SparseArray)
tm.assert_sp_array_equal(res, res2)
res3 = op(first.values, second)
assert isinstance(res3, SparseArray)
tm.assert_sp_array_equal(res, res3)
res4 = op(first, 4)
assert isinstance(res4, SparseArray)
# Ignore this if the actual op raises (e.g. pow).
try:
exp = op(first.values, 4)
exp_fv = op(first.fill_value, 4)
except ValueError:
pass
else:
assert_almost_equal(res4.fill_value, exp_fv)
assert_almost_equal(res4.values, exp)
with np.errstate(all="ignore"):
for first_arr, second_arr in [(arr1, arr2), (farr1, farr2)]:
_check_op(op, first_arr, second_arr)
def test_pickle(self):
def _check_roundtrip(obj):
unpickled = tm.round_trip_pickle(obj)
tm.assert_sp_array_equal(unpickled, obj)
_check_roundtrip(self.arr)
_check_roundtrip(self.zarr)
def test_generator_warnings(self):
sp_arr = SparseArray([1, 2, 3])
with warnings.catch_warnings(record=True) as w:
warnings.filterwarnings(action='always',
category=DeprecationWarning)
warnings.filterwarnings(action='always',
category=PendingDeprecationWarning)
for _ in sp_arr:
pass
assert len(w) == 0
def test_fillna(self):
s = SparseArray([1, np.nan, np.nan, 3, np.nan])
res = s.fillna(-1)
exp = SparseArray([1, -1, -1, 3, -1], fill_value=-1, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([1, np.nan, np.nan, 3, np.nan], fill_value=0)
res = s.fillna(-1)
exp = SparseArray([1, -1, -1, 3, -1], fill_value=0, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([1, np.nan, 0, 3, 0])
res = s.fillna(-1)
exp = SparseArray([1, -1, 0, 3, 0], fill_value=-1, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([1, np.nan, 0, 3, 0], fill_value=0)
res = s.fillna(-1)
exp = SparseArray([1, -1, 0, 3, 0], fill_value=0, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([np.nan, np.nan, np.nan, np.nan])
res = s.fillna(-1)
exp = SparseArray([-1, -1, -1, -1], fill_value=-1, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([np.nan, np.nan, np.nan, np.nan], fill_value=0)
res = s.fillna(-1)
exp = SparseArray([-1, -1, -1, -1], fill_value=0, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
# float dtype's fill_value is np.nan, replaced by -1
s = SparseArray([0., 0., 0., 0.])
res = s.fillna(-1)
exp = SparseArray([0., 0., 0., 0.], fill_value=-1)
tm.assert_sp_array_equal(res, exp)
# int dtype shouldn't have missing. No changes.
s = SparseArray([0, 0, 0, 0])
assert s.dtype == SparseDtype(np.int64)
assert s.fill_value == 0
res = s.fillna(-1)
tm.assert_sp_array_equal(res, s)
s = SparseArray([0, 0, 0, 0], fill_value=0)
assert s.dtype == SparseDtype(np.int64)
assert s.fill_value == 0
res = s.fillna(-1)
exp = SparseArray([0, 0, 0, 0], fill_value=0)
tm.assert_sp_array_equal(res, exp)
# fill_value can be nan if there is no missing hole.
# only fill_value will be changed
s = SparseArray([0, 0, 0, 0], fill_value=np.nan)
assert s.dtype == SparseDtype(np.int64, fill_value=np.nan)
assert np.isnan(s.fill_value)
res = s.fillna(-1)
exp = SparseArray([0, 0, 0, 0], fill_value=-1)
tm.assert_sp_array_equal(res, exp)
def test_fillna_overlap(self):
s = SparseArray([1, np.nan, np.nan, 3, np.nan])
# filling with existing value doesn't replace existing value with
# fill_value, i.e. existing 3 remains in sp_values
res = s.fillna(3)
exp = np.array([1, 3, 3, 3, 3], dtype=np.float64)
tm.assert_numpy_array_equal(res.to_dense(), exp)
s = SparseArray([1, np.nan, np.nan, 3, np.nan], fill_value=0)
res = s.fillna(3)
exp = SparseArray([1, 3, 3, 3, 3], fill_value=0, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
class TestSparseArray(object):
def setup_method(self, method):
self.arr_data = np.array([nan, nan, 1, 2, 3, nan, 4, 5, nan, 6])
self.arr = SparseArray(self.arr_data)
self.zarr = SparseArray([0, 0, 1, 2, 3, 0, 4, 5, 0, 6], fill_value=0)
def test_constructor_dtype(self):
arr = SparseArray([np.nan, 1, 2, np.nan])
assert arr.dtype == np.float64
assert np.isnan(arr.fill_value)
arr = SparseArray([np.nan, 1, 2, np.nan], fill_value=0)
assert arr.dtype == np.float64
assert arr.fill_value == 0
arr = SparseArray([0, 1, 2, 4], dtype=np.float64)
assert arr.dtype == np.float64
assert np.isnan(arr.fill_value)
arr = SparseArray([0, 1, 2, 4], dtype=np.int64)
assert arr.dtype == np.int64
assert arr.fill_value == 0
arr = SparseArray([0, 1, 2, 4], fill_value=0, dtype=np.int64)
assert arr.dtype == np.int64
assert arr.fill_value == 0
arr = SparseArray([0, 1, 2, 4], dtype=None)
assert arr.dtype == np.int64
assert arr.fill_value == 0
arr = SparseArray([0, 1, 2, 4], fill_value=0, dtype=None)
assert arr.dtype == np.int64
assert arr.fill_value == 0
def test_constructor_object_dtype(self):
# GH 11856
arr = SparseArray(['A', 'A', np.nan, 'B'], dtype=np.object)
assert arr.dtype == np.object
assert np.isnan(arr.fill_value)
arr = SparseArray(['A', 'A', np.nan, 'B'], dtype=np.object,
fill_value='A')
assert arr.dtype == np.object
assert arr.fill_value == 'A'
# GH 17574
data = [False, 0, 100.0, 0.0]
arr = SparseArray(data, dtype=np.object, fill_value=False)
assert arr.dtype == np.object
assert arr.fill_value is False
arr_expected = np.array(data, dtype=np.object)
it = (type(x) == type(y) and x == y for x, y in zip(arr, arr_expected))
assert np.fromiter(it, dtype=np.bool).all()
def test_constructor_spindex_dtype(self):
arr = SparseArray(data=[1, 2], sparse_index=IntIndex(4, [1, 2]))
tm.assert_sp_array_equal(arr, SparseArray([np.nan, 1, 2, np.nan]))
assert arr.dtype == np.float64
assert np.isnan(arr.fill_value)
arr = SparseArray(data=[1, 2, 3],
sparse_index=IntIndex(4, [1, 2, 3]),
dtype=np.int64, fill_value=0)
exp = SparseArray([0, 1, 2, 3], dtype=np.int64, fill_value=0)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == np.int64
assert arr.fill_value == 0
arr = SparseArray(data=[1, 2], sparse_index=IntIndex(4, [1, 2]),
fill_value=0, dtype=np.int64)
exp = SparseArray([0, 1, 2, 0], fill_value=0, dtype=np.int64)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == np.int64
assert arr.fill_value == 0
arr = SparseArray(data=[1, 2, 3],
sparse_index=IntIndex(4, [1, 2, 3]),
dtype=None, fill_value=0)
exp = SparseArray([0, 1, 2, 3], dtype=None)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == np.int64
assert arr.fill_value == 0
# scalar input
arr = SparseArray(data=1, sparse_index=IntIndex(1, [0]), dtype=None)
exp = SparseArray([1], dtype=None)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == np.int64
assert arr.fill_value == 0
arr = SparseArray(data=[1, 2], sparse_index=IntIndex(4, [1, 2]),
fill_value=0, dtype=None)
exp = SparseArray([0, 1, 2, 0], fill_value=0, dtype=None)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == np.int64
assert arr.fill_value == 0
@pytest.mark.parametrize('scalar,dtype', [
(False, bool),
(0.0, 'float64'),
(1, 'int64'),
('z', 'object')])
def test_scalar_with_index_infer_dtype(self, scalar, dtype):
# GH 19163
arr = SparseArray(scalar, index=[1, 2, 3], fill_value=scalar)
exp = SparseArray([scalar, scalar, scalar], fill_value=scalar)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == dtype
assert exp.dtype == dtype
def test_sparseseries_roundtrip(self):
# GH 13999
for kind in ['integer', 'block']:
for fill in [1, np.nan, 0]:
arr = SparseArray([np.nan, 1, np.nan, 2, 3], kind=kind,
fill_value=fill)
res = SparseArray(SparseSeries(arr))
tm.assert_sp_array_equal(arr, res)
arr = SparseArray([0, 0, 0, 1, 1, 2], dtype=np.int64,
kind=kind, fill_value=fill)
res = SparseArray(SparseSeries(arr), dtype=np.int64)
tm.assert_sp_array_equal(arr, res)
res = SparseArray(SparseSeries(arr))
tm.assert_sp_array_equal(arr, res)
for fill in [True, False, np.nan]:
arr = SparseArray([True, False, True, True], dtype=np.bool,
kind=kind, fill_value=fill)
res = SparseArray(SparseSeries(arr))
tm.assert_sp_array_equal(arr, res)
res = SparseArray(SparseSeries(arr))
tm.assert_sp_array_equal(arr, res)
def test_get_item(self):
assert np.isnan(self.arr[1])
assert self.arr[2] == 1
assert self.arr[7] == 5
assert self.zarr[0] == 0
assert self.zarr[2] == 1
assert self.zarr[7] == 5
errmsg = re.compile("bounds")
tm.assert_raises_regex(IndexError, errmsg, lambda: self.arr[11])
tm.assert_raises_regex(IndexError, errmsg, lambda: self.arr[-11])
assert self.arr[-1] == self.arr[len(self.arr) - 1]
def test_take(self):
assert np.isnan(self.arr.take(0))
assert np.isscalar(self.arr.take(2))
assert self.arr.take(2) == np.take(self.arr_data, 2)
assert self.arr.take(6) == np.take(self.arr_data, 6)
exp = SparseArray(np.take(self.arr_data, [2, 3]))
tm.assert_sp_array_equal(self.arr.take([2, 3]), exp)
exp = SparseArray(np.take(self.arr_data, [0, 1, 2]))
tm.assert_sp_array_equal(self.arr.take([0, 1, 2]), exp)
def test_take_fill_value(self):
data = np.array([1, np.nan, 0, 3, 0])
sparse = SparseArray(data, fill_value=0)
exp = SparseArray(np.take(data, [0]), fill_value=0)
tm.assert_sp_array_equal(sparse.take([0]), exp)
exp = SparseArray(np.take(data, [1, 3, 4]), fill_value=0)
tm.assert_sp_array_equal(sparse.take([1, 3, 4]), exp)
def test_take_negative(self):
exp = SparseArray(np.take(self.arr_data, [-1]))
tm.assert_sp_array_equal(self.arr.take([-1]), exp)
exp = SparseArray(np.take(self.arr_data, [-4, -3, -2]))
tm.assert_sp_array_equal(self.arr.take([-4, -3, -2]), exp)
def test_bad_take(self):
tm.assert_raises_regex(
IndexError, "bounds", lambda: self.arr.take(11))
pytest.raises(IndexError, lambda: self.arr.take(-11))
def test_take_invalid_kwargs(self):
msg = r"take\(\) got an unexpected keyword argument 'foo'"
tm.assert_raises_regex(TypeError, msg, self.arr.take,
[2, 3], foo=2)
msg = "the 'out' parameter is not supported"
tm.assert_raises_regex(ValueError, msg, self.arr.take,
[2, 3], out=self.arr)
msg = "the 'mode' parameter is not supported"
tm.assert_raises_regex(ValueError, msg, self.arr.take,
[2, 3], mode='clip')
def test_take_filling(self):
# similar tests as GH 12631
sparse = SparseArray([np.nan, np.nan, 1, np.nan, 4])
result = sparse.take(np.array([1, 0, -1]))
expected = SparseArray([np.nan, np.nan, 4])
tm.assert_sp_array_equal(result, expected)
# fill_value
result = sparse.take(np.array([1, 0, -1]), fill_value=True)
expected = SparseArray([np.nan, np.nan, np.nan])
tm.assert_sp_array_equal(result, expected)
# allow_fill=False
result = sparse.take(np.array([1, 0, -1]),
allow_fill=False, fill_value=True)
expected = SparseArray([np.nan, np.nan, 4])
tm.assert_sp_array_equal(result, expected)
msg = ('When allow_fill=True and fill_value is not None, '
'all indices must be >= -1')
with tm.assert_raises_regex(ValueError, msg):
sparse.take(np.array([1, 0, -2]), fill_value=True)
with tm.assert_raises_regex(ValueError, msg):
sparse.take(np.array([1, 0, -5]), fill_value=True)
with pytest.raises(IndexError):
sparse.take(np.array([1, -6]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]), fill_value=True)
def test_take_filling_fill_value(self):
# same tests as GH 12631
sparse = SparseArray([np.nan, 0, 1, 0, 4], fill_value=0)
