def test_empty_columns(df): df["c"] = np.nan res = Description(df) dropped = res.frame.c.dropna() assert dropped.shape[0] == 2 assert "missing" in dropped assert "nobs" in dropped df["c"] = np.nan res = Description(df.c) dropped = res.frame.dropna() assert dropped.shape[0] == 2
def test_extension_types(df): df["c"] = pd.Series(np.arange(100.0)) df["d"] = pd.Series(np.arange(100), dtype=pd.Int64Dtype()) df.loc[df.index[::2], "c"] = np.nan df.loc[df.index[::2], "d"] = pd.NA res = Description(df) np.testing.assert_allclose(res.frame.c, res.frame.d)
def test_std_err(df): """ Test the standard error of the mean matches result from scipy.stats.sem """ np.testing.assert_allclose( Description(df["a"]).frame.loc["std_err"], scipy.stats.sem(df["a"]) )
def test_odd_percentiles(df): percentiles = np.linspace(7.0, 93.0, 13) res = Description(df, percentiles=percentiles) stats = [ 'nobs', 'missing', 'mean', 'std_err', 'upper_ci', 'lower_ci', 'std', 'iqr', 'iqr_normal', 'mad', 'mad_normal', 'coef_var', 'range', 'max', 'min', 'skew', 'kurtosis', 'jarque_bera', 'jarque_bera_pval', 'mode', 'mode_freq', 'median', 'distinct', 'top_1', 'top_2', 'top_3', 'top_4', 'top_5', 'freq_1', 'freq_2', 'freq_3', 'freq_4', 'freq_5', '7.0%', '14.1%', '21.3%', '28.5%', '35.6%', '42.8%', '50.0%', '57.1%', '64.3%', '71.5%', '78.6%', '85.8%', '93.0%'] assert_equal(res.frame.index.tolist(), stats)
def test_description_basic(df): res = Description(df) assert isinstance(res.frame, pd.DataFrame) assert isinstance(res.numeric, pd.DataFrame) assert isinstance(res.categorical, pd.DataFrame) assert isinstance(res.summary(), SimpleTable) assert isinstance(res.summary().as_text(), str) assert "Descriptive" in str(res) res = Description(df.a) assert isinstance(res.frame, pd.DataFrame) assert isinstance(res.numeric, pd.DataFrame) assert isinstance(res.categorical, pd.DataFrame) assert isinstance(res.summary(), SimpleTable) assert isinstance(res.summary().as_text(), str) assert "Descriptive" in str(res) res = Description(df.b) assert isinstance(res.frame, pd.DataFrame) assert isinstance(res.numeric, pd.DataFrame) assert isinstance(res.categorical, pd.DataFrame) assert isinstance(res.summary(), SimpleTable) assert isinstance(res.summary().as_text(), str) assert "Descriptive" in str(res)
def test_description_exceptions(): df = pd.DataFrame( {"a": np.empty(100), "b": pd.Series(np.arange(100) % 10)}, dtype="category", ) with pytest.raises(ValueError): Description(df, stats=["unknown"]) with pytest.raises(ValueError): Description(df, alpha=-0.3) with pytest.raises(ValueError): Description(df, percentiles=[0, 100]) with pytest.raises(ValueError): Description(df, percentiles=[10, 20, 30, 10]) with pytest.raises(ValueError): Description(df, ntop=-3) with pytest.raises(ValueError): Description(df, numeric=False, categorical=False)
def test_describe(df): pd.testing.assert_frame_equal(describe(df), Description(df).frame)
def test_special_stats(df, stat): all_stats = [st for st in Description.default_statistics] all_stats.remove(stat[0]) res = Description(df, stats=all_stats) for val in stat[1]: assert val not in res.frame.index
def test_use_t(df): res = Description(df) res_t = Description(df, use_t=True) assert res_t.frame.a.lower_ci < res.frame.a.lower_ci assert res_t.frame.a.upper_ci > res.frame.a.upper_ci
def test_large_ntop(df): res = Description(df, ntop=15) assert "top_15" in res.frame.index
def test_odd_percentiles(df): percentiles = np.linspace(7.0, 93.0, 13) res = Description(df, percentiles=percentiles) print(res.frame.index)