def test_repr_dataframe(self):
kdf = ks.range(ReprTest.max_display_count)
self.assertTrue("Showing only the first" not in repr(kdf))
self.assert_eq(repr(kdf), repr(kdf.to_pandas()))
kdf = ks.range(ReprTest.max_display_count + 1)
self.assertTrue("Showing only the first" in repr(kdf))
with option_context("display.max_rows", None):
kdf = ks.range(ReprTest.max_display_count + 1)
self.assert_eq(repr(kdf), repr(kdf.to_pandas()))
def test_repr_indexes(self):
kdf = ks.range(ReprTest.max_display_count)
kidx = kdf.index
self.assertTrue("Showing only the first" not in repr(kidx))
self.assert_eq(repr(kidx), repr(kidx.to_pandas()))
kdf = ks.range(ReprTest.max_display_count + 1)
kidx = kdf.index
self.assertTrue("Showing only the first" in repr(kidx))
with option_context("display.max_rows", None):
kdf = ks.range(ReprTest.max_display_count + 1)
kidx = kdf.index
self.assert_eq(repr(kidx), repr(kidx.to_pandas()))
def test_repr_indexes(self):
kidx = ks.range(ReprTest.max_display_count).index
self.assertTrue("Showing only the first" not in repr(kidx))
self.assert_eq(repr(kidx), repr(kidx.to_pandas()))
kidx = ks.range(ReprTest.max_display_count + 1).index
self.assertTrue("Showing only the first" in repr(kidx))
self.assertTrue(
repr(kidx).startswith(
repr(kidx.to_pandas().to_series().head(
ReprTest.max_display_count).index)))
with option_context("display.max_rows", None):
kidx = ks.range(ReprTest.max_display_count + 1).index
self.assert_eq(repr(kidx), repr(kidx.to_pandas()))
kidx = ks.MultiIndex.from_tuples([
(100 * i, i) for i in range(ReprTest.max_display_count)
])
self.assertTrue("Showing only the first" not in repr(kidx))
self.assert_eq(repr(kidx), repr(kidx.to_pandas()))
kidx = ks.MultiIndex.from_tuples([
(100 * i, i) for i in range(ReprTest.max_display_count + 1)
])
self.assertTrue("Showing only the first" in repr(kidx))
self.assertTrue(
repr(kidx).startswith(
repr(kidx.to_pandas().to_frame().head(
ReprTest.max_display_count).index)))
with option_context("display.max_rows", None):
kidx = ks.MultiIndex.from_tuples([
(100 * i, i) for i in range(ReprTest.max_display_count + 1)
])
self.assert_eq(repr(kidx), repr(kidx.to_pandas()))
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., -2, 3, -4, 5] * 300,
'C': [-6., -7, -8, -9, 10] * 300,
'D': [True, False, True, False, False] * 300
})
kdf = ks.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.std(axis=1), pdf.std(axis=1))
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.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))
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 = ks.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),
)
def test_sampled_plot_with_ratio(self):
with option_context("plotting.sample_ratio", 0.5):
pdf = pd.DataFrame(np.random.rand(2500, 4), columns=["a", "b", "c", "d"])
kdf = ks.from_pandas(pdf)
data = SampledPlotBase().get_sampled(kdf)
self.assertEqual(round(len(data) / 2500, 1), 0.5)