result = sparse.take(np.array([1, 0, -1]))
expected = SparseArray([0, np.nan, 4], fill_value=0)
tm.assert_sp_array_equal(result, expected)
# fill_value
result = sparse.take(np.array([1, 0, -1]), fill_value=True)
expected = SparseArray([0, np.nan, 0], fill_value=0)
tm.assert_sp_array_equal(result, expected)
# allow_fill=False
result = sparse.take(np.array([1, 0, -1]),
allow_fill=False, fill_value=True)
expected = SparseArray([0, np.nan, 4], fill_value=0)
tm.assert_sp_array_equal(result, expected)
msg = ('When allow_fill=True and fill_value is not None, '
'all indices must be >= -1')
with tm.assert_raises_regex(ValueError, msg):
sparse.take(np.array([1, 0, -2]), fill_value=True)
with tm.assert_raises_regex(ValueError, msg):
sparse.take(np.array([1, 0, -5]), fill_value=True)
with pytest.raises(IndexError):
sparse.take(np.array([1, -6]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]), fill_value=True)
def test_take_filling_all_nan(self):
sparse = SparseArray([np.nan, np.nan, np.nan, np.nan, np.nan])
result = sparse.take(np.array([1, 0, -1]))
expected = SparseArray([np.nan, np.nan, np.nan])
tm.assert_sp_array_equal(result, expected)
result = sparse.take(np.array([1, 0, -1]), fill_value=True)
expected = SparseArray([np.nan, np.nan, np.nan])
tm.assert_sp_array_equal(result, expected)
with pytest.raises(IndexError):
sparse.take(np.array([1, -6]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]), fill_value=True)
def test_set_item(self):
def setitem():
self.arr[5] = 3
def setslice():
self.arr[1:5] = 2
tm.assert_raises_regex(TypeError, "item assignment", setitem)
tm.assert_raises_regex(TypeError, "item assignment", setslice)
def test_constructor_from_too_large_array(self):
tm.assert_raises_regex(TypeError, "expected dimension <= 1 data",
SparseArray, np.arange(10).reshape((2, 5)))
def test_constructor_from_sparse(self):
res = SparseArray(self.zarr)
assert res.fill_value == 0
assert_almost_equal(res.sp_values, self.zarr.sp_values)
def test_constructor_copy(self):
cp = SparseArray(self.arr, copy=True)
cp.sp_values[:3] = 0
assert not (self.arr.sp_values[:3] == 0).any()
not_copy = SparseArray(self.arr)
not_copy.sp_values[:3] = 0
assert (self.arr.sp_values[:3] == 0).all()
def test_constructor_bool(self):
# GH 10648
data = np.array([False, False, True, True, False, False])
arr = SparseArray(data, fill_value=False, dtype=bool)
assert arr.dtype == bool
tm.assert_numpy_array_equal(arr.sp_values, np.array([True, True]))
tm.assert_numpy_array_equal(arr.sp_values, np.asarray(arr))
tm.assert_numpy_array_equal(arr.sp_index.indices,
np.array([2, 3], np.int32))
for dense in [arr.to_dense(), arr.values]:
assert dense.dtype == bool
tm.assert_numpy_array_equal(dense, data)
def test_constructor_bool_fill_value(self):
arr = SparseArray([True, False, True], dtype=None)
assert arr.dtype == np.bool
assert not arr.fill_value
arr = SparseArray([True, False, True], dtype=np.bool)
assert arr.dtype == np.bool
assert not arr.fill_value
arr = SparseArray([True, False, True], dtype=np.bool, fill_value=True)
assert arr.dtype == np.bool
assert arr.fill_value
def test_constructor_float32(self):
# GH 10648
data = np.array([1., np.nan, 3], dtype=np.float32)
arr = SparseArray(data, dtype=np.float32)
assert arr.dtype == np.float32
tm.assert_numpy_array_equal(arr.sp_values,
np.array([1, 3], dtype=np.float32))
tm.assert_numpy_array_equal(arr.sp_values, np.asarray(arr))
tm.assert_numpy_array_equal(arr.sp_index.indices,
np.array([0, 2], dtype=np.int32))
for dense in [arr.to_dense(), arr.values]:
assert dense.dtype == np.float32
tm.assert_numpy_array_equal(dense, data)
def test_astype(self):
res = self.arr.astype('f8')
res.sp_values[:3] = 27
assert not (self.arr.sp_values[:3] == 27).any()
msg = "unable to coerce current fill_value nan to int64 dtype"
with tm.assert_raises_regex(ValueError, msg):
self.arr.astype('i8')
arr = SparseArray([0, np.nan, 0, 1])
with tm.assert_raises_regex(ValueError, msg):
arr.astype('i8')
arr = SparseArray([0, np.nan, 0, 1], fill_value=0)
msg = 'Cannot convert non-finite values \\(NA or inf\\) to integer'
with tm.assert_raises_regex(ValueError, msg):
arr.astype('i8')
def test_astype_all(self):
vals = np.array([1, 2, 3])
arr = SparseArray(vals, fill_value=1)
types = [np.float64, np.float32, np.int64,
np.int32, np.int16, np.int8]
for typ in types:
res = arr.astype(typ)
assert res.dtype == typ
assert res.sp_values.dtype == typ
tm.assert_numpy_array_equal(res.values, vals.astype(typ))
def test_set_fill_value(self):
arr = SparseArray([1., np.nan, 2.], fill_value=np.nan)
arr.fill_value = 2
assert arr.fill_value == 2
arr = SparseArray([1, 0, 2], fill_value=0, dtype=np.int64)
arr.fill_value = 2
assert arr.fill_value == 2
# coerces to int
msg = "unable to set fill_value 3\\.1 to int64 dtype"
with tm.assert_raises_regex(ValueError, msg):
arr.fill_value = 3.1
msg = "unable to set fill_value nan to int64 dtype"
with tm.assert_raises_regex(ValueError, msg):
arr.fill_value = np.nan
arr = SparseArray([True, False, True], fill_value=False, dtype=np.bool)
arr.fill_value = True
assert arr.fill_value
# coerces to bool
msg = "unable to set fill_value 0 to bool dtype"
with tm.assert_raises_regex(ValueError, msg):
arr.fill_value = 0
msg = "unable to set fill_value nan to bool dtype"
with tm.assert_raises_regex(ValueError, msg):
arr.fill_value = np.nan
# invalid
msg = "fill_value must be a scalar"
for val in [[1, 2, 3], np.array([1, 2]), (1, 2, 3)]:
with tm.assert_raises_regex(ValueError, msg):
arr.fill_value = val
def test_copy_shallow(self):
arr2 = self.arr.copy(deep=False)
def _get_base(values):
base = values.base
while base.base is not None:
base = base.base
return base
assert (_get_base(arr2) is _get_base(self.arr))
def test_values_asarray(self):
assert_almost_equal(self.arr.values, self.arr_data)
assert_almost_equal(self.arr.to_dense(), self.arr_data)
assert_almost_equal(self.arr.sp_values, np.asarray(self.arr))
def test_to_dense(self):
vals = np.array([1, np.nan, np.nan, 3, np.nan])
res = SparseArray(vals).to_dense()
tm.assert_numpy_array_equal(res, vals)
res = SparseArray(vals, fill_value=0).to_dense()
tm.assert_numpy_array_equal(res, vals)
vals = np.array([1, np.nan, 0, 3, 0])
res = SparseArray(vals).to_dense()
tm.assert_numpy_array_equal(res, vals)
res = SparseArray(vals, fill_value=0).to_dense()
tm.assert_numpy_array_equal(res, vals)
vals = np.array([np.nan, np.nan, np.nan, np.nan, np.nan])
res = SparseArray(vals).to_dense()
tm.assert_numpy_array_equal(res, vals)
res = SparseArray(vals, fill_value=0).to_dense()
tm.assert_numpy_array_equal(res, vals)
# see gh-14647
with tm.assert_produces_warning(FutureWarning,
check_stacklevel=False):
SparseArray(vals).to_dense(fill=2)
def test_getitem(self):
def _checkit(i):
assert_almost_equal(self.arr[i], self.arr.values[i])
for i in range(len(self.arr)):
_checkit(i)
_checkit(-i)
def test_getslice(self):
result = self.arr[:-3]
exp = SparseArray(self.arr.values[:-3])
tm.assert_sp_array_equal(result, exp)
result = self.arr[-4:]
exp = SparseArray(self.arr.values[-4:])
tm.assert_sp_array_equal(result, exp)
# two corner cases from Series
result = self.arr[-12:]
exp = SparseArray(self.arr)
tm.assert_sp_array_equal(result, exp)
result = self.arr[:-12]
exp = SparseArray(self.arr.values[:0])
tm.assert_sp_array_equal(result, exp)
def test_getslice_tuple(self):
dense = np.array([np.nan, 0, 3, 4, 0, 5, np.nan, np.nan, 0])
sparse = SparseArray(dense)
res = sparse[4:, ]
exp = SparseArray(dense[4:, ])
tm.assert_sp_array_equal(res, exp)
sparse = SparseArray(dense, fill_value=0)
res = sparse[4:, ]
exp = SparseArray(dense[4:, ], fill_value=0)
tm.assert_sp_array_equal(res, exp)
with pytest.raises(IndexError):
sparse[4:, :]
with pytest.raises(IndexError):
# check numpy compat
dense[4:, :]
def test_binary_operators(self):
data1 = np.random.randn(20)
data2 = np.random.randn(20)
data1[::2] = np.nan
data2[::3] = np.nan
arr1 = SparseArray(data1)
arr2 = SparseArray(data2)
data1[::2] = 3
data2[::3] = 3
farr1 = SparseArray(data1, fill_value=3)
farr2 = SparseArray(data2, fill_value=3)
def _check_op(op, first, second):
res = op(first, second)
exp = SparseArray(op(first.values, second.values),
fill_value=first.fill_value)
assert isinstance(res, SparseArray)
assert_almost_equal(res.values, exp.values)
res2 = op(first, second.values)
assert isinstance(res2, SparseArray)
tm.assert_sp_array_equal(res, res2)
res3 = op(first.values, second)
assert isinstance(res3, SparseArray)
tm.assert_sp_array_equal(res, res3)
res4 = op(first, 4)
assert isinstance(res4, SparseArray)
# ignore this if the actual op raises (e.g. pow)
try:
exp = op(first.values, 4)
exp_fv = op(first.fill_value, 4)
assert_almost_equal(res4.fill_value, exp_fv)
assert_almost_equal(res4.values, exp)
except ValueError:
pass
def _check_inplace_op(op):
tmp = arr1.copy()
pytest.raises(NotImplementedError, op, tmp, arr2)
with np.errstate(all='ignore'):
bin_ops = [operator.add, operator.sub, operator.mul,
operator.truediv, operator.floordiv, operator.pow]
for op in bin_ops:
_check_op(op, arr1, arr2)
_check_op(op, farr1, farr2)
inplace_ops = ['iadd', 'isub', 'imul', 'itruediv', 'ifloordiv',
'ipow']
for op in inplace_ops:
_check_inplace_op(getattr(operator, op))
def test_pickle(self):
def _check_roundtrip(obj):
unpickled = tm.round_trip_pickle(obj)
tm.assert_sp_array_equal(unpickled, obj)
_check_roundtrip(self.arr)
_check_roundtrip(self.zarr)
def test_generator_warnings(self):
sp_arr = SparseArray([1, 2, 3])
with warnings.catch_warnings(record=True) as w:
warnings.filterwarnings(action='always',
category=DeprecationWarning)
warnings.filterwarnings(action='always',
category=PendingDeprecationWarning)
for _ in sp_arr:
pass
assert len(w) == 0
def test_fillna(self):
s = SparseArray([1, np.nan, np.nan, 3, np.nan])
res = s.fillna(-1)
exp = SparseArray([1, -1, -1, 3, -1], fill_value=-1, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([1, np.nan, np.nan, 3, np.nan], fill_value=0)
res = s.fillna(-1)
exp = SparseArray([1, -1, -1, 3, -1], fill_value=0, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([1, np.nan, 0, 3, 0])
res = s.fillna(-1)
exp = SparseArray([1, -1, 0, 3, 0], fill_value=-1, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([1, np.nan, 0, 3, 0], fill_value=0)
res = s.fillna(-1)
exp = SparseArray([1, -1, 0, 3, 0], fill_value=0, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([np.nan, np.nan, np.nan, np.nan])
res = s.fillna(-1)
exp = SparseArray([-1, -1, -1, -1], fill_value=-1, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([np.nan, np.nan, np.nan, np.nan], fill_value=0)
res = s.fillna(-1)
exp = SparseArray([-1, -1, -1, -1], fill_value=0, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
# float dtype's fill_value is np.nan, replaced by -1
s = SparseArray([0., 0., 0., 0.])
