def test_series_set_equal_length_object_by_mask(replace_data):
psr = pd.Series([1, 2, 3, 4, 5])
gsr = Series.from_pandas(psr)
# Lengths match in trivial case
pd_bool_col = pd.Series([True] * len(psr))
gd_bool_col = Series.from_pandas(pd_bool_col)
psr[pd_bool_col] = (
replace_data.to_pandas()
if hasattr(replace_data, "to_pandas")
else replace_data
)
gsr[gd_bool_col] = replace_data
assert_eq(psr.astype("float"), gsr.astype("float"))
# Test partial masking
psr[psr > 1] = (
replace_data.to_pandas()
if hasattr(replace_data, "to_pandas")
else replace_data
)
gsr[gsr > 1] = replace_data
assert_eq(psr.astype("float"), gsr.astype("float"))
def test_series_set_item(psr, arg):
gsr = Series.from_pandas(psr)
psr[arg] = 11
gsr[arg] = 11
assert_eq(psr, gsr)
def test_scan_boolean_cumprod():
s = Series([0, -1, -300, 23, 4, -3, 0, 0, 100])
# cumprod test
got = (s > 0).cumprod()
expect = (s > 0).to_pandas().cumprod()
assert_eq(expect, got)
def test_series_setitem_index():
df = pd.DataFrame(
data={"b": [-1, -2, -3], "c": [1, 2, 3]}, index=[1, 2, 3]
)
df["b"] = pd.Series(data=[12, 11, 10], index=[3, 2, 1])
gdf = DataFrame(data={"b": [-1, -2, -3], "c": [1, 2, 3]}, index=[1, 2, 3])
gdf["b"] = Series(data=[12, 11, 10], index=[3, 2, 1])
assert_eq(df, gdf, check_dtype=False)
def test_column_set_equal_length_object_by_mask():
# Series.__setitem__ might bypass some of the cases
# handled in column.__setitem__ so this test is needed
data = Series([0, 0, 1, 1, 1])._column
replace_data = Series([100, 200, 300, 400, 500])._column
bool_col = Series([True, True, True, True, True])._column
data[bool_col] = replace_data
assert_eq(Series(data), Series(replace_data))
data = Series([0, 0, 1, 1, 1])._column
bool_col = Series([True, False, True, False, True])._column
data[bool_col] = replace_data
assert_eq(Series(data), Series([100, 0, 300, 1, 500]))
def test_cummin(dtype, nelem):
if dtype == np.int8:
# to keep data in range
data = gen_rand(dtype, nelem, low=-2, high=2)
else:
data = gen_rand(dtype, nelem)
decimal = 4 if dtype == np.float32 else 6
# series
gs = Series(data)
ps = pd.Series(data)
np.testing.assert_array_almost_equal(gs.cummin().to_array(),
ps.cummin(),
decimal=decimal)
# dataframe series (named series)
gdf = DataFrame()
gdf["a"] = Series(data)
pdf = pd.DataFrame()
pdf["a"] = pd.Series(data)
np.testing.assert_array_almost_equal(gdf.a.cummin().to_array(),
pdf.a.cummin(),
decimal=decimal)
def test_cummin_masked():
data = [1, 2, None, 4, 5]
float_types = ["float32", "float64"]
for type_ in float_types:
gs = Series(data).astype(type_)
ps = pd.Series(data).astype(type_)
assert_eq(gs.cummin(), ps.cummin())
for type_ in INTEGER_TYPES:
gs = Series(data).astype(type_)
expected = pd.Series([1, 1, np.nan, 1, 1]).astype("float64")
assert_eq(gs.cummin(), expected)
def test_cumsum_masked():
data = [1, 2, None, 4, 5]
float_types = ["float32", "float64"]
for type_ in float_types:
gs = Series(data).astype(type_)
ps = pd.Series(data).astype(type_)
assert_eq(gs.cumsum(), ps.cumsum())
for type_ in INTEGER_TYPES:
gs = Series(data).astype(type_)
got = gs.cumsum()
expected = pd.Series([1, 3, np.nan, 7, 12], dtype="float64")
assert_eq(got, expected)
def test_cummin_masked():
data = [1, 2, None, 4, 5]
float_types = ["float32", "float64"]
int_types = ["int8", "int16", "int32", "int64"]
for type_ in float_types:
gs = Series(data).astype(type_)
ps = pd.Series(data).astype(type_)
assert_eq(gs.cummin(), ps.cummin())
for type_ in int_types:
expected = pd.Series([1, 1, -1, 1, 1]).astype(type_)
gs = Series(data).astype(type_)
assert_eq(gs.cummin(), expected)
assert_eq(pdf, gdf)
psr_a = pdf["a"]
gsr_a = gdf["a"]
psr_a.replace(500, 501, inplace=True)
gsr_a.replace(500, 501, inplace=True)
assert_eq(pdf, gdf)
@pytest.mark.parametrize(
"replace_data",
[
[100, 200, 300, 400, 500],
Series([100, 200, 300, 400, 500]),
Series([100, 200, 300, 400, 500], index=[2, 3, 4, 5, 6]),
],
)
def test_series_set_equal_length_object_by_mask(replace_data):
psr = pd.Series([1, 2, 3, 4, 5])
gsr = Series.from_pandas(psr)
# Lengths match in trivial case
pd_bool_col = pd.Series([True] * len(psr))
gd_bool_col = Series.from_pandas(pd_bool_col)
psr[pd_bool_col] = (
replace_data.to_pandas()
if hasattr(replace_data, "to_pandas")