def test_constructor_object_dtype(self):
# GH 11856
arr = SparseArray(["A", "A", np.nan, "B"], dtype=object)
assert arr.dtype == SparseDtype(object)
assert np.isnan(arr.fill_value)
arr = SparseArray(["A", "A", np.nan, "B"], dtype=object, fill_value="A")
assert arr.dtype == SparseDtype(object, "A")
assert arr.fill_value == "A"
# GH 17574
data = [False, 0, 100.0, 0.0]
arr = SparseArray(data, dtype=object, fill_value=False)
assert arr.dtype == SparseDtype(object, False)
assert arr.fill_value is False
arr_expected = np.array(data, dtype=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_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
def test_get_dummies_all_sparse(self):
df = pd.DataFrame({"A": [1, 2]})
result = pd.get_dummies(df, columns=["A"], sparse=True)
dtype = SparseDtype("uint8", 0)
expected = pd.DataFrame({
"A_1": SparseArray([1, 0], dtype=dtype),
"A_2": SparseArray([0, 1], dtype=dtype),
})
tm.assert_frame_equal(result, expected)
def test_fill_value(self, fill_value, max_expected, min_expected):
arr = SparseArray(
np.array([fill_value, 0, 1]), dtype=SparseDtype("int", fill_value)
)
max_result = arr.max()
assert max_result == max_expected
min_result = arr.min()
assert min_result == min_expected
def test_only_fill_value(self):
fv = 100
arr = SparseArray(np.array([fv, fv, fv]), dtype=SparseDtype("int", fv))
assert len(arr._valid_sp_values) == 0
assert arr.max() == fv
assert arr.min() == fv
assert arr.max(skipna=False) == fv
assert arr.min(skipna=False) == fv
def test_to_dense(self):
df = pd.DataFrame(
{
"A": SparseArray([1, 0], dtype=SparseDtype("int64", 0)),
"B": SparseArray([1, 0], dtype=SparseDtype("int64", 1)),
"C": SparseArray([1.0, 0.0], dtype=SparseDtype("float64",
0.0)),
},
index=["b", "a"],
)
result = df.sparse.to_dense()
expected = pd.DataFrame({
"A": [1, 0],
"B": [1, 0],
"C": [1.0, 0.0]
},
index=["b", "a"])
tm.assert_frame_equal(result, expected)
def test_from_spmatrix_columns(self, columns):
import scipy.sparse
dtype = SparseDtype("float64", 0.0)
mat = scipy.sparse.random(10, 2, density=0.5)
result = pd.DataFrame.sparse.from_spmatrix(mat, columns=columns)
expected = pd.DataFrame(mat.toarray(), columns=columns).astype(dtype)
tm.assert_frame_equal(result, expected)
def test_from_spmatrix_including_explicit_zero(self, format):
import scipy.sparse
mat = scipy.sparse.random(10, 2, density=0.5, format=format)
mat.data[0] = 0
result = pd.DataFrame.sparse.from_spmatrix(mat)
dtype = SparseDtype("float64", 0.0)
expected = pd.DataFrame(mat.todense()).astype(dtype)
tm.assert_frame_equal(result, expected)
def test_astype_all(self, any_real_numpy_dtype):
vals = np.array([1, 2, 3])
arr = SparseArray(vals, fill_value=1)
typ = np.dtype(any_real_numpy_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))
def test_from_spmatrix(self, format, labels, dtype):
import scipy.sparse
sp_dtype = SparseDtype(dtype, np.array(0, dtype=dtype).item())
mat = scipy.sparse.eye(10, format=format, dtype=dtype)
result = pd.DataFrame.sparse.from_spmatrix(mat, index=labels, columns=labels)
expected = pd.DataFrame(
np.eye(10, dtype=dtype), index=labels, columns=labels
).astype(sp_dtype)
tm.assert_frame_equal(result, expected)
def test_setting_fill_value_updates():
arr = SparseArray([0.0, np.nan], fill_value=0)