res = s.fillna(-1)
exp = SparseArray([0., 0., 0., 0.], fill_value=-1)
tm.assert_sp_array_equal(res, exp)
# int dtype shouldn't have missing. No changes.
s = SparseArray([0, 0, 0, 0])
assert s.dtype == np.int64
assert s.fill_value == 0
res = s.fillna(-1)
tm.assert_sp_array_equal(res, s)
s = SparseArray([0, 0, 0, 0], fill_value=0)
assert s.dtype == np.int64
assert s.fill_value == 0
res = s.fillna(-1)
exp = SparseArray([0, 0, 0, 0], fill_value=0)
tm.assert_sp_array_equal(res, exp)
# fill_value can be nan if there is no missing hole.
# only fill_value will be changed
s = SparseArray([0, 0, 0, 0], fill_value=np.nan)
assert s.dtype == np.int64
assert np.isnan(s.fill_value)
res = s.fillna(-1)
exp = SparseArray([0, 0, 0, 0], fill_value=-1)
tm.assert_sp_array_equal(res, exp)
def test_fillna_overlap(self):
s = SparseArray([1, np.nan, np.nan, 3, np.nan])
# filling with existing value doesn't replace existing value with
# fill_value, i.e. existing 3 remains in sp_values
res = s.fillna(3)
exp = np.array([1, 3, 3, 3, 3], dtype=np.float64)
tm.assert_numpy_array_equal(res.to_dense(), exp)
s = SparseArray([1, np.nan, np.nan, 3, np.nan], fill_value=0)
res = s.fillna(3)
exp = SparseArray([1, 3, 3, 3, 3], fill_value=0, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
class TestSparseArray(object):
def setup_method(self, method):
self.arr_data = np.array([nan, nan, 1, 2, 3, nan, 4, 5, nan, 6])
self.arr = SparseArray(self.arr_data)
self.zarr = SparseArray([0, 0, 1, 2, 3, 0, 4, 5, 0, 6], fill_value=0)
def test_constructor_dtype(self):
arr = SparseArray([np.nan, 1, 2, np.nan])
assert arr.dtype == SparseDtype(np.float64, np.nan)
assert arr.dtype.subtype == np.float64
assert np.isnan(arr.fill_value)
arr = SparseArray([np.nan, 1, 2, np.nan], fill_value=0)
assert arr.dtype == SparseDtype(np.float64, 0)
assert arr.fill_value == 0
arr = SparseArray([0, 1, 2, 4], dtype=np.float64)
assert arr.dtype == SparseDtype(np.float64, np.nan)
assert np.isnan(arr.fill_value)
arr = SparseArray([0, 1, 2, 4], dtype=np.int64)
assert arr.dtype == SparseDtype(np.int64, 0)
assert arr.fill_value == 0
arr = SparseArray([0, 1, 2, 4], fill_value=0, dtype=np.int64)
assert arr.dtype == SparseDtype(np.int64, 0)
assert arr.fill_value == 0
arr = SparseArray([0, 1, 2, 4], dtype=None)
assert arr.dtype == SparseDtype(np.int64, 0)
assert arr.fill_value == 0
arr = SparseArray([0, 1, 2, 4], fill_value=0, dtype=None)
assert arr.dtype == SparseDtype(np.int64, 0)
assert arr.fill_value == 0
def test_constructor_dtype_str(self):
result = SparseArray([1, 2, 3], dtype='int')
expected = SparseArray([1, 2, 3], dtype=int)
tm.assert_sp_array_equal(result, expected)
def test_constructor_sparse_dtype(self):
result = SparseArray([1, 0, 0, 1], dtype=SparseDtype('int64', -1))
expected = SparseArray([1, 0, 0, 1], fill_value=-1, dtype=np.int64)
tm.assert_sp_array_equal(result, expected)
assert result.sp_values.dtype == np.dtype('int64')
def test_constructor_sparse_dtype_str(self):
result = SparseArray([1, 0, 0, 1], dtype='Sparse[int32]')
expected = SparseArray([1, 0, 0, 1], dtype=np.int32)
tm.assert_sp_array_equal(result, expected)
assert result.sp_values.dtype == np.dtype('int32')
def test_constructor_object_dtype(self):
# GH 11856
arr = SparseArray(['A', 'A', np.nan, 'B'], dtype=np.object)
assert arr.dtype == SparseDtype(np.object)
assert np.isnan(arr.fill_value)
arr = SparseArray(['A', 'A', np.nan, 'B'], dtype=np.object,
fill_value='A')
assert arr.dtype == SparseDtype(np.object, 'A')
assert arr.fill_value == 'A'
# GH 17574
data = [False, 0, 100.0, 0.0]
arr = SparseArray(data, dtype=np.object, fill_value=False)
assert arr.dtype == SparseDtype(np.object, False)
assert arr.fill_value is False
arr_expected = np.array(data, dtype=np.object)
it = (type(x) == type(y) and x == y for x, y in zip(arr, arr_expected))
assert np.fromiter(it, dtype=np.bool).all()
@pytest.mark.parametrize("dtype", [SparseDtype(int, 0), int])
def test_constructor_na_dtype(self, dtype):
with tm.assert_raises_regex(ValueError, "Cannot convert"):
SparseArray([0, 1, np.nan], dtype=dtype)
def test_constructor_spindex_dtype(self):
arr = SparseArray(data=[1, 2], sparse_index=IntIndex(4, [1, 2]))
# XXX: Behavior change: specifying SparseIndex no longer changes the
# fill_value
expected = SparseArray([0, 1, 2, 0], kind='integer')
tm.assert_sp_array_equal(arr, expected)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
arr = SparseArray(data=[1, 2, 3],
sparse_index=IntIndex(4, [1, 2, 3]),
dtype=np.int64, fill_value=0)
exp = SparseArray([0, 1, 2, 3], dtype=np.int64, fill_value=0)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
arr = SparseArray(data=[1, 2], sparse_index=IntIndex(4, [1, 2]),
fill_value=0, dtype=np.int64)
exp = SparseArray([0, 1, 2, 0], fill_value=0, dtype=np.int64)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
arr = SparseArray(data=[1, 2, 3],
sparse_index=IntIndex(4, [1, 2, 3]),
dtype=None, fill_value=0)
exp = SparseArray([0, 1, 2, 3], dtype=None)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
@pytest.mark.parametrize("sparse_index", [
None, IntIndex(1, [0]),
])
def test_constructor_spindex_dtype_scalar(self, sparse_index):
# scalar input
arr = SparseArray(data=1, sparse_index=sparse_index, dtype=None)
exp = SparseArray([1], dtype=None)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
arr = SparseArray(data=1, sparse_index=IntIndex(1, [0]), dtype=None)
exp = SparseArray([1], dtype=None)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
def test_constructor_spindex_dtype_scalar_broadcasts(self):
arr = SparseArray(data=[1, 2], sparse_index=IntIndex(4, [1, 2]),
fill_value=0, dtype=None)
exp = SparseArray([0, 1, 2, 0], fill_value=0, dtype=None)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
@pytest.mark.parametrize('data, fill_value', [
(np.array([1, 2]), 0),
(np.array([1.0, 2.0]), np.nan),
([True, False], False),
([pd.Timestamp('2017-01-01')], pd.NaT),
])
def test_constructor_inferred_fill_value(self, data, fill_value):
result = SparseArray(data).fill_value
if pd.isna(fill_value):
assert pd.isna(result)
else:
assert result == fill_value
@pytest.mark.parametrize('scalar,dtype', [
(False, SparseDtype(bool, False)),
(0.0, SparseDtype('float64', 0)),
(1, SparseDtype('int64', 1)),
('z', SparseDtype('object', 'z'))])
def test_scalar_with_index_infer_dtype(self, scalar, dtype):
# GH 19163
arr = SparseArray(scalar, index=[1, 2, 3], fill_value=scalar)
exp = SparseArray([scalar, scalar, scalar], fill_value=scalar)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == dtype
assert exp.dtype == dtype
@pytest.mark.parametrize("fill", [1, np.nan, 0])
def test_sparse_series_round_trip(self, kind, fill):
# see gh-13999
arr = SparseArray([np.nan, 1, np.nan, 2, 3],
kind=kind, fill_value=fill)
res = SparseArray(SparseSeries(arr))
tm.assert_sp_array_equal(arr, res)
arr = SparseArray([0, 0, 0, 1, 1, 2], dtype=np.int64,
kind=kind, fill_value=fill)
res = SparseArray(SparseSeries(arr), dtype=np.int64)
tm.assert_sp_array_equal(arr, res)
res = SparseArray(SparseSeries(arr))
tm.assert_sp_array_equal(arr, res)
@pytest.mark.parametrize("fill", [True, False, np.nan])
def test_sparse_series_round_trip2(self, kind, fill):
# see gh-13999
arr = SparseArray([True, False, True, True], dtype=np.bool,
kind=kind, fill_value=fill)
res = SparseArray(SparseSeries(arr))
tm.assert_sp_array_equal(arr, res)
res = SparseArray(SparseSeries(arr))
tm.assert_sp_array_equal(arr, res)
def test_get_item(self):
assert np.isnan(self.arr[1])
assert self.arr[2] == 1
assert self.arr[7] == 5
assert self.zarr[0] == 0
assert self.zarr[2] == 1
assert self.zarr[7] == 5
errmsg = re.compile("bounds")
tm.assert_raises_regex(IndexError, errmsg, lambda: self.arr[11])
tm.assert_raises_regex(IndexError, errmsg, lambda: self.arr[-11])
assert self.arr[-1] == self.arr[len(self.arr) - 1]
def test_take_scalar_raises(self):
msg = "'indices' must be an array, not a scalar '2'."
with tm.assert_raises_regex(ValueError, msg):
self.arr.take(2)
def test_take(self):
exp = SparseArray(np.take(self.arr_data, [2, 3]))
tm.assert_sp_array_equal(self.arr.take([2, 3]), exp)
exp = SparseArray(np.take(self.arr_data, [0, 1, 2]))
tm.assert_sp_array_equal(self.arr.take([0, 1, 2]), exp)
def test_take_fill_value(self):
data = np.array([1, np.nan, 0, 3, 0])
sparse = SparseArray(data, fill_value=0)
exp = SparseArray(np.take(data, [0]), fill_value=0)
tm.assert_sp_array_equal(sparse.take([0]), exp)
exp = SparseArray(np.take(data, [1, 3, 4]), fill_value=0)
tm.assert_sp_array_equal(sparse.take([1, 3, 4]), exp)
def test_take_negative(self):
exp = SparseArray(np.take(self.arr_data, [-1]))
tm.assert_sp_array_equal(self.arr.take([-1]), exp)
exp = SparseArray(np.take(self.arr_data, [-4, -3, -2]))
tm.assert_sp_array_equal(self.arr.take([-4, -3, -2]), exp)
def test_bad_take(self):
tm.assert_raises_regex(
IndexError, "bounds", lambda: self.arr.take([11]))
def test_take_filling(self):
# similar tests as GH 12631
sparse = SparseArray([np.nan, np.nan, 1, np.nan, 4])
result = sparse.take(np.array([1, 0, -1]))
expected = SparseArray([np.nan, np.nan, 4])
tm.assert_sp_array_equal(result, expected)
# XXX: test change: fill_value=True -> allow_fill=True
result = sparse.take(np.array([1, 0, -1]), allow_fill=True)
expected = SparseArray([np.nan, np.nan, np.nan])
tm.assert_sp_array_equal(result, expected)
# allow_fill=False
result = sparse.take(np.array([1, 0, -1]),
allow_fill=False, fill_value=True)
expected = SparseArray([np.nan, np.nan, 4])
tm.assert_sp_array_equal(result, expected)
msg = ("Invalid value in 'indices'")
with tm.assert_raises_regex(ValueError, msg):
sparse.take(np.array([1, 0, -2]), allow_fill=True)
with tm.assert_raises_regex(ValueError, msg):
sparse.take(np.array([1, 0, -5]), allow_fill=True)
with pytest.raises(IndexError):
sparse.take(np.array([1, -6]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]), allow_fill=True)
def test_take_filling_fill_value(self):
# same tests as GH 12631
sparse = SparseArray([np.nan, 0, 1, 0, 4], fill_value=0)
result = sparse.take(np.array([1, 0, -1]))
expected = SparseArray([0, np.nan, 4], fill_value=0)
tm.assert_sp_array_equal(result, expected)
# fill_value
result = sparse.take(np.array([1, 0, -1]), allow_fill=True)
# XXX: behavior change.
# the old way of filling self.fill_value doesn't follow EA rules.
# It's supposed to be self.dtype.na_value (nan in this case)
expected = SparseArray([0, np.nan, np.nan], fill_value=0)
tm.assert_sp_array_equal(result, expected)
# allow_fill=False
result = sparse.take(np.array([1, 0, -1]),
allow_fill=False, fill_value=True)
expected = SparseArray([0, np.nan, 4], fill_value=0)
tm.assert_sp_array_equal(result, expected)
msg = ("Invalid value in 'indices'.")
