def test_misc_quantiles(data, q):
pdf_series = pd.Series(data)
gdf_series = Series(data)
expected = pdf_series.quantile(q)
actual = gdf_series.quantile(q)
assert_eq(expected, actual)
def test_misc_quantiles(data, q):
from cudf.tests import utils
pdf_series = pd.Series(data)
gdf_series = Series(data)
expected = pdf_series.quantile(q)
actual = gdf_series.quantile(q)
utils.assert_eq(expected, actual)
def test_approx_quantiles_int():
arr = np.asarray([1, 2, 3])
quant_values = [0.5]
approx_results = [2]
gdf_series = Series(arr)
q1 = gdf_series.quantile(quant_values, exact=False)
assert approx_results == q1.to_pandas().values
def test_approx_quantiles():
arr = np.asarray([6.8, 0.15, 3.4, 4.17, 2.13, 1.11, -1.01, 0.8, 5.7])
quant_values = [0.0, 0.25, 0.33, 0.5, 1.0]
gdf_series = Series(arr)
pdf_series = pd.Series(arr)
q1 = gdf_series.quantile(quant_values, exact=False)
q2 = pdf_series.quantile(quant_values)
assert_eq(q1, q2)
def test_approx_quantiles():
arr = np.asarray([6.8, 0.15, 3.4, 4.17, 2.13, 1.11, -1.01, 0.8, 5.7])
quant_values = [0.0, 0.25, 0.33, 0.5, 1.0]
approx_results = [-1.01, 0.8, 0.8, 2.13, 6.8]
gdf_series = Series(arr)
q1 = gdf_series.quantile(quant_values, exact=False)
np.testing.assert_allclose(q1.to_pandas().values,
approx_results,
rtol=1e-10)
def test_exact_quantiles_int(int_method):
arr = np.asarray([7, 0, 3, 4, 2, 1, -1, 1, 6])
quant_values = [0.0, 0.25, 0.33, 0.5, 1.0]
df = pd.DataFrame(arr)
gdf_series = Series(arr)
q1 = gdf_series.quantile(
quant_values, interpolation=int_method, exact=True
)
q2 = df.quantile(quant_values, interpolation=int_method)
np.testing.assert_allclose(
q1.to_pandas().values, np.array(q2.values).T.flatten(), rtol=1e-10
)
def test_exact_quantiles(int_method):
arr = np.asarray([6.8, 0.15, 3.4, 4.17, 2.13, 1.11, -1.01, 0.8, 5.7])
quant_values = [0.0, 0.25, 0.33, 0.5, 1.0]
df = pd.DataFrame(arr)
gdf_series = Series(arr)
q1 = gdf_series.quantile(
quant_values, interpolation=int_method, exact=True
)
q2 = df.quantile(quant_values, interpolation=int_method)
np.testing.assert_allclose(
q1.to_pandas().values, np.array(q2.values).T.flatten(), rtol=1e-10
)
