def test_le(self):
with option_context("compute.ops_on_diff_frames", True):
for pser, psser in self.fractional_extension_pser_psser_pairs:
self.check_extension(pser <= pser,
(psser <= psser).sort_index())
def test_ge(self):
with option_context("compute.ops_on_diff_frames", True):
self.check_extension(self.pser >= self.other_pser,
(self.psser >= self.other_psser).sort_index())
self.check_extension(self.pser >= self.pser,
(self.psser >= self.psser).sort_index())
def test_ne(self):
with option_context("compute.ops_on_diff_frames", True):
for pser, psser in self.numeric_pser_psser_pairs:
self.assert_eq(pser != pser, (psser != psser).sort_index())
def test_gt(self):
with option_context("compute.ops_on_diff_frames", True):
self.assert_eq(self.pser > self.other_pser,
(self.psser > self.other_psser).sort_index())
self.assert_eq(self.pser > self.pser,
(self.psser > self.psser).sort_index())
def test_axis_on_dataframe(self):
# The number of each count is intentionally big
# because when data is small, it executes a shortcut.
# Less than 'compute.shortcut_limit' will execute a shortcut
# by using collected pandas dataframe directly.
# now we set the 'compute.shortcut_limit' as 1000 explicitly
with option_context("compute.shortcut_limit", 1000):
pdf = pd.DataFrame(
{
"A": [1, -2, 3, -4, 5] * 300,
"B": [1.0, -2, 3, -4, 5] * 300,
"C": [-6.0, -7, -8, -9, 10] * 300,
"D": [True, False, True, False, False] * 300,
},
index=range(10, 15001, 10),
)
kdf = ps.from_pandas(pdf)
self.assert_eq(kdf.count(axis=1), pdf.count(axis=1))
self.assert_eq(kdf.var(axis=1), pdf.var(axis=1))
self.assert_eq(kdf.var(axis=1, ddof=0), pdf.var(axis=1, ddof=0))
self.assert_eq(kdf.std(axis=1), pdf.std(axis=1))
self.assert_eq(kdf.std(axis=1, ddof=0), pdf.std(axis=1, ddof=0))
self.assert_eq(kdf.max(axis=1), pdf.max(axis=1))
self.assert_eq(kdf.min(axis=1), pdf.min(axis=1))
self.assert_eq(kdf.sum(axis=1), pdf.sum(axis=1))
self.assert_eq(kdf.product(axis=1), pdf.product(axis=1))
self.assert_eq(kdf.kurtosis(axis=1), pdf.kurtosis(axis=1))
self.assert_eq(kdf.skew(axis=1), pdf.skew(axis=1))
self.assert_eq(kdf.mean(axis=1), pdf.mean(axis=1))
self.assert_eq(kdf.sem(axis=1), pdf.sem(axis=1))
self.assert_eq(kdf.sem(axis=1, ddof=0), pdf.sem(axis=1, ddof=0))
self.assert_eq(kdf.count(axis=1, numeric_only=True),
pdf.count(axis=1, numeric_only=True))
self.assert_eq(kdf.var(axis=1, numeric_only=True),
pdf.var(axis=1, numeric_only=True))
self.assert_eq(
kdf.var(axis=1, ddof=0, numeric_only=True),
pdf.var(axis=1, ddof=0, numeric_only=True),
)
self.assert_eq(kdf.std(axis=1, numeric_only=True),
pdf.std(axis=1, numeric_only=True))
self.assert_eq(
kdf.std(axis=1, ddof=0, numeric_only=True),
pdf.std(axis=1, ddof=0, numeric_only=True),
)
self.assert_eq(kdf.max(axis=1, numeric_only=True),
pdf.max(axis=1, numeric_only=True).astype(float))
self.assert_eq(kdf.min(axis=1, numeric_only=True),
pdf.min(axis=1, numeric_only=True).astype(float))
self.assert_eq(kdf.sum(axis=1, numeric_only=True),
pdf.sum(axis=1, numeric_only=True).astype(float))
self.assert_eq(
kdf.product(axis=1, numeric_only=True),
pdf.product(axis=1, numeric_only=True).astype(float),
)
self.assert_eq(kdf.kurtosis(axis=1, numeric_only=True),
pdf.kurtosis(axis=1, numeric_only=True))
self.assert_eq(kdf.skew(axis=1, numeric_only=True),
pdf.skew(axis=1, numeric_only=True))
self.assert_eq(kdf.mean(axis=1, numeric_only=True),
pdf.mean(axis=1, numeric_only=True))
self.assert_eq(kdf.sem(axis=1, numeric_only=True),
pdf.sem(axis=1, numeric_only=True))
self.assert_eq(
kdf.sem(axis=1, ddof=0, numeric_only=True),
pdf.sem(axis=1, ddof=0, numeric_only=True),
)