with tm.assert_raises_regex(ValueError, msg):
sparse.take(np.array([1, 0, -2]), allow_fill=True)
with tm.assert_raises_regex(ValueError, msg):
sparse.take(np.array([1, 0, -5]), allow_fill=True)
with pytest.raises(IndexError):
sparse.take(np.array([1, -6]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]), fill_value=True)
def test_take_filling_all_nan(self):
sparse = SparseArray([np.nan, np.nan, np.nan, np.nan, np.nan])
# XXX: did the default kind from take change?
result = sparse.take(np.array([1, 0, -1]))
expected = SparseArray([np.nan, np.nan, np.nan], kind='block')
tm.assert_sp_array_equal(result, expected)
result = sparse.take(np.array([1, 0, -1]), fill_value=True)
expected = SparseArray([np.nan, np.nan, np.nan], kind='block')
tm.assert_sp_array_equal(result, expected)
with pytest.raises(IndexError):
sparse.take(np.array([1, -6]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]), fill_value=True)
def test_set_item(self):
def setitem():
self.arr[5] = 3
def setslice():
self.arr[1:5] = 2
tm.assert_raises_regex(TypeError, "item assignment", setitem)
tm.assert_raises_regex(TypeError, "item assignment", setslice)
def test_constructor_from_too_large_array(self):
tm.assert_raises_regex(TypeError, "expected dimension <= 1 data",
SparseArray, np.arange(10).reshape((2, 5)))
def test_constructor_from_sparse(self):
res = SparseArray(self.zarr)
assert res.fill_value == 0
assert_almost_equal(res.sp_values, self.zarr.sp_values)
def test_constructor_copy(self):
cp = SparseArray(self.arr, copy=True)
cp.sp_values[:3] = 0
assert not (self.arr.sp_values[:3] == 0).any()
not_copy = SparseArray(self.arr)
not_copy.sp_values[:3] = 0
assert (self.arr.sp_values[:3] == 0).all()
def test_constructor_bool(self):
# GH 10648
data = np.array([False, False, True, True, False, False])
arr = SparseArray(data, fill_value=False, dtype=bool)
assert arr.dtype == SparseDtype(bool)
tm.assert_numpy_array_equal(arr.sp_values, np.array([True, True]))
# Behavior change: np.asarray densifies.
# tm.assert_numpy_array_equal(arr.sp_values, np.asarray(arr))
tm.assert_numpy_array_equal(arr.sp_index.indices,
np.array([2, 3], np.int32))
for dense in [arr.to_dense(), arr.values]:
assert dense.dtype == bool
tm.assert_numpy_array_equal(dense, data)
def test_constructor_bool_fill_value(self):
arr = SparseArray([True, False, True], dtype=None)
assert arr.dtype == SparseDtype(np.bool)
assert not arr.fill_value
arr = SparseArray([True, False, True], dtype=np.bool)
assert arr.dtype == SparseDtype(np.bool)
assert not arr.fill_value
arr = SparseArray([True, False, True], dtype=np.bool, fill_value=True)
assert arr.dtype == SparseDtype(np.bool, True)
assert arr.fill_value
def test_constructor_float32(self):
# GH 10648
data = np.array([1., np.nan, 3], dtype=np.float32)
arr = SparseArray(data, dtype=np.float32)
assert arr.dtype == SparseDtype(np.float32)
tm.assert_numpy_array_equal(arr.sp_values,
np.array([1, 3], dtype=np.float32))
# Behavior change: np.asarray densifies.
# tm.assert_numpy_array_equal(arr.sp_values, np.asarray(arr))
tm.assert_numpy_array_equal(arr.sp_index.indices,
np.array([0, 2], dtype=np.int32))
for dense in [arr.to_dense(), arr.values]:
assert dense.dtype == np.float32
tm.assert_numpy_array_equal(dense, data)
def test_astype(self):
# float -> float
arr = SparseArray([None, None, 0, 2])
result = arr.astype("Sparse[float32]")
expected = SparseArray([None, None, 0, 2], dtype=np.dtype('float32'))
tm.assert_sp_array_equal(result, expected)
dtype = SparseDtype("float64", fill_value=0)
result = arr.astype(dtype)
expected = SparseArray._simple_new(np.array([0., 2.],
dtype=dtype.subtype),
IntIndex(4, [2, 3]),
dtype)
tm.assert_sp_array_equal(result, expected)
dtype = SparseDtype("int64", 0)
result = arr.astype(dtype)
expected = SparseArray._simple_new(np.array([0, 2], dtype=np.int64),
IntIndex(4, [2, 3]),
dtype)
tm.assert_sp_array_equal(result, expected)
arr = SparseArray([0, np.nan, 0, 1], fill_value=0)
with tm.assert_raises_regex(ValueError, 'NA'):
arr.astype('Sparse[i8]')
def test_astype_bool(self):
a = pd.SparseArray([1, 0, 0, 1], dtype=SparseDtype(int, 0))
result = a.astype(bool)
expected = SparseArray([True, 0, 0, True],
dtype=SparseDtype(bool, 0))
tm.assert_sp_array_equal(result, expected)
# update fill value
result = a.astype(SparseDtype(bool, False))
expected = SparseArray([True, False, False, True],
dtype=SparseDtype(bool, False))
tm.assert_sp_array_equal(result, expected)
def test_astype_all(self, any_real_dtype):
vals = np.array([1, 2, 3])
arr = SparseArray(vals, fill_value=1)
typ = np.dtype(any_real_dtype)
res = arr.astype(typ)
assert res.dtype == SparseDtype(typ, 1)
assert res.sp_values.dtype == typ
tm.assert_numpy_array_equal(np.asarray(res.values),
vals.astype(typ))
def test_set_fill_value(self):
arr = SparseArray([1., np.nan, 2.], fill_value=np.nan)
arr.fill_value = 2
assert arr.fill_value == 2
arr = SparseArray([1, 0, 2], fill_value=0, dtype=np.int64)
arr.fill_value = 2
assert arr.fill_value == 2
# XXX: this seems fine? You can construct an integer
# sparsearray with NaN fill value, why not update one?
# coerces to int
# msg = "unable to set fill_value 3\\.1 to int64 dtype"
# with tm.assert_raises_regex(ValueError, msg):
arr.fill_value = 3.1
assert arr.fill_value == 3.1
# msg = "unable to set fill_value nan to int64 dtype"
# with tm.assert_raises_regex(ValueError, msg):
arr.fill_value = np.nan
assert np.isnan(arr.fill_value)
arr = SparseArray([True, False, True], fill_value=False, dtype=np.bool)
arr.fill_value = True
assert arr.fill_value
# coerces to bool
# msg = "unable to set fill_value 0 to bool dtype"
# with tm.assert_raises_regex(ValueError, msg):
arr.fill_value = 0
assert arr.fill_value == 0
# msg = "unable to set fill_value nan to bool dtype"
# with tm.assert_raises_regex(ValueError, msg):
arr.fill_value = np.nan
assert np.isnan(arr.fill_value)
@pytest.mark.parametrize("val", [[1, 2, 3], np.array([1, 2]), (1, 2, 3)])
def test_set_fill_invalid_non_scalar(self, val):
arr = SparseArray([True, False, True], fill_value=False, dtype=np.bool)
msg = "fill_value must be a scalar"
with tm.assert_raises_regex(ValueError, msg):
arr.fill_value = val
def test_copy_shallow(self):
arr2 = self.arr.copy(deep=False)
assert arr2.sp_values is self.arr.sp_values
assert arr2.sp_index is self.arr.sp_index
def test_values_asarray(self):
assert_almost_equal(self.arr.values, self.arr_data)
assert_almost_equal(self.arr.to_dense(), self.arr_data)
@pytest.mark.parametrize('data,shape,dtype', [
([0, 0, 0, 0, 0], (5,), None),
([], (0,), None),
([0], (1,), None),
(['A', 'A', np.nan, 'B'], (4,), np.object)
])
def test_shape(self, data, shape, dtype):
# GH 21126
out = SparseArray(data, dtype=dtype)
assert out.shape == shape
@pytest.mark.parametrize("vals", [
[np.nan, np.nan, np.nan, np.nan, np.nan],
[1, np.nan, np.nan, 3, np.nan],
[1, np.nan, 0, 3, 0],
])
@pytest.mark.parametrize("method", ["to_dense", "get_values"])
@pytest.mark.parametrize("fill_value", [None, 0])
def test_dense_repr(self, vals, fill_value, method):
vals = np.array(vals)
arr = SparseArray(vals, fill_value=fill_value)
dense_func = getattr(arr, method)
res = dense_func()
tm.assert_numpy_array_equal(res, vals)
def test_getitem(self):
def _checkit(i):
assert_almost_equal(self.arr[i], self.arr.values[i])
for i in range(len(self.arr)):
_checkit(i)
_checkit(-i)
def test_getitem_arraylike_mask(self):
arr = SparseArray([0, 1, 2])
result = arr[[True, False, True]]
expected = SparseArray([0, 2])
tm.assert_sp_array_equal(result, expected)
def test_getslice(self):
result = self.arr[:-3]
exp = SparseArray(self.arr.values[:-3])
tm.assert_sp_array_equal(result, exp)
result = self.arr[-4:]
exp = SparseArray(self.arr.values[-4:])
tm.assert_sp_array_equal(result, exp)
# two corner cases from Series
result = self.arr[-12:]
exp = SparseArray(self.arr)
tm.assert_sp_array_equal(result, exp)
result = self.arr[:-12]
exp = SparseArray(self.arr.values[:0])
tm.assert_sp_array_equal(result, exp)
def test_getslice_tuple(self):
dense = np.array([np.nan, 0, 3, 4, 0, 5, np.nan, np.nan, 0])
sparse = SparseArray(dense)
res = sparse[4:, ]
exp = SparseArray(dense[4:, ])
tm.assert_sp_array_equal(res, exp)
sparse = SparseArray(dense, fill_value=0)
res = sparse[4:, ]
exp = SparseArray(dense[4:, ], fill_value=0)
tm.assert_sp_array_equal(res, exp)
with pytest.raises(IndexError):
sparse[4:, :]
with pytest.raises(IndexError):
# check numpy compat
dense[4:, :]
def test_boolean_slice_empty(self):
arr = pd.SparseArray([0, 1, 2])
res = arr[[False, False, False]]
assert res.dtype == arr.dtype
@pytest.mark.parametrize("op", ["add", "sub", "mul",
"truediv", "floordiv", "pow"])
def test_binary_operators(self, op):
op = getattr(operator, op)
data1 = np.random.randn(20)
data2 = np.random.randn(20)
data1[::2] = np.nan
data2[::3] = np.nan
arr1 = SparseArray(data1)
arr2 = SparseArray(data2)
data1[::2] = 3
data2[::3] = 3
farr1 = SparseArray(data1, fill_value=3)
farr2 = SparseArray(data2, fill_value=3)
def _check_op(op, first, second):
res = op(first, second)
exp = SparseArray(op(first.values, second.values),
fill_value=first.fill_value)
assert isinstance(res, SparseArray)
assert_almost_equal(res.values, exp.values)
res2 = op(first, second.values)
assert isinstance(res2, SparseArray)
tm.assert_sp_array_equal(res, res2)
res3 = op(first.values, second)
assert isinstance(res3, SparseArray)
tm.assert_sp_array_equal(res, res3)
res4 = op(first, 4)
assert isinstance(res4, SparseArray)
# Ignore this if the actual op raises (e.g. pow).
try:
exp = op(first.values, 4)
exp_fv = op(first.fill_value, 4)
except ValueError:
pass
else:
assert_almost_equal(res4.fill_value, exp_fv)
assert_almost_equal(res4.values, exp)
with np.errstate(all="ignore"):
for first_arr, second_arr in [(arr1, arr2), (farr1, farr2)]:
_check_op(op, first_arr, second_arr)
def test_pickle(self):
def _check_roundtrip(obj):
unpickled = tm.round_trip_pickle(obj)
tm.assert_sp_array_equal(unpickled, obj)
_check_roundtrip(self.arr)
_check_roundtrip(self.zarr)
def test_generator_warnings(self):
sp_arr = SparseArray([1, 2, 3])
with warnings.catch_warnings(record=True) as w:
warnings.filterwarnings(action='always',
category=DeprecationWarning)
warnings.filterwarnings(action='always',
category=PendingDeprecationWarning)
for _ in sp_arr:
pass
assert len(w) == 0
def test_fillna(self):
s = SparseArray([1, np.nan, np.nan, 3, np.nan])
res = s.fillna(-1)
exp = SparseArray([1, -1, -1, 3, -1], fill_value=-1, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([1, np.nan, np.nan, 3, np.nan], fill_value=0)
res = s.fillna(-1)
exp = SparseArray([1, -1, -1, 3, -1], fill_value=0, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([1, np.nan, 0, 3, 0])
res = s.fillna(-1)
exp = SparseArray([1, -1, 0, 3, 0], fill_value=-1, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([1, np.nan, 0, 3, 0], fill_value=0)
res = s.fillna(-1)
exp = SparseArray([1, -1, 0, 3, 0], fill_value=0, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([np.nan, np.nan, np.nan, np.nan])
res = s.fillna(-1)
exp = SparseArray([-1, -1, -1, -1], fill_value=-1, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([np.nan, np.nan, np.nan, np.nan], fill_value=0)
res = s.fillna(-1)
exp = SparseArray([-1, -1, -1, -1], fill_value=0, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
# float dtype's fill_value is np.nan, replaced by -1
s = SparseArray([0., 0., 0., 0.])
