def test_validity_add(nelem, lhs_nulls, rhs_nulls):
np.random.seed(0)
# LHS
lhs_data = np.random.random(nelem)
if lhs_nulls == "some":
lhs_mask = utils.random_bitmask(nelem)
lhs_bitmask = utils.expand_bits_to_bytes(lhs_mask)[:nelem]
lhs_null_count = utils.count_zero(lhs_bitmask)
assert lhs_null_count >= 0
lhs = Series.from_masked_array(lhs_data, lhs_mask)
assert lhs.null_count == lhs_null_count
else:
lhs = Series(lhs_data)
# RHS
rhs_data = np.random.random(nelem)
if rhs_nulls == "some":
rhs_mask = utils.random_bitmask(nelem)
rhs_bitmask = utils.expand_bits_to_bytes(rhs_mask)[:nelem]
rhs_null_count = utils.count_zero(rhs_bitmask)
assert rhs_null_count >= 0
rhs = Series.from_masked_array(rhs_data, rhs_mask)
assert rhs.null_count == rhs_null_count
else:
rhs = Series(rhs_data)
# Result
res = lhs + rhs
if lhs_nulls == "some" and rhs_nulls == "some":
res_mask = np.asarray(
utils.expand_bits_to_bytes(lhs_mask & rhs_mask), dtype=np.bool
)[:nelem]
if lhs_nulls == "some" and rhs_nulls == "none":
res_mask = np.asarray(
utils.expand_bits_to_bytes(lhs_mask), dtype=np.bool
)[:nelem]
if lhs_nulls == "none" and rhs_nulls == "some":
res_mask = np.asarray(
utils.expand_bits_to_bytes(rhs_mask), dtype=np.bool
)[:nelem]
# Fill NA values
na_value = -10000
got = res.fillna(na_value).to_array()
expect = lhs_data + rhs_data
if lhs_nulls == "some" or rhs_nulls == "some":
expect[~res_mask] = na_value
np.testing.assert_array_equal(expect, got)
def test_serialize_masked_series():
nelem = 50
data = np.random.random(nelem)
mask = utils.random_bitmask(nelem)
bitmask = utils.expand_bits_to_bytes(mask)[:nelem]
null_count = utils.count_zero(bitmask)
assert null_count >= 0
sr = cudf.Series.from_masked_array(data, mask, null_count=null_count)
outsr = cudf.Series.deserialize(*sr.serialize())
assert_eq(sr, outsr)
def test_serialize_masked_series():
nelem = 50
data = np.random.random(nelem)
mask = utils.random_bitmask(nelem)
bitmask = utils.expand_bits_to_bytes(mask)[:nelem]
null_count = utils.count_zero(bitmask)
assert null_count >= 0
sr = cudf.Series.from_masked_array(data, mask, null_count=null_count)
outsr = deserialize(*serialize(sr))
pd.util.testing.assert_series_equal(sr.to_pandas(), outsr.to_pandas())
def test_sum_masked(nelem):
dtype = np.float64
data = gen_rand(dtype, nelem)
mask = utils.random_bitmask(nelem)
bitmask = utils.expand_bits_to_bytes(mask)[:nelem]
null_count = utils.count_zero(bitmask)
sr = Series.from_masked_array(data, mask, null_count)
got = sr.sum()
res_mask = np.asarray(bitmask, dtype=np.bool_)[: data.size]
expect = data[res_mask].sum()
significant = 4 if dtype == np.float32 else 6
np.testing.assert_approx_equal(expect, got, significant=significant)
