def test_df_corr():
gdf = randomdata(100, {str(x): float for x in range(50)})
pdf = gdf.to_pandas()
got = gdf.corr()
expected = pdf.corr()
assert_eq(got, expected)
def test_df_corr():
from cudf.tests import utils
gdf = randomdata(100, {str(x): float for x in range(50)})
pdf = gdf.to_pandas()
got = gdf.corr()
expected = pdf.corr()
utils.assert_eq(got, expected)
@pytest.mark.parametrize(
"data",
[
Series(np.random.normal(-100, 100, 1000)),
Series(np.random.randint(-50, 50, 1000)),
Series(np.zeros(100)),
Series(np.repeat(np.nan, 100)),
Series(np.array([1.123, 2.343, np.nan, 0.0])),
Series(
[5, 10, 53, None, np.nan, None, 12, 43, -423], nan_as_null=False
),
Series([1.1032, 2.32, 43.4, 13, -312.0], index=[0, 4, 3, 19, 6]),
Series([]),
Series([-3]),
randomdata(
nrows=1000, dtypes={"a": float, "b": int, "c": float, "d": str}
),
],
)
@pytest.mark.parametrize("null_flag", [False, True])
def test_kurtosis(data, null_flag):
pdata = data.to_pandas()
if null_flag and len(data) > 2:
data.iloc[[0, 2]] = None
pdata.iloc[[0, 2]] = None
got = data.kurtosis()
got = got if np.isscalar(got) else got.to_array()
expected = pdata.kurtosis()
np.testing.assert_array_almost_equal(got, expected)