def test_cython_group_transform_algos():
# see gh-4095
is_datetimelike = False
# with nans
labels = np.array([0, 0, 0, 0, 0], dtype=np.int64)
ngroups = 1
data = np.array([[1], [2], [3], [np.nan], [4]], dtype="float64")
actual = np.zeros_like(data)
actual.fill(np.nan)
group_cumprod_float64(actual, data, labels, ngroups, is_datetimelike)
expected = np.array([1, 2, 6, np.nan, 24], dtype="float64")
tm.assert_numpy_array_equal(actual[:, 0], expected)
actual = np.zeros_like(data)
actual.fill(np.nan)
group_cumsum(actual, data, labels, ngroups, is_datetimelike)
expected = np.array([1, 3, 6, np.nan, 10], dtype="float64")
tm.assert_numpy_array_equal(actual[:, 0], expected)
# timedelta
is_datetimelike = True
data = np.array([np.timedelta64(1, "ns")] * 5, dtype="m8[ns]")[:, None]
actual = np.zeros_like(data, dtype="int64")
group_cumsum(actual, data.view("int64"), labels, ngroups, is_datetimelike)
expected = np.array([
np.timedelta64(1, "ns"),
np.timedelta64(2, "ns"),
np.timedelta64(3, "ns"),
np.timedelta64(4, "ns"),
np.timedelta64(5, "ns"),
])
tm.assert_numpy_array_equal(actual[:, 0].view("m8[ns]"), expected)
def test_cython_group_transform_algos():
# see gh-4095
is_datetimelike = False
# with nans
labels = np.array([0, 0, 0, 0, 0], dtype=np.int64)
data = np.array([[1], [2], [3], [np.nan], [4]], dtype='float64')
actual = np.zeros_like(data)
actual.fill(np.nan)
groupby.group_cumprod_float64(actual, data, labels, is_datetimelike)
expected = np.array([1, 2, 6, np.nan, 24], dtype='float64')
tm.assert_numpy_array_equal(actual[:, 0], expected)
actual = np.zeros_like(data)
actual.fill(np.nan)
groupby.group_cumsum(actual, data, labels, is_datetimelike)
expected = np.array([1, 3, 6, np.nan, 10], dtype='float64')
tm.assert_numpy_array_equal(actual[:, 0], expected)
# timedelta
is_datetimelike = True
data = np.array([np.timedelta64(1, 'ns')] * 5, dtype='m8[ns]')[:, None]
actual = np.zeros_like(data, dtype='int64')
groupby.group_cumsum(actual, data.view('int64'), labels,
is_datetimelike)
expected = np.array([np.timedelta64(1, 'ns'), np.timedelta64(
2, 'ns'), np.timedelta64(3, 'ns'), np.timedelta64(4, 'ns'),
np.timedelta64(5, 'ns')])
tm.assert_numpy_array_equal(actual[:, 0].view('m8[ns]'), expected)
def test_cython_group_transform_algos(self):
# GH 4095
dtypes = [
np.int8, np.int16, np.int32, np.int64, np.uint8, np.uint32,
np.uint64, np.float32, np.float64
]
ops = [(groupby.group_cumprod_float64, np.cumproduct, [np.float64]),
(groupby.group_cumsum, np.cumsum, dtypes)]
is_datetimelike = False
for pd_op, np_op, dtypes in ops:
for dtype in dtypes:
data = np.array([[1], [2], [3], [4]], dtype=dtype)
ans = np.zeros_like(data)
labels = np.array([0, 0, 0, 0], dtype=np.int64)
pd_op(ans, data, labels, is_datetimelike)
tm.assert_numpy_array_equal(np_op(data),
ans[:, 0],
check_dtype=False)
# with nans
labels = np.array([0, 0, 0, 0, 0], dtype=np.int64)
data = np.array([[1], [2], [3], [np.nan], [4]], dtype='float64')
actual = np.zeros_like(data)
actual.fill(np.nan)
groupby.group_cumprod_float64(actual, data, labels, is_datetimelike)
expected = np.array([1, 2, 6, np.nan, 24], dtype='float64')
tm.assert_numpy_array_equal(actual[:, 0], expected)
actual = np.zeros_like(data)
actual.fill(np.nan)
groupby.group_cumsum(actual, data, labels, is_datetimelike)
expected = np.array([1, 3, 6, np.nan, 10], dtype='float64')
tm.assert_numpy_array_equal(actual[:, 0], expected)
# timedelta
is_datetimelike = True
data = np.array([np.timedelta64(1, 'ns')] * 5, dtype='m8[ns]')[:, None]
actual = np.zeros_like(data, dtype='int64')
groupby.group_cumsum(actual, data.view('int64'), labels,
is_datetimelike)
expected = np.array([
np.timedelta64(1, 'ns'),
np.timedelta64(2, 'ns'),
np.timedelta64(3, 'ns'),
np.timedelta64(4, 'ns'),
np.timedelta64(5, 'ns')
])
tm.assert_numpy_array_equal(actual[:, 0].view('m8[ns]'), expected)
def test_cython_group_transform_algos(self):
# GH 4095
dtypes = [np.int8, np.int16, np.int32, np.int64, np.uint8, np.uint32,
np.uint64, np.float32, np.float64]
ops = [(groupby.group_cumprod_float64, np.cumproduct, [np.float64]),
(groupby.group_cumsum, np.cumsum, dtypes)]
is_datetimelike = False
for pd_op, np_op, dtypes in ops:
for dtype in dtypes:
data = np.array([[1], [2], [3], [4]], dtype=dtype)
ans = np.zeros_like(data)
labels = np.array([0, 0, 0, 0], dtype=np.int64)
pd_op(ans, data, labels, is_datetimelike)
tm.assert_numpy_array_equal(np_op(data), ans[:, 0],
check_dtype=False)
# with nans
labels = np.array([0, 0, 0, 0, 0], dtype=np.int64)
data = np.array([[1], [2], [3], [np.nan], [4]], dtype='float64')
actual = np.zeros_like(data)
actual.fill(np.nan)
groupby.group_cumprod_float64(actual, data, labels, is_datetimelike)
expected = np.array([1, 2, 6, np.nan, 24], dtype='float64')
tm.assert_numpy_array_equal(actual[:, 0], expected)
actual = np.zeros_like(data)
actual.fill(np.nan)
groupby.group_cumsum(actual, data, labels, is_datetimelike)
expected = np.array([1, 3, 6, np.nan, 10], dtype='float64')
tm.assert_numpy_array_equal(actual[:, 0], expected)
# timedelta
is_datetimelike = True
data = np.array([np.timedelta64(1, 'ns')] * 5, dtype='m8[ns]')[:, None]
actual = np.zeros_like(data, dtype='int64')
groupby.group_cumsum(actual, data.view('int64'), labels,
is_datetimelike)
expected = np.array([np.timedelta64(1, 'ns'), np.timedelta64(
2, 'ns'), np.timedelta64(3, 'ns'), np.timedelta64(4, 'ns'),
np.timedelta64(5, 'ns')])
tm.assert_numpy_array_equal(actual[:, 0].view('m8[ns]'), expected)