res = s.fillna(-1)
exp = SparseArray([0., 0., 0., 0.], fill_value=-1)
tm.assert_sp_array_equal(res, exp)
# int dtype shouldn't have missing. No changes.
s = SparseArray([0, 0, 0, 0])
assert s.dtype == SparseDtype(np.int64)
assert s.fill_value == 0
res = s.fillna(-1)
tm.assert_sp_array_equal(res, s)
s = SparseArray([0, 0, 0, 0], fill_value=0)
assert s.dtype == SparseDtype(np.int64)
assert s.fill_value == 0
res = s.fillna(-1)
exp = SparseArray([0, 0, 0, 0], fill_value=0)
tm.assert_sp_array_equal(res, exp)
# fill_value can be nan if there is no missing hole.
# only fill_value will be changed
s = SparseArray([0, 0, 0, 0], fill_value=np.nan)
assert s.dtype == SparseDtype(np.int64, fill_value=np.nan)
assert np.isnan(s.fill_value)
res = s.fillna(-1)
exp = SparseArray([0, 0, 0, 0], fill_value=-1)
tm.assert_sp_array_equal(res, exp)
def test_fillna_overlap(self):
s = SparseArray([1, np.nan, np.nan, 3, np.nan])
# filling with existing value doesn't replace existing value with
# fill_value, i.e. existing 3 remains in sp_values
res = s.fillna(3)
exp = np.array([1, 3, 3, 3, 3], dtype=np.float64)
tm.assert_numpy_array_equal(res.to_dense(), exp)
s = SparseArray([1, np.nan, np.nan, 3, np.nan], fill_value=0)
res = s.fillna(3)
exp = SparseArray([1, 3, 3, 3, 3], fill_value=0, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
class TestSparseArray(tm.TestCase):
def setUp(self):
self.arr_data = np.array([nan, nan, 1, 2, 3, nan, 4, 5, nan, 6])
self.arr = SparseArray(self.arr_data)
self.zarr = SparseArray([0, 0, 1, 2, 3, 0, 4, 5, 0, 6], fill_value=0)
def test_constructor_dtype(self):
arr = SparseArray([np.nan, 1, 2, np.nan])
self.assertEqual(arr.dtype, np.float64)
self.assertTrue(np.isnan(arr.fill_value))
arr = SparseArray([np.nan, 1, 2, np.nan], fill_value=0)
self.assertEqual(arr.dtype, np.float64)
self.assertEqual(arr.fill_value, 0)
arr = SparseArray([0, 1, 2, 4], dtype=np.float64)
self.assertEqual(arr.dtype, np.float64)
self.assertTrue(np.isnan(arr.fill_value))
arr = SparseArray([0, 1, 2, 4], dtype=np.int64)
self.assertEqual(arr.dtype, np.int64)
self.assertEqual(arr.fill_value, 0)
arr = SparseArray([0, 1, 2, 4], fill_value=0, dtype=np.int64)
self.assertEqual(arr.dtype, np.int64)
self.assertEqual(arr.fill_value, 0)
arr = SparseArray([0, 1, 2, 4], dtype=None)
self.assertEqual(arr.dtype, np.int64)
self.assertEqual(arr.fill_value, 0)
arr = SparseArray([0, 1, 2, 4], fill_value=0, dtype=None)
self.assertEqual(arr.dtype, np.int64)
self.assertEqual(arr.fill_value, 0)
def test_constructor_object_dtype(self):
# GH 11856
arr = SparseArray(['A', 'A', np.nan, 'B'], dtype=np.object)
self.assertEqual(arr.dtype, np.object)
self.assertTrue(np.isnan(arr.fill_value))
arr = SparseArray(['A', 'A', np.nan, 'B'], dtype=np.object,
fill_value='A')
self.assertEqual(arr.dtype, np.object)
self.assertEqual(arr.fill_value, 'A')
def test_constructor_spindex_dtype(self):
arr = SparseArray(data=[1, 2], sparse_index=IntIndex(4, [1, 2]))
tm.assert_sp_array_equal(arr, SparseArray([np.nan, 1, 2, np.nan]))
self.assertEqual(arr.dtype, np.float64)
self.assertTrue(np.isnan(arr.fill_value))
arr = SparseArray(data=[1, 2, 3],
sparse_index=IntIndex(4, [1, 2, 3]),
dtype=np.int64, fill_value=0)
exp = SparseArray([0, 1, 2, 3], dtype=np.int64, fill_value=0)
tm.assert_sp_array_equal(arr, exp)
self.assertEqual(arr.dtype, np.int64)
self.assertEqual(arr.fill_value, 0)
arr = SparseArray(data=[1, 2], sparse_index=IntIndex(4, [1, 2]),
fill_value=0, dtype=np.int64)
exp = SparseArray([0, 1, 2, 0], fill_value=0, dtype=np.int64)
tm.assert_sp_array_equal(arr, exp)
self.assertEqual(arr.dtype, np.int64)
self.assertEqual(arr.fill_value, 0)
arr = SparseArray(data=[1, 2, 3],
sparse_index=IntIndex(4, [1, 2, 3]),
dtype=None, fill_value=0)
exp = SparseArray([0, 1, 2, 3], dtype=None)
tm.assert_sp_array_equal(arr, exp)
self.assertEqual(arr.dtype, np.int64)
self.assertEqual(arr.fill_value, 0)
# scalar input
arr = SparseArray(data=1, sparse_index=IntIndex(1, [0]), dtype=None)
exp = SparseArray([1], dtype=None)
tm.assert_sp_array_equal(arr, exp)
self.assertEqual(arr.dtype, np.int64)
self.assertEqual(arr.fill_value, 0)
arr = SparseArray(data=[1, 2], sparse_index=IntIndex(4, [1, 2]),
fill_value=0, dtype=None)
exp = SparseArray([0, 1, 2, 0], fill_value=0, dtype=None)
tm.assert_sp_array_equal(arr, exp)
self.assertEqual(arr.dtype, np.int64)
self.assertEqual(arr.fill_value, 0)
def test_sparseseries_roundtrip(self):
# GH 13999
for kind in ['integer', 'block']:
for fill in [1, np.nan, 0]:
arr = SparseArray([np.nan, 1, np.nan, 2, 3], kind=kind,
fill_value=fill)
res = SparseArray(SparseSeries(arr))
tm.assert_sp_array_equal(arr, res)
arr = SparseArray([0, 0, 0, 1, 1, 2], dtype=np.int64,
kind=kind, fill_value=fill)
res = SparseArray(SparseSeries(arr), dtype=np.int64)
tm.assert_sp_array_equal(arr, res)
res = SparseArray(SparseSeries(arr))
tm.assert_sp_array_equal(arr, res)
for fill in [True, False, np.nan]:
arr = SparseArray([True, False, True, True], dtype=np.bool,
kind=kind, fill_value=fill)
res = SparseArray(SparseSeries(arr))
tm.assert_sp_array_equal(arr, res)
res = SparseArray(SparseSeries(arr))
tm.assert_sp_array_equal(arr, res)
def test_get_item(self):
self.assertTrue(np.isnan(self.arr[1]))
self.assertEqual(self.arr[2], 1)
self.assertEqual(self.arr[7], 5)
self.assertEqual(self.zarr[0], 0)
self.assertEqual(self.zarr[2], 1)
self.assertEqual(self.zarr[7], 5)
errmsg = re.compile("bounds")
assertRaisesRegexp(IndexError, errmsg, lambda: self.arr[11])
assertRaisesRegexp(IndexError, errmsg, lambda: self.arr[-11])
self.assertEqual(self.arr[-1], self.arr[len(self.arr) - 1])
def test_take(self):
self.assertTrue(np.isnan(self.arr.take(0)))
self.assertTrue(np.isscalar(self.arr.take(2)))
# np.take in < 1.8 doesn't support scalar indexing
if not _np_version_under1p8:
self.assertEqual(self.arr.take(2), np.take(self.arr_data, 2))
self.assertEqual(self.arr.take(6), np.take(self.arr_data, 6))
exp = SparseArray(np.take(self.arr_data, [2, 3]))
tm.assert_sp_array_equal(self.arr.take([2, 3]), exp)
exp = SparseArray(np.take(self.arr_data, [0, 1, 2]))
tm.assert_sp_array_equal(self.arr.take([0, 1, 2]), exp)
def test_take_fill_value(self):
data = np.array([1, np.nan, 0, 3, 0])
sparse = SparseArray(data, fill_value=0)
exp = SparseArray(np.take(data, [0]), fill_value=0)
tm.assert_sp_array_equal(sparse.take([0]), exp)
exp = SparseArray(np.take(data, [1, 3, 4]), fill_value=0)
tm.assert_sp_array_equal(sparse.take([1, 3, 4]), exp)
def test_take_negative(self):
exp = SparseArray(np.take(self.arr_data, [-1]))
tm.assert_sp_array_equal(self.arr.take([-1]), exp)
exp = SparseArray(np.take(self.arr_data, [-4, -3, -2]))
tm.assert_sp_array_equal(self.arr.take([-4, -3, -2]), exp)
def test_bad_take(self):
assertRaisesRegexp(IndexError, "bounds", lambda: self.arr.take(11))
self.assertRaises(IndexError, lambda: self.arr.take(-11))
def test_take_invalid_kwargs(self):
msg = r"take\(\) got an unexpected keyword argument 'foo'"
tm.assertRaisesRegexp(TypeError, msg, self.arr.take,
[2, 3], foo=2)
msg = "the 'out' parameter is not supported"
tm.assertRaisesRegexp(ValueError, msg, self.arr.take,
[2, 3], out=self.arr)
msg = "the 'mode' parameter is not supported"
tm.assertRaisesRegexp(ValueError, msg, self.arr.take,
[2, 3], mode='clip')
def test_take_filling(self):
# similar tests as GH 12631
sparse = SparseArray([np.nan, np.nan, 1, np.nan, 4])
result = sparse.take(np.array([1, 0, -1]))
expected = SparseArray([np.nan, np.nan, 4])
tm.assert_sp_array_equal(result, expected)
# fill_value
result = sparse.take(np.array([1, 0, -1]), fill_value=True)
expected = SparseArray([np.nan, np.nan, np.nan])
tm.assert_sp_array_equal(result, expected)
# allow_fill=False
result = sparse.take(np.array([1, 0, -1]),
allow_fill=False, fill_value=True)
expected = SparseArray([np.nan, np.nan, 4])
tm.assert_sp_array_equal(result, expected)
msg = ('When allow_fill=True and fill_value is not None, '
'all indices must be >= -1')
with tm.assertRaisesRegexp(ValueError, msg):
sparse.take(np.array([1, 0, -2]), fill_value=True)
with tm.assertRaisesRegexp(ValueError, msg):
sparse.take(np.array([1, 0, -5]), fill_value=True)
with tm.assertRaises(IndexError):
sparse.take(np.array([1, -6]))
with tm.assertRaises(IndexError):
sparse.take(np.array([1, 5]))
with tm.assertRaises(IndexError):
sparse.take(np.array([1, 5]), fill_value=True)
def test_take_filling_fill_value(self):
# same tests as GH 12631
sparse = SparseArray([np.nan, 0, 1, 0, 4], fill_value=0)
result = sparse.take(np.array([1, 0, -1]))
expected = SparseArray([0, np.nan, 4], fill_value=0)
tm.assert_sp_array_equal(result, expected)
# fill_value
result = sparse.take(np.array([1, 0, -1]), fill_value=True)
expected = SparseArray([0, np.nan, 0], fill_value=0)
tm.assert_sp_array_equal(result, expected)
# allow_fill=False
result = sparse.take(np.array([1, 0, -1]),
allow_fill=False, fill_value=True)
expected = SparseArray([0, np.nan, 4], fill_value=0)
tm.assert_sp_array_equal(result, expected)
msg = ('When allow_fill=True and fill_value is not None, '
'all indices must be >= -1')
with tm.assertRaisesRegexp(ValueError, msg):
sparse.take(np.array([1, 0, -2]), fill_value=True)
with tm.assertRaisesRegexp(ValueError, msg):
sparse.take(np.array([1, 0, -5]), fill_value=True)
with tm.assertRaises(IndexError):
sparse.take(np.array([1, -6]))
with tm.assertRaises(IndexError):
sparse.take(np.array([1, 5]))
with tm.assertRaises(IndexError):
sparse.take(np.array([1, 5]), fill_value=True)
def test_take_filling_all_nan(self):
sparse = SparseArray([np.nan, np.nan, np.nan, np.nan, np.nan])
result = sparse.take(np.array([1, 0, -1]))
expected = SparseArray([np.nan, np.nan, np.nan])
tm.assert_sp_array_equal(result, expected)
result = sparse.take(np.array([1, 0, -1]), fill_value=True)
expected = SparseArray([np.nan, np.nan, np.nan])
tm.assert_sp_array_equal(result, expected)
with tm.assertRaises(IndexError):
sparse.take(np.array([1, -6]))
with tm.assertRaises(IndexError):
sparse.take(np.array([1, 5]))
with tm.assertRaises(IndexError):
sparse.take(np.array([1, 5]), fill_value=True)
