core_test.py 文件源码

def testShuffledDataframeRelativeToJackknife(self):
    # Same as test above, but also testing that reordering the data doesn't
    # change results, up to order.
    df = pd.DataFrame({"X": range(11),
                       "Y": np.concatenate((np.zeros(6), np.ones(5))),
                       "Z": np.concatenate((np.zeros(3), np.ones(8)))})

    metric = metrics.Distribution("X", ["Z"])
    se_method = standard_errors.Jackknife()
    output = core.Analyze(df.iloc[np.random.permutation(11)]).relative_to(
        comparisons.AbsoluteDifference("Y", 0)).with_standard_errors(
            se_method).calculate(metric).run()
    output = (output.
              reset_index().
              sort_values(by=["Y", "Z"]).
              set_index(["Y", "Z"]))

    correct = pd.DataFrame(
        np.array([[-0.2, 0.18100283490],
                  [0.2, 0.18100283490]]),
        columns=["X Distribution Absolute Difference",
                 "X Distribution Absolute Difference Jackknife SE"],
        index=pd.MultiIndex(levels=[[1.], [0., 1.]],
                            labels=[[0, 0], [0, 1]],
                            names=["Y", "Z"]))
    correct = (correct.
               reset_index().
               sort_values(by=["Y", "Z"]).
               set_index(["Y", "Z"]))

    self.assertTrue(all(output.index == correct.index) and
                    all(output.columns == correct.columns) and
                    np.all(abs(output.values - correct.values) < 1e-10))