arr.fill_value = np.nan
# use private constructor to get the index right
# otherwise both nans would be un-stored.
expected = SparseArray._simple_new(
sparse_array=np.array([np.nan]),
sparse_index=IntIndex(2, [1]),
dtype=SparseDtype(float, np.nan),
)
tm.assert_sp_array_equal(arr, expected)
def test_astype_all(self, any_real_numpy_dtype):
vals = np.array([1, 2, 3])
arr = SparseArray(vals, fill_value=1)
typ = np.dtype(any_real_numpy_dtype)
with tm.assert_produces_warning(FutureWarning,
match="astype from Sparse"):
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))
def test_constructor_spindex_dtype(self):
arr = SparseArray(data=[1, 2], sparse_index=IntIndex(4, [1, 2]))
# TODO: actionable?
# 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
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_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_mixed_array_float_int(self, kind, mix, all_arithmetic_functions, request):
op = all_arithmetic_functions
if (
not np_version_under1p20
and op in [operator.floordiv, ops.rfloordiv]
and mix
):
mark = pytest.mark.xfail(raises=AssertionError, reason="GH#38172")
request.node.add_marker(mark)
rdtype = "int64"
values = self._base([np.nan, 1, 2, 0, np.nan, 0, 1, 2, 1, np.nan])
rvalues = self._base([2, 0, 2, 3, 0, 0, 1, 5, 2, 0], dtype=rdtype)
a = self._klass(values, kind=kind)
b = self._klass(rvalues, kind=kind)
assert b.dtype == SparseDtype(rdtype)
self._check_numeric_ops(a, b, values, rvalues, mix, op)
self._check_numeric_ops(a, b * 0, values, rvalues * 0, mix, op)
a = self._klass(values, kind=kind, fill_value=0)
b = self._klass(rvalues, kind=kind)
assert b.dtype == SparseDtype(rdtype)
self._check_numeric_ops(a, b, values, rvalues, mix, op)
a = self._klass(values, kind=kind, fill_value=0)
b = self._klass(rvalues, kind=kind, fill_value=0)
assert b.dtype == SparseDtype(rdtype)
self._check_numeric_ops(a, b, values, rvalues, mix, op)
a = self._klass(values, kind=kind, fill_value=1)
b = self._klass(rvalues, kind=kind, fill_value=2)
assert b.dtype == SparseDtype(rdtype, fill_value=2)
self._check_numeric_ops(a, b, values, rvalues, mix, op)
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_dataframe_dummies_subset(self, df, sparse):
result = get_dummies(df, prefix=["from_A"], columns=["A"], sparse=sparse)
expected = DataFrame(
{
"B": ["b", "b", "c"],
"C": [1, 2, 3],
"from_A_a": [1, 0, 1],
"from_A_b": [0, 1, 0],
},
dtype=np.uint8,
)
expected[["C"]] = df[["C"]]
if sparse:
cols = ["from_A_a", "from_A_b"]
expected[cols] = expected[cols].astype(SparseDtype("uint8", 0))
tm.assert_frame_equal(result, expected)
def test_dataframe_dummies_mix_default(self, df, sparse, dtype):
result = get_dummies(df, sparse=sparse, dtype=dtype)
if sparse:
arr = SparseArray
typ = SparseDtype(dtype, 0)
else:
arr = np.array
typ = dtype
expected = DataFrame({
"C": [1, 2, 3],
"A_a": arr([1, 0, 1], dtype=typ),
"A_b": arr([0, 1, 0], dtype=typ),
"B_b": arr([1, 1, 0], dtype=typ),
"B_c": arr([0, 0, 1], dtype=typ),
})
expected = expected[["C", "A_a", "A_b", "B_b", "B_c"]]
tm.assert_frame_equal(result, expected)
def test_dataframe_dummies_with_categorical(self, df, sparse, dtype):
df["cat"] = pd.Categorical(["x", "y", "y"])
result = get_dummies(df, sparse=sparse, dtype=dtype).sort_index(axis=1)
if sparse:
arr = SparseArray
typ = SparseDtype(dtype, 0)
else:
arr = np.array
typ = dtype
expected = DataFrame({
"C": [1, 2, 3],
"A_a": arr([1, 0, 1], dtype=typ),