def test_set_item(self):
def setitem():
self.arr[5] = 3
def setslice():
self.arr[1:5] = 2
assertRaisesRegexp(TypeError, "item assignment", setitem)
assertRaisesRegexp(TypeError, "item assignment", setslice)
def test_constructor_from_too_large_array(self):
assertRaisesRegexp(TypeError, "expected dimension <= 1 data",
SparseArray, np.arange(10).reshape((2, 5)))
def test_constructor_from_sparse(self):
res = SparseArray(self.zarr)
self.assertEqual(res.fill_value, 0)
assert_almost_equal(res.sp_values, self.zarr.sp_values)
def test_constructor_copy(self):
cp = SparseArray(self.arr, copy=True)
cp.sp_values[:3] = 0
self.assertFalse((self.arr.sp_values[:3] == 0).any())
not_copy = SparseArray(self.arr)
not_copy.sp_values[:3] = 0
self.assertTrue((self.arr.sp_values[:3] == 0).all())
def test_constructor_bool(self):
# GH 10648
data = np.array([False, False, True, True, False, False])
arr = SparseArray(data, fill_value=False, dtype=bool)
self.assertEqual(arr.dtype, bool)
tm.assert_numpy_array_equal(arr.sp_values, np.array([True, True]))
tm.assert_numpy_array_equal(arr.sp_values, np.asarray(arr))
tm.assert_numpy_array_equal(arr.sp_index.indices,
np.array([2, 3], np.int32))
for dense in [arr.to_dense(), arr.values]:
self.assertEqual(dense.dtype, bool)
tm.assert_numpy_array_equal(dense, data)
def test_constructor_bool_fill_value(self):
arr = SparseArray([True, False, True], dtype=None)
self.assertEqual(arr.dtype, np.bool)
self.assertFalse(arr.fill_value)
arr = SparseArray([True, False, True], dtype=np.bool)
self.assertEqual(arr.dtype, np.bool)
self.assertFalse(arr.fill_value)
arr = SparseArray([True, False, True], dtype=np.bool, fill_value=True)
self.assertEqual(arr.dtype, np.bool)
self.assertTrue(arr.fill_value)
def test_constructor_float32(self):
# GH 10648
data = np.array([1., np.nan, 3], dtype=np.float32)
arr = SparseArray(data, dtype=np.float32)
self.assertEqual(arr.dtype, np.float32)
tm.assert_numpy_array_equal(arr.sp_values,
np.array([1, 3], dtype=np.float32))
tm.assert_numpy_array_equal(arr.sp_values, np.asarray(arr))
tm.assert_numpy_array_equal(arr.sp_index.indices,
np.array([0, 2], dtype=np.int32))
for dense in [arr.to_dense(), arr.values]:
self.assertEqual(dense.dtype, np.float32)
tm.assert_numpy_array_equal(dense, data)
def test_astype(self):
res = self.arr.astype('f8')
res.sp_values[:3] = 27
self.assertFalse((self.arr.sp_values[:3] == 27).any())
msg = "unable to coerce current fill_value nan to int64 dtype"
with tm.assertRaisesRegexp(ValueError, msg):
self.arr.astype('i8')
arr = SparseArray([0, np.nan, 0, 1])
with tm.assertRaisesRegexp(ValueError, msg):
arr.astype('i8')
arr = SparseArray([0, np.nan, 0, 1], fill_value=0)
msg = 'Cannot convert non-finite values \\(NA or inf\\) to integer'
with tm.assertRaisesRegexp(ValueError, msg):
arr.astype('i8')
def test_astype_all(self):
vals = np.array([1, 2, 3])
arr = SparseArray(vals, fill_value=1)
types = [np.float64, np.float32, np.int64,
np.int32, np.int16, np.int8]
for typ in types:
res = arr.astype(typ)
self.assertEqual(res.dtype, typ)
self.assertEqual(res.sp_values.dtype, typ)
tm.assert_numpy_array_equal(res.values, vals.astype(typ))
def test_set_fill_value(self):
arr = SparseArray([1., np.nan, 2.], fill_value=np.nan)
arr.fill_value = 2
self.assertEqual(arr.fill_value, 2)
arr = SparseArray([1, 0, 2], fill_value=0, dtype=np.int64)
arr.fill_value = 2
self.assertEqual(arr.fill_value, 2)
# coerces to int
msg = "unable to set fill_value 3\\.1 to int64 dtype"
with tm.assertRaisesRegexp(ValueError, msg):
arr.fill_value = 3.1
msg = "unable to set fill_value nan to int64 dtype"
with tm.assertRaisesRegexp(ValueError, msg):
arr.fill_value = np.nan
arr = SparseArray([True, False, True], fill_value=False, dtype=np.bool)
arr.fill_value = True
self.assertTrue(arr.fill_value)
# coerces to bool
msg = "unable to set fill_value 0 to bool dtype"
with tm.assertRaisesRegexp(ValueError, msg):
arr.fill_value = 0
msg = "unable to set fill_value nan to bool dtype"
with tm.assertRaisesRegexp(ValueError, msg):
arr.fill_value = np.nan
# invalid
msg = "fill_value must be a scalar"
for val in [[1, 2, 3], np.array([1, 2]), (1, 2, 3)]:
with tm.assertRaisesRegexp(ValueError, msg):
arr.fill_value = val
def test_copy_shallow(self):
arr2 = self.arr.copy(deep=False)
def _get_base(values):
base = values.base
while base.base is not None:
base = base.base
return base
assert (_get_base(arr2) is _get_base(self.arr))
def test_values_asarray(self):
assert_almost_equal(self.arr.values, self.arr_data)
assert_almost_equal(self.arr.to_dense(), self.arr_data)
assert_almost_equal(self.arr.sp_values, np.asarray(self.arr))
def test_to_dense(self):
vals = np.array([1, np.nan, np.nan, 3, np.nan])
res = SparseArray(vals).to_dense()
tm.assert_numpy_array_equal(res, vals)
res = SparseArray(vals, fill_value=0).to_dense()
tm.assert_numpy_array_equal(res, vals)
vals = np.array([1, np.nan, 0, 3, 0])
res = SparseArray(vals).to_dense()
tm.assert_numpy_array_equal(res, vals)
res = SparseArray(vals, fill_value=0).to_dense()
tm.assert_numpy_array_equal(res, vals)
vals = np.array([np.nan, np.nan, np.nan, np.nan, np.nan])
res = SparseArray(vals).to_dense()
tm.assert_numpy_array_equal(res, vals)
res = SparseArray(vals, fill_value=0).to_dense()
tm.assert_numpy_array_equal(res, vals)
# see gh-14647
with tm.assert_produces_warning(FutureWarning,
check_stacklevel=False):
SparseArray(vals).to_dense(fill=2)
def test_getitem(self):
def _checkit(i):
assert_almost_equal(self.arr[i], self.arr.values[i])
for i in range(len(self.arr)):
_checkit(i)
_checkit(-i)
def test_getslice(self):
result = self.arr[:-3]
exp = SparseArray(self.arr.values[:-3])
tm.assert_sp_array_equal(result, exp)
result = self.arr[-4:]
exp = SparseArray(self.arr.values[-4:])
tm.assert_sp_array_equal(result, exp)
# two corner cases from Series
result = self.arr[-12:]
exp = SparseArray(self.arr)
tm.assert_sp_array_equal(result, exp)
result = self.arr[:-12]
exp = SparseArray(self.arr.values[:0])
tm.assert_sp_array_equal(result, exp)
def test_getslice_tuple(self):
dense = np.array([np.nan, 0, 3, 4, 0, 5, np.nan, np.nan, 0])
sparse = SparseArray(dense)
res = sparse[4:, ]
exp = SparseArray(dense[4:, ])
tm.assert_sp_array_equal(res, exp)
sparse = SparseArray(dense, fill_value=0)
res = sparse[4:, ]
exp = SparseArray(dense[4:, ], fill_value=0)
tm.assert_sp_array_equal(res, exp)
with tm.assertRaises(IndexError):
sparse[4:, :]
with tm.assertRaises(IndexError):
# check numpy compat
dense[4:, :]
def test_binary_operators(self):
data1 = np.random.randn(20)
data2 = np.random.randn(20)
data1[::2] = np.nan
data2[::3] = np.nan
arr1 = SparseArray(data1)
arr2 = SparseArray(data2)
data1[::2] = 3
data2[::3] = 3
farr1 = SparseArray(data1, fill_value=3)
farr2 = SparseArray(data2, fill_value=3)
def _check_op(op, first, second):
res = op(first, second)
exp = SparseArray(op(first.values, second.values),
fill_value=first.fill_value)
assert isinstance(res, SparseArray)
assert_almost_equal(res.values, exp.values)
res2 = op(first, second.values)
assert isinstance(res2, SparseArray)
tm.assert_sp_array_equal(res, res2)
res3 = op(first.values, second)
assert isinstance(res3, SparseArray)
tm.assert_sp_array_equal(res, res3)
res4 = op(first, 4)
assert isinstance(res4, SparseArray)
# ignore this if the actual op raises (e.g. pow)
try:
exp = op(first.values, 4)
exp_fv = op(first.fill_value, 4)
assert_almost_equal(res4.fill_value, exp_fv)
assert_almost_equal(res4.values, exp)
except ValueError:
pass
def _check_inplace_op(op):
tmp = arr1.copy()
self.assertRaises(NotImplementedError, op, tmp, arr2)
with np.errstate(all='ignore'):
bin_ops = [operator.add, operator.sub, operator.mul,
operator.truediv, operator.floordiv, operator.pow]
for op in bin_ops:
_check_op(op, arr1, arr2)
_check_op(op, farr1, farr2)
inplace_ops = ['iadd', 'isub', 'imul', 'itruediv', 'ifloordiv',
'ipow']
for op in inplace_ops:
_check_inplace_op(getattr(operator, op))
def test_pickle(self):
def _check_roundtrip(obj):
unpickled = tm.round_trip_pickle(obj)
tm.assert_sp_array_equal(unpickled, obj)
_check_roundtrip(self.arr)
_check_roundtrip(self.zarr)
def test_generator_warnings(self):
sp_arr = SparseArray([1, 2, 3])
with warnings.catch_warnings(record=True) as w:
warnings.filterwarnings(action='always',
category=DeprecationWarning)
warnings.filterwarnings(action='always',
category=PendingDeprecationWarning)
for _ in sp_arr:
pass
assert len(w) == 0
def test_fillna(self):
s = SparseArray([1, np.nan, np.nan, 3, np.nan])
res = s.fillna(-1)
exp = SparseArray([1, -1, -1, 3, -1], fill_value=-1, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([1, np.nan, np.nan, 3, np.nan], fill_value=0)
res = s.fillna(-1)
exp = SparseArray([1, -1, -1, 3, -1], fill_value=0, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([1, np.nan, 0, 3, 0])
res = s.fillna(-1)
exp = SparseArray([1, -1, 0, 3, 0], fill_value=-1, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([1, np.nan, 0, 3, 0], fill_value=0)
res = s.fillna(-1)
exp = SparseArray([1, -1, 0, 3, 0], fill_value=0, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([np.nan, np.nan, np.nan, np.nan])
res = s.fillna(-1)
exp = SparseArray([-1, -1, -1, -1], fill_value=-1, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([np.nan, np.nan, np.nan, np.nan], fill_value=0)
res = s.fillna(-1)
exp = SparseArray([-1, -1, -1, -1], fill_value=0, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
# float dtype's fill_value is np.nan, replaced by -1
s = SparseArray([0., 0., 0., 0.])
res = s.fillna(-1)
exp = SparseArray([0., 0., 0., 0.], fill_value=-1)
tm.assert_sp_array_equal(res, exp)
# int dtype shouldn't have missing. No changes.
s = SparseArray([0, 0, 0, 0])
self.assertEqual(s.dtype, np.int64)
self.assertEqual(s.fill_value, 0)
res = s.fillna(-1)
tm.assert_sp_array_equal(res, s)
s = SparseArray([0, 0, 0, 0], fill_value=0)
self.assertEqual(s.dtype, np.int64)
self.assertEqual(s.fill_value, 0)
res = s.fillna(-1)
exp = SparseArray([0, 0, 0, 0], fill_value=0)
tm.assert_sp_array_equal(res, exp)
