def test_corr1d(data1, data2): gs1 = Series(data1) gs2 = Series(data2) ps1 = gs1.to_pandas() ps2 = gs2.to_pandas() got = gs1.corr(gs2) expected = ps1.corr(ps2) np.testing.assert_approx_equal(got, expected, significant=8)
def test_series_nlargest_nelem(nelem): np.random.seed(0) elems = np.random.random(nelem) gds = Series(elems).nlargest(nelem) pds = pd.Series(elems).nlargest(nelem) assert (pds == gds.to_pandas()).all().all()
def test_series_sort_values_ignore_index(ignore_index): gsr = Series([1, 3, 5, 2, 4]) psr = gsr.to_pandas() expect = psr.sort_values(ignore_index=ignore_index) got = gsr.sort_values(ignore_index=ignore_index) assert_eq(expect, got)
def test_series_std(ddof): np.random.seed(0) arr = np.random.random(100) - 0.5 sr = Series(arr) pd = sr.to_pandas() got = sr.std(ddof=ddof) expect = pd.std(ddof=ddof) np.testing.assert_approx_equal(expect, got)
def test_operator_func_between_series_logical(dtype, func, scalar_a, scalar_b, fill_value): gdf_series_a = Series([scalar_a]).astype(dtype) gdf_series_b = Series([scalar_b]).astype(dtype) pdf_series_a = gdf_series_a.to_pandas() pdf_series_b = gdf_series_b.to_pandas() gdf_series_result = getattr(gdf_series_a, func)(gdf_series_b, fill_value=fill_value) pdf_series_result = getattr(pdf_series_a, func)(pdf_series_b, fill_value=fill_value) if scalar_a in [None, np.nan] and scalar_b in [None, np.nan]: # cudf binary operations will return `None` when both left- and right- # side values are `None`. It will return `np.nan` when either side is # `np.nan`. As a consequence, when we convert our gdf => pdf during # assert_eq, we get a pdf with dtype='object' (all inputs are none). # to account for this, we use fillna. gdf_series_result.fillna(func == "ne", inplace=True) utils.assert_eq(pdf_series_result, gdf_series_result)