"A_b": arr([0, 1, 0], dtype=typ),
"B_b": arr([1, 1, 0], dtype=typ),
"B_c": arr([0, 0, 1], dtype=typ),
"cat_x": arr([1, 0, 0], dtype=typ),
"cat_y": arr([0, 1, 1], dtype=typ),
}).sort_index(axis=1)
tm.assert_frame_equal(result, expected)
def test_dataframe_dummies_prefix_dict(self, sparse):
prefixes = {"A": "from_A", "B": "from_B"}
df = DataFrame({"C": [1, 2, 3], "A": ["a", "b", "a"], "B": ["b", "b", "c"]})
result = get_dummies(df, prefix=prefixes, sparse=sparse)
expected = DataFrame(
{
"C": [1, 2, 3],
"from_A_a": [1, 0, 1],
"from_A_b": [0, 1, 0],
"from_B_b": [1, 1, 0],
"from_B_c": [0, 0, 1],
}
)
columns = ["from_A_a", "from_A_b", "from_B_b", "from_B_c"]
expected[columns] = expected[columns].astype(np.uint8)
if sparse:
expected[columns] = expected[columns].astype(SparseDtype("uint8", 0))
tm.assert_frame_equal(result, expected)
def test_locindexer_from_spmatrix(self, spmatrix_t, dtype):
import scipy.sparse
spmatrix_t = getattr(scipy.sparse, spmatrix_t)
# The bug is triggered by a sparse matrix with purely sparse columns. So the
# recipe below generates a rectangular matrix of dimension (5, 7) where all the
# diagonal cells are ones, meaning the last two columns are purely sparse.
rows, cols = 5, 7
spmatrix = spmatrix_t(np.eye(rows, cols, dtype=dtype), dtype=dtype)
df = pd.DataFrame.sparse.from_spmatrix(spmatrix)
# regression test for #34526
itr_idx = range(2, rows)
result = df.loc[itr_idx].values
expected = spmatrix.toarray()[itr_idx]
tm.assert_numpy_array_equal(result, expected)
# regression test for #34540
result = df.loc[itr_idx].dtypes.values
expected = np.full(cols, SparseDtype(dtype, fill_value=0))
tm.assert_numpy_array_equal(result, expected)
assert registry.find(dtype) == expected
@pytest.mark.parametrize(
"dtype, expected",
[
(str, False),
(int, False),
(bool, True),
(np.bool, True),
(np.array(["a", "b"]), False),
(pd.Series([1, 2]), False),
(np.array([True, False]), True),
(pd.Series([True, False]), True),
(pd.SparseArray([True, False]), True),
(SparseDtype(bool), True),
],
)
def test_is_bool_dtype(dtype, expected):
result = is_bool_dtype(dtype)
assert result is expected
def test_is_bool_dtype_sparse():
result = is_bool_dtype(pd.Series(pd.SparseArray([True, False])))
assert result is True
@pytest.mark.parametrize(
"check",
[
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")
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
tm.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):
tm.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):
tm.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)
tm.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:
tm.assert_almost_equal(res4.fill_value, exp_fv)
tm.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)
def test_construct_from_string_raises():
with pytest.raises(
TypeError,
match="Cannot construct a 'SparseDtype' from 'not a dtype'"):
SparseDtype.construct_from_string("not a dtype")
def test_nans_equal():
a = SparseDtype(float, float("nan"))
b = SparseDtype(float, np.nan)
assert a == b
assert b == a
def test_equal(dtype, fill_value):
a = SparseDtype(dtype, fill_value)
b = SparseDtype(dtype, fill_value)
assert a == b
assert b == a
def test_from_sparse_dtype_fill_value():
dtype = SparseDtype("int", 1)
result = SparseDtype(dtype, fill_value=2)
expected = SparseDtype("int", 2)
assert result == expected
def test_from_sparse_dtype():
dtype = SparseDtype("float", 0)
result = SparseDtype(dtype)
assert result.fill_value == 0