# fill_value can be nan if there is no missing hole.
# only fill_value will be changed
s = SparseArray([0, 0, 0, 0], fill_value=np.nan)
self.assertEqual(s.dtype, np.int64)
self.assertTrue(np.isnan(s.fill_value))
res = s.fillna(-1)
exp = SparseArray([0, 0, 0, 0], fill_value=-1)
tm.assert_sp_array_equal(res, exp)
def test_fillna_overlap(self):
s = SparseArray([1, np.nan, np.nan, 3, np.nan])
# filling with existing value doesn't replace existing value with
# fill_value, i.e. existing 3 remains in sp_values
res = s.fillna(3)
exp = np.array([1, 3, 3, 3, 3], dtype=np.float64)
tm.assert_numpy_array_equal(res.to_dense(), exp)
s = SparseArray([1, np.nan, np.nan, 3, np.nan], fill_value=0)
res = s.fillna(3)
exp = SparseArray([1, 3, 3, 3, 3], fill_value=0, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
class TestSparseArray:
def setup_method(self, method):
self.arr_data = np.array(
[np.nan, np.nan, 1, 2, 3, np.nan, 4, 5, np.nan, 6])
self.arr = SparseArray(self.arr_data)
self.zarr = SparseArray([0, 0, 1, 2, 3, 0, 4, 5, 0, 6], fill_value=0)
def test_constructor_dtype(self):
arr = SparseArray([np.nan, 1, 2, np.nan])
assert arr.dtype == SparseDtype(np.float64, np.nan)
assert arr.dtype.subtype == np.float64
assert np.isnan(arr.fill_value)
arr = SparseArray([np.nan, 1, 2, np.nan], fill_value=0)
assert arr.dtype == SparseDtype(np.float64, 0)
assert arr.fill_value == 0
arr = SparseArray([0, 1, 2, 4], dtype=np.float64)
assert arr.dtype == SparseDtype(np.float64, np.nan)
assert np.isnan(arr.fill_value)
arr = SparseArray([0, 1, 2, 4], dtype=np.int64)
assert arr.dtype == SparseDtype(np.int64, 0)
assert arr.fill_value == 0
arr = SparseArray([0, 1, 2, 4], fill_value=0, dtype=np.int64)
assert arr.dtype == SparseDtype(np.int64, 0)
assert arr.fill_value == 0
arr = SparseArray([0, 1, 2, 4], dtype=None)
assert arr.dtype == SparseDtype(np.int64, 0)
assert arr.fill_value == 0
arr = SparseArray([0, 1, 2, 4], fill_value=0, dtype=None)
assert arr.dtype == SparseDtype(np.int64, 0)
assert arr.fill_value == 0
def test_constructor_dtype_str(self):
result = SparseArray([1, 2, 3], dtype="int")
expected = SparseArray([1, 2, 3], dtype=int)
tm.assert_sp_array_equal(result, expected)
def test_constructor_sparse_dtype(self):
result = SparseArray([1, 0, 0, 1], dtype=SparseDtype("int64", -1))
expected = SparseArray([1, 0, 0, 1], fill_value=-1, dtype=np.int64)
tm.assert_sp_array_equal(result, expected)
assert result.sp_values.dtype == np.dtype("int64")
def test_constructor_sparse_dtype_str(self):
result = SparseArray([1, 0, 0, 1], dtype="Sparse[int32]")
expected = SparseArray([1, 0, 0, 1], dtype=np.int32)
tm.assert_sp_array_equal(result, expected)
assert result.sp_values.dtype == np.dtype("int32")
def test_constructor_object_dtype(self):
# GH 11856
arr = SparseArray(["A", "A", np.nan, "B"], dtype=np.object)
assert arr.dtype == SparseDtype(np.object)
assert np.isnan(arr.fill_value)
arr = SparseArray(["A", "A", np.nan, "B"],
dtype=np.object,
fill_value="A")
assert arr.dtype == SparseDtype(np.object, "A")
assert arr.fill_value == "A"
# GH 17574
data = [False, 0, 100.0, 0.0]
arr = SparseArray(data, dtype=np.object, fill_value=False)
assert arr.dtype == SparseDtype(np.object, False)
assert arr.fill_value is False
arr_expected = np.array(data, dtype=np.object)
it = (type(x) == type(y) and x == y for x, y in zip(arr, arr_expected))
assert np.fromiter(it, dtype=np.bool).all()
@pytest.mark.parametrize("dtype", [SparseDtype(int, 0), int])
def test_constructor_na_dtype(self, dtype):
with pytest.raises(ValueError, match="Cannot convert"):
SparseArray([0, 1, np.nan], dtype=dtype)
def test_constructor_spindex_dtype(self):
arr = SparseArray(data=[1, 2], sparse_index=IntIndex(4, [1, 2]))
# XXX: Behavior change: specifying SparseIndex no longer changes the
# fill_value
expected = SparseArray([0, 1, 2, 0], kind="integer")
tm.assert_sp_array_equal(arr, expected)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
arr = SparseArray(
data=[1, 2, 3],
sparse_index=IntIndex(4, [1, 2, 3]),
dtype=np.int64,
fill_value=0,
)
exp = SparseArray([0, 1, 2, 3], dtype=np.int64, fill_value=0)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
arr = SparseArray(data=[1, 2],
sparse_index=IntIndex(4, [1, 2]),
fill_value=0,
dtype=np.int64)
exp = SparseArray([0, 1, 2, 0], fill_value=0, dtype=np.int64)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
arr = SparseArray(
data=[1, 2, 3],
sparse_index=IntIndex(4, [1, 2, 3]),
dtype=None,
fill_value=0,
)
exp = SparseArray([0, 1, 2, 3], dtype=None)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
@pytest.mark.parametrize("sparse_index", [None, IntIndex(1, [0])])
def test_constructor_spindex_dtype_scalar(self, sparse_index):
# scalar input
arr = SparseArray(data=1, sparse_index=sparse_index, dtype=None)
exp = SparseArray([1], dtype=None)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
arr = SparseArray(data=1, sparse_index=IntIndex(1, [0]), dtype=None)
exp = SparseArray([1], dtype=None)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
def test_constructor_spindex_dtype_scalar_broadcasts(self):
arr = SparseArray(data=[1, 2],
sparse_index=IntIndex(4, [1, 2]),
fill_value=0,
dtype=None)
exp = SparseArray([0, 1, 2, 0], fill_value=0, dtype=None)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == SparseDtype(np.int64)
assert arr.fill_value == 0
@pytest.mark.parametrize(
"data, fill_value",
[
(np.array([1, 2]), 0),
(np.array([1.0, 2.0]), np.nan),
([True, False], False),
([pd.Timestamp("2017-01-01")], pd.NaT),
],
)
def test_constructor_inferred_fill_value(self, data, fill_value):
result = SparseArray(data).fill_value
if pd.isna(fill_value):
assert pd.isna(result)
else:
assert result == fill_value
@pytest.mark.parametrize("format", ["coo", "csc", "csr"])
@pytest.mark.parametrize(
"size",
[
pytest.param(
0, marks=td.skip_if_np_lt("1.16", reason="NumPy-11383")), 10
],
)
@td.skip_if_no_scipy
def test_from_spmatrix(self, size, format):
import scipy.sparse
mat = scipy.sparse.random(size, 1, density=0.5, format=format)
result = SparseArray.from_spmatrix(mat)
result = np.asarray(result)
expected = mat.toarray().ravel()
tm.assert_numpy_array_equal(result, expected)
@td.skip_if_no_scipy
def test_from_spmatrix_raises(self):
import scipy.sparse
mat = scipy.sparse.eye(5, 4, format="csc")
with pytest.raises(ValueError, match="not '4'"):
SparseArray.from_spmatrix(mat)
@pytest.mark.parametrize(
"scalar,dtype",
[
(False, SparseDtype(bool, False)),
(0.0, SparseDtype("float64", 0)),
(1, SparseDtype("int64", 1)),
("z", SparseDtype("object", "z")),
],
)
def test_scalar_with_index_infer_dtype(self, scalar, dtype):
# GH 19163
arr = SparseArray(scalar, index=[1, 2, 3], fill_value=scalar)
exp = SparseArray([scalar, scalar, scalar], fill_value=scalar)
tm.assert_sp_array_equal(arr, exp)
assert arr.dtype == dtype
assert exp.dtype == dtype
def test_get_item(self):
assert np.isnan(self.arr[1])
assert self.arr[2] == 1
assert self.arr[7] == 5
assert self.zarr[0] == 0
assert self.zarr[2] == 1
assert self.zarr[7] == 5
errmsg = re.compile("bounds")
with pytest.raises(IndexError, match=errmsg):
self.arr[11]
with pytest.raises(IndexError, match=errmsg):
self.arr[-11]
assert self.arr[-1] == self.arr[len(self.arr) - 1]
def test_take_scalar_raises(self):
msg = "'indices' must be an array, not a scalar '2'."
with pytest.raises(ValueError, match=msg):
self.arr.take(2)
def test_take(self):
exp = SparseArray(np.take(self.arr_data, [2, 3]))
tm.assert_sp_array_equal(self.arr.take([2, 3]), exp)
exp = SparseArray(np.take(self.arr_data, [0, 1, 2]))
tm.assert_sp_array_equal(self.arr.take([0, 1, 2]), exp)
def test_take_fill_value(self):
data = np.array([1, np.nan, 0, 3, 0])
sparse = SparseArray(data, fill_value=0)
exp = SparseArray(np.take(data, [0]), fill_value=0)
tm.assert_sp_array_equal(sparse.take([0]), exp)
exp = SparseArray(np.take(data, [1, 3, 4]), fill_value=0)
tm.assert_sp_array_equal(sparse.take([1, 3, 4]), exp)
def test_take_negative(self):
exp = SparseArray(np.take(self.arr_data, [-1]))
tm.assert_sp_array_equal(self.arr.take([-1]), exp)
exp = SparseArray(np.take(self.arr_data, [-4, -3, -2]))
tm.assert_sp_array_equal(self.arr.take([-4, -3, -2]), exp)
@pytest.mark.parametrize("fill_value", [0, None, np.nan])
def test_shift_fill_value(self, fill_value):
# GH #24128
sparse = SparseArray(np.array([1, 0, 0, 3, 0]), fill_value=8.0)
res = sparse.shift(1, fill_value=fill_value)
if isna(fill_value):
fill_value = res.dtype.na_value
exp = SparseArray(np.array([fill_value, 1, 0, 0, 3]), fill_value=8.0)
tm.assert_sp_array_equal(res, exp)
def test_bad_take(self):
with pytest.raises(IndexError, match="bounds"):
self.arr.take([11])
def test_take_filling(self):
# similar tests as GH 12631
sparse = SparseArray([np.nan, np.nan, 1, np.nan, 4])
result = sparse.take(np.array([1, 0, -1]))
expected = SparseArray([np.nan, np.nan, 4])
tm.assert_sp_array_equal(result, expected)
# XXX: test change: fill_value=True -> allow_fill=True
result = sparse.take(np.array([1, 0, -1]), allow_fill=True)
expected = SparseArray([np.nan, np.nan, np.nan])
tm.assert_sp_array_equal(result, expected)
# allow_fill=False
result = sparse.take(np.array([1, 0, -1]),
allow_fill=False,
fill_value=True)
expected = SparseArray([np.nan, np.nan, 4])
tm.assert_sp_array_equal(result, expected)
msg = "Invalid value in 'indices'"
with pytest.raises(ValueError, match=msg):
sparse.take(np.array([1, 0, -2]), allow_fill=True)
with pytest.raises(ValueError, match=msg):
sparse.take(np.array([1, 0, -5]), allow_fill=True)
with pytest.raises(IndexError):
sparse.take(np.array([1, -6]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]), allow_fill=True)
def test_take_filling_fill_value(self):
# same tests as GH 12631
sparse = SparseArray([np.nan, 0, 1, 0, 4], fill_value=0)
result = sparse.take(np.array([1, 0, -1]))
expected = SparseArray([0, np.nan, 4], fill_value=0)
tm.assert_sp_array_equal(result, expected)
# fill_value
result = sparse.take(np.array([1, 0, -1]), allow_fill=True)
# XXX: behavior change.
# the old way of filling self.fill_value doesn't follow EA rules.
# It's supposed to be self.dtype.na_value (nan in this case)
expected = SparseArray([0, np.nan, np.nan], fill_value=0)
tm.assert_sp_array_equal(result, expected)
# allow_fill=False
result = sparse.take(np.array([1, 0, -1]),
allow_fill=False,
fill_value=True)
expected = SparseArray([0, np.nan, 4], fill_value=0)
tm.assert_sp_array_equal(result, expected)
msg = "Invalid value in 'indices'."
with pytest.raises(ValueError, match=msg):
sparse.take(np.array([1, 0, -2]), allow_fill=True)
with pytest.raises(ValueError, match=msg):
sparse.take(np.array([1, 0, -5]), allow_fill=True)
with pytest.raises(IndexError):
sparse.take(np.array([1, -6]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]), fill_value=True)
def test_take_filling_all_nan(self):
sparse = SparseArray([np.nan, np.nan, np.nan, np.nan, np.nan])
# XXX: did the default kind from take change?
result = sparse.take(np.array([1, 0, -1]))
expected = SparseArray([np.nan, np.nan, np.nan], kind="block")
tm.assert_sp_array_equal(result, expected)
result = sparse.take(np.array([1, 0, -1]), fill_value=True)
expected = SparseArray([np.nan, np.nan, np.nan], kind="block")
tm.assert_sp_array_equal(result, expected)
with pytest.raises(IndexError):
sparse.take(np.array([1, -6]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]))
with pytest.raises(IndexError):
sparse.take(np.array([1, 5]), fill_value=True)
def test_set_item(self):
def setitem():
self.arr[5] = 3
def setslice():
self.arr[1:5] = 2
with pytest.raises(TypeError, match="assignment via setitem"):
setitem()
with pytest.raises(TypeError, match="assignment via setitem"):
setslice()
def test_constructor_from_too_large_array(self):
with pytest.raises(TypeError, match="expected dimension <= 1 data"):
SparseArray(np.arange(10).reshape((2, 5)))
def test_constructor_from_sparse(self):
res = SparseArray(self.zarr)
assert res.fill_value == 0
assert_almost_equal(res.sp_values, self.zarr.sp_values)
def test_constructor_copy(self):
cp = SparseArray(self.arr, copy=True)
cp.sp_values[:3] = 0
assert not (self.arr.sp_values[:3] == 0).any()
not_copy = SparseArray(self.arr)
not_copy.sp_values[:3] = 0
assert (self.arr.sp_values[:3] == 0).all()
def test_constructor_bool(self):
# GH 10648
data = np.array([False, False, True, True, False, False])
arr = SparseArray(data, fill_value=False, dtype=bool)
assert arr.dtype == SparseDtype(bool)
tm.assert_numpy_array_equal(arr.sp_values, np.array([True, True]))
# Behavior change: np.asarray densifies.
# tm.assert_numpy_array_equal(arr.sp_values, np.asarray(arr))
tm.assert_numpy_array_equal(arr.sp_index.indices,
np.array([2, 3], np.int32))
dense = arr.to_dense()
assert dense.dtype == bool
tm.assert_numpy_array_equal(dense, data)
def test_constructor_bool_fill_value(self):
arr = SparseArray([True, False, True], dtype=None)
assert arr.dtype == SparseDtype(np.bool)
assert not arr.fill_value
arr = SparseArray([True, False, True], dtype=np.bool)
assert arr.dtype == SparseDtype(np.bool)
assert not arr.fill_value
arr = SparseArray([True, False, True], dtype=np.bool, fill_value=True)
assert arr.dtype == SparseDtype(np.bool, True)
assert arr.fill_value
def test_constructor_float32(self):
# GH 10648
data = np.array([1.0, np.nan, 3], dtype=np.float32)
arr = SparseArray(data, dtype=np.float32)
assert arr.dtype == SparseDtype(np.float32)
tm.assert_numpy_array_equal(arr.sp_values,
np.array([1, 3], dtype=np.float32))
