test_data.py 文件源码

def test_general_weighted_demean_oneway(panel):
    y = PanelData(panel)
    weights = pd.DataFrame(
        np.random.chisquare(10, (y.dataframe.shape[0], 1)) / 10, index=y.index)
    w = PanelData(weights)

    dm1 = y.demean('entity', weights=w)
    g = PanelData(pd.DataFrame(y.entity_ids, index=y.index))
    dm2 = y.general_demean(g, w)
    assert_allclose(dm1.values2d, dm2.values2d)

    dm1 = y.demean('time', weights=w)
    g = PanelData(pd.DataFrame(y.time_ids, index=y.index))
    dm2 = y.general_demean(g, w)
    assert_allclose(dm1.values2d, dm2.values2d)

    g = PanelData(pd.DataFrame(np.random.randint(0, 10, g.dataframe.shape),
                               index=y.index))
    dm2 = y.general_demean(g, w)
    g = pd.Categorical(g.dataframe.iloc[:, 0])
    d = pd.get_dummies(g)
    wd = np.sqrt(w.values2d) * d
    wy = np.sqrt(w.values2d) * y.values2d
    dm1 = wy - wd @ np.linalg.lstsq(wd, wy)[0]
    assert_allclose(dm1, dm2.values2d, atol=1e-14)