# Behavior change: np.asarray densifies.
# tm.assert_numpy_array_equal(arr.sp_values, np.asarray(arr))
tm.assert_numpy_array_equal(arr.sp_index.indices,
np.array([0, 2], dtype=np.int32))
dense = arr.to_dense()
assert dense.dtype == np.float32
tm.assert_numpy_array_equal(dense, data)
def test_astype(self):
# float -> float
arr = SparseArray([None, None, 0, 2])
result = arr.astype("Sparse[float32]")
expected = SparseArray([None, None, 0, 2], dtype=np.dtype("float32"))
tm.assert_sp_array_equal(result, expected)
dtype = SparseDtype("float64", fill_value=0)
result = arr.astype(dtype)
expected = SparseArray._simple_new(
np.array([0.0, 2.0], dtype=dtype.subtype), IntIndex(4, [2, 3]),
dtype)
tm.assert_sp_array_equal(result, expected)
dtype = SparseDtype("int64", 0)
result = arr.astype(dtype)
expected = SparseArray._simple_new(np.array([0, 2], dtype=np.int64),
IntIndex(4, [2, 3]), dtype)
tm.assert_sp_array_equal(result, expected)
arr = SparseArray([0, np.nan, 0, 1], fill_value=0)
with pytest.raises(ValueError, match="NA"):
arr.astype("Sparse[i8]")
def test_astype_bool(self):
a = pd.SparseArray([1, 0, 0, 1], dtype=SparseDtype(int, 0))
result = a.astype(bool)
expected = SparseArray([True, 0, 0, True], dtype=SparseDtype(bool, 0))
tm.assert_sp_array_equal(result, expected)
# update fill value
result = a.astype(SparseDtype(bool, False))
expected = SparseArray([True, False, False, True],
dtype=SparseDtype(bool, False))
tm.assert_sp_array_equal(result, expected)
def test_astype_all(self, any_real_dtype):
vals = np.array([1, 2, 3])
arr = SparseArray(vals, fill_value=1)
typ = np.dtype(any_real_dtype)
res = arr.astype(typ)
assert res.dtype == SparseDtype(typ, 1)
assert res.sp_values.dtype == typ
tm.assert_numpy_array_equal(np.asarray(res.to_dense()),
vals.astype(typ))
@pytest.mark.parametrize(
"array, dtype, expected",
[
(
SparseArray([0, 1]),
"float",
SparseArray([0.0, 1.0], dtype=SparseDtype(float, 0.0)),
),
(SparseArray([0, 1]), bool, SparseArray([False, True])),
(
SparseArray([0, 1], fill_value=1),
bool,
SparseArray([False, True], dtype=SparseDtype(bool, True)),
),
pytest.param(
SparseArray([0, 1]),
"datetime64[ns]",
SparseArray(
np.array([0, 1], dtype="datetime64[ns]"),
dtype=SparseDtype("datetime64[ns]", pd.Timestamp("1970")),
),
marks=[pytest.mark.xfail(reason="NumPy-7619")],
),
(
SparseArray([0, 1, 10]),
str,
SparseArray(["0", "1", "10"], dtype=SparseDtype(str, "0")),
),
(SparseArray(["10", "20"]), float, SparseArray([10.0, 20.0])),
(
SparseArray([0, 1, 0]),
object,
SparseArray([0, 1, 0], dtype=SparseDtype(object, 0)),
),
],
)
def test_astype_more(self, array, dtype, expected):
result = array.astype(dtype)
tm.assert_sp_array_equal(result, expected)
def test_astype_nan_raises(self):
arr = SparseArray([1.0, np.nan])
with pytest.raises(ValueError, match="Cannot convert non-finite"):
arr.astype(int)
def test_set_fill_value(self):
arr = SparseArray([1.0, np.nan, 2.0], fill_value=np.nan)
arr.fill_value = 2
assert arr.fill_value == 2
arr = SparseArray([1, 0, 2], fill_value=0, dtype=np.int64)
arr.fill_value = 2
assert arr.fill_value == 2
# XXX: this seems fine? You can construct an integer
# sparsearray with NaN fill value, why not update one?
# coerces to int
# msg = "unable to set fill_value 3\\.1 to int64 dtype"
# with pytest.raises(ValueError, match=msg):
arr.fill_value = 3.1
assert arr.fill_value == 3.1
# msg = "unable to set fill_value nan to int64 dtype"
# with pytest.raises(ValueError, match=msg):
arr.fill_value = np.nan
assert np.isnan(arr.fill_value)
arr = SparseArray([True, False, True], fill_value=False, dtype=np.bool)
arr.fill_value = True
assert arr.fill_value
# coerces to bool
# msg = "unable to set fill_value 0 to bool dtype"
# with pytest.raises(ValueError, match=msg):
arr.fill_value = 0
assert arr.fill_value == 0
# msg = "unable to set fill_value nan to bool dtype"
# with pytest.raises(ValueError, match=msg):
arr.fill_value = np.nan
assert np.isnan(arr.fill_value)
@pytest.mark.parametrize("val", [[1, 2, 3], np.array([1, 2]), (1, 2, 3)])
def test_set_fill_invalid_non_scalar(self, val):
arr = SparseArray([True, False, True], fill_value=False, dtype=np.bool)
msg = "fill_value must be a scalar"
with pytest.raises(ValueError, match=msg):
arr.fill_value = val
def test_copy(self):
arr2 = self.arr.copy()
assert arr2.sp_values is not self.arr.sp_values
assert arr2.sp_index is self.arr.sp_index
def test_values_asarray(self):
assert_almost_equal(self.arr.to_dense(), self.arr_data)
@pytest.mark.parametrize(
"data,shape,dtype",
[
([0, 0, 0, 0, 0], (5, ), None),
([], (0, ), None),
([0], (1, ), None),
(["A", "A", np.nan, "B"], (4, ), np.object),
],
)
def test_shape(self, data, shape, dtype):
# GH 21126
out = SparseArray(data, dtype=dtype)
assert out.shape == shape
@pytest.mark.parametrize(
"vals",
[
[np.nan, np.nan, np.nan, np.nan, np.nan],
[1, np.nan, np.nan, 3, np.nan],
[1, np.nan, 0, 3, 0],
],
)
@pytest.mark.parametrize("fill_value", [None, 0])
def test_dense_repr(self, vals, fill_value):
vals = np.array(vals)
arr = SparseArray(vals, fill_value=fill_value)
res = arr.to_dense()
tm.assert_numpy_array_equal(res, vals)
with tm.assert_produces_warning(FutureWarning):
res2 = arr.get_values()
tm.assert_numpy_array_equal(res2, vals)
def test_getitem(self):
def _checkit(i):
assert_almost_equal(self.arr[i], self.arr.to_dense()[i])
for i in range(len(self.arr)):
_checkit(i)
_checkit(-i)
def test_getitem_arraylike_mask(self):
arr = SparseArray([0, 1, 2])
result = arr[[True, False, True]]
expected = SparseArray([0, 2])
tm.assert_sp_array_equal(result, expected)
def test_getslice(self):
result = self.arr[:-3]
exp = SparseArray(self.arr.to_dense()[:-3])
tm.assert_sp_array_equal(result, exp)
result = self.arr[-4:]
exp = SparseArray(self.arr.to_dense()[-4:])
tm.assert_sp_array_equal(result, exp)
# two corner cases from Series
result = self.arr[-12:]
exp = SparseArray(self.arr)
tm.assert_sp_array_equal(result, exp)
result = self.arr[:-12]
exp = SparseArray(self.arr.to_dense()[:0])
tm.assert_sp_array_equal(result, exp)
def test_getslice_tuple(self):
dense = np.array([np.nan, 0, 3, 4, 0, 5, np.nan, np.nan, 0])
sparse = SparseArray(dense)
res = sparse[4:, ] # noqa: E231
exp = SparseArray(dense[4:, ]) # noqa: E231
tm.assert_sp_array_equal(res, exp)
sparse = SparseArray(dense, fill_value=0)
res = sparse[4:, ] # noqa: E231
exp = SparseArray(dense[4:, ], fill_value=0) # noqa: E231
tm.assert_sp_array_equal(res, exp)
with pytest.raises(IndexError):
sparse[4:, :]
with pytest.raises(IndexError):
# check numpy compat
dense[4:, :]
def test_boolean_slice_empty(self):
arr = pd.SparseArray([0, 1, 2])
res = arr[[False, False, False]]
assert res.dtype == arr.dtype
@pytest.mark.parametrize(
"op", ["add", "sub", "mul", "truediv", "floordiv", "pow"])
def test_binary_operators(self, op):
op = getattr(operator, op)
data1 = np.random.randn(20)
data2 = np.random.randn(20)
data1[::2] = np.nan
data2[::3] = np.nan
arr1 = SparseArray(data1)
arr2 = SparseArray(data2)
data1[::2] = 3
data2[::3] = 3
farr1 = SparseArray(data1, fill_value=3)
farr2 = SparseArray(data2, fill_value=3)
def _check_op(op, first, second):
res = op(first, second)
exp = SparseArray(op(first.to_dense(), second.to_dense()),
fill_value=first.fill_value)
assert isinstance(res, SparseArray)
assert_almost_equal(res.to_dense(), exp.to_dense())
res2 = op(first, second.to_dense())
assert isinstance(res2, SparseArray)
tm.assert_sp_array_equal(res, res2)
res3 = op(first.to_dense(), second)
assert isinstance(res3, SparseArray)
tm.assert_sp_array_equal(res, res3)
res4 = op(first, 4)
assert isinstance(res4, SparseArray)
# Ignore this if the actual op raises (e.g. pow).
try:
exp = op(first.to_dense(), 4)
exp_fv = op(first.fill_value, 4)
except ValueError:
pass
else:
assert_almost_equal(res4.fill_value, exp_fv)
assert_almost_equal(res4.to_dense(), exp)
with np.errstate(all="ignore"):
for first_arr, second_arr in [(arr1, arr2), (farr1, farr2)]:
_check_op(op, first_arr, second_arr)
def test_pickle(self):
def _check_roundtrip(obj):
unpickled = tm.round_trip_pickle(obj)
tm.assert_sp_array_equal(unpickled, obj)
_check_roundtrip(self.arr)
_check_roundtrip(self.zarr)
def test_generator_warnings(self):
sp_arr = SparseArray([1, 2, 3])
with warnings.catch_warnings(record=True) as w:
warnings.filterwarnings(action="always",
category=DeprecationWarning)
warnings.filterwarnings(action="always",
category=PendingDeprecationWarning)
for _ in sp_arr:
pass
assert len(w) == 0
def test_fillna(self):
s = SparseArray([1, np.nan, np.nan, 3, np.nan])
res = s.fillna(-1)
exp = SparseArray([1, -1, -1, 3, -1], fill_value=-1, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([1, np.nan, np.nan, 3, np.nan], fill_value=0)
res = s.fillna(-1)
exp = SparseArray([1, -1, -1, 3, -1], fill_value=0, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([1, np.nan, 0, 3, 0])
res = s.fillna(-1)
exp = SparseArray([1, -1, 0, 3, 0], fill_value=-1, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([1, np.nan, 0, 3, 0], fill_value=0)
res = s.fillna(-1)
exp = SparseArray([1, -1, 0, 3, 0], fill_value=0, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([np.nan, np.nan, np.nan, np.nan])
res = s.fillna(-1)
exp = SparseArray([-1, -1, -1, -1], fill_value=-1, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
s = SparseArray([np.nan, np.nan, np.nan, np.nan], fill_value=0)
res = s.fillna(-1)
exp = SparseArray([-1, -1, -1, -1], fill_value=0, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
# float dtype's fill_value is np.nan, replaced by -1
s = SparseArray([0.0, 0.0, 0.0, 0.0])
res = s.fillna(-1)
exp = SparseArray([0.0, 0.0, 0.0, 0.0], fill_value=-1)
tm.assert_sp_array_equal(res, exp)
# int dtype shouldn't have missing. No changes.
s = SparseArray([0, 0, 0, 0])
assert s.dtype == SparseDtype(np.int64)
assert s.fill_value == 0
res = s.fillna(-1)
tm.assert_sp_array_equal(res, s)
s = SparseArray([0, 0, 0, 0], fill_value=0)
assert s.dtype == SparseDtype(np.int64)
assert s.fill_value == 0
res = s.fillna(-1)
exp = SparseArray([0, 0, 0, 0], fill_value=0)
tm.assert_sp_array_equal(res, exp)
# fill_value can be nan if there is no missing hole.
# only fill_value will be changed
s = SparseArray([0, 0, 0, 0], fill_value=np.nan)
assert s.dtype == SparseDtype(np.int64, fill_value=np.nan)
assert np.isnan(s.fill_value)
res = s.fillna(-1)
exp = SparseArray([0, 0, 0, 0], fill_value=-1)
tm.assert_sp_array_equal(res, exp)
def test_fillna_overlap(self):
s = SparseArray([1, np.nan, np.nan, 3, np.nan])
# filling with existing value doesn't replace existing value with
# fill_value, i.e. existing 3 remains in sp_values
res = s.fillna(3)
exp = np.array([1, 3, 3, 3, 3], dtype=np.float64)
tm.assert_numpy_array_equal(res.to_dense(), exp)
s = SparseArray([1, np.nan, np.nan, 3, np.nan], fill_value=0)
res = s.fillna(3)
exp = SparseArray([1, 3, 3, 3, 3], fill_value=0, dtype=np.float64)
tm.assert_sp_array_equal(res, exp)
def test_nonzero(self):
# Tests regression #21172.
sa = pd.SparseArray(
[float("nan"),
float("nan"), 1, 0, 0, 2, 0, 0, 0, 3, 0, 0])
expected = np.array([2, 5, 9], dtype=np.int32)
result, = sa.nonzero()
tm.assert_numpy_array_equal(expected, result)
sa = pd.SparseArray([0, 0, 1, 0, 0, 2, 0, 0, 0, 3, 0, 0])
result, = sa.nonzero()
tm.assert_numpy_array_equal(expected, result)
