Python bootstrap.IIDBootstrap类代码示例

 def test_pandas_integer_index(self):
     x = self.x
     x_int = self.x_df.copy()
     x_int.index = 10 + np.arange(x.shape[0])
     bs = IIDBootstrap(x, x_int)
     bs.seed(23456)
     for pdata, kwdata in bs.bootstrap(10):
         assert_equal(pdata[0], pdata[1].values)

    def test_conf_int_bca_scaler(self):
        num_bootstrap = 100
        bs = IIDBootstrap(self.y)
        bs.seed(23456)

        ci = bs.conf_int(np.mean, reps=num_bootstrap, method='bca')
        msg = 'conf_int(method=\'bca\') scalar input regression. Ensure ' \
              'output is at least 1D with numpy.atleast_1d().'
        assert ci.shape == (2, 1), msg

def test_iid_unequal_equiv():
    rs = RandomState(0)
    x = rs.randn(500)
    rs1 = RandomState(0)
    bs1 = IIDBootstrap(x, random_state=rs1)

    rs2 = RandomState(0)
    bs2 = IndependentSamplesBootstrap(x, random_state=rs2)

    v1 = bs1.var(np.mean)
    v2 = bs2.var(np.mean)
    assert_allclose(v1, v2)

    def test_extra_kwargs(self):
        extra_kwargs = {'axis': 0}
        bs = IIDBootstrap(self.x)
        bs.seed(23456)
        num_bootstrap = 100

        bs.cov(self.func, reps=num_bootstrap, extra_kwargs=extra_kwargs)

        bs = IIDBootstrap(axis=self.x)
        bs.seed(23456)
        with pytest.raises(ValueError):
            bs.cov(self.func, reps=num_bootstrap, extra_kwargs=extra_kwargs)

    def test_conf_int_bca_scaler(self):
        num_bootstrap = 100
        bs = IIDBootstrap(self.y)
        bs.seed(23456)

        try:
            ci = bs.conf_int(np.mean, reps=num_bootstrap, method='bca')
            assert(ci.shape == (2, 1))
        except IndexError:
            pytest.fail('conf_int(method=\'bca\') scaler input regression. '
                        'Ensure output is at least 1D with '
                        'numpy.atleast_1d().')

 def test_mixed_types(self):
     x, y, z = self.x_df, self.y_series, self.z
     bs = IIDBootstrap(y, x=x, z=z)
     bs.seed(23456)
     for data, kwdata in bs.bootstrap(10):
         index = bs.index
         assert_equal(len(data), 1)
         assert_equal(len(kwdata.keys()), 2)
         assert_frame_equal(x.iloc[index], kwdata['x'])
         assert_frame_equal(x.iloc[index], bs.x)
         assert_series_equal(y.iloc[index], data[0])
         assert_equal(z[index], kwdata['z'])
         assert_equal(z[index], bs.z)

    def test_str(self):
        bs = IIDBootstrap(self.y_series)
        expected = 'IID Bootstrap(no. pos. inputs: 1, no. keyword inputs: 0)'
        assert_equal(str(bs), expected)
        expected = expected[:-1] + ', ID: ' + hex(id(bs)) + ')'
        assert_equal(bs.__repr__(), expected)
        expected = '<strong>IID Bootstrap</strong>(' + \
                   '<strong>no. pos. inputs</strong>: 1, ' + \
                   '<strong>no. keyword inputs</strong>: 0, ' + \
                   '<strong>ID</strong>: ' + hex(id(bs)) + ')'
        assert_equal(bs._repr_html(), expected)

        bs = StationaryBootstrap(10, self.y_series, self.x_df)
        expected = 'Stationary Bootstrap(block size: 10, no. pos. inputs: 2, no. keyword inputs: 0)'
        assert_equal(str(bs), expected)
        expected = expected[:-1] + ', ID: ' + hex(id(bs)) + ')'
        assert_equal(bs.__repr__(), expected)

        bs = CircularBlockBootstrap(block_size=20, y=self.y_series, x=self.x_df)
        expected = 'Circular Block Bootstrap(block size: 20, no. pos. inputs: 0, no. keyword inputs: 2)'
        assert_equal(str(bs), expected)
        expected = expected[:-1] + ', ID: ' + hex(id(bs)) + ')'
        assert_equal(bs.__repr__(), expected)
        expected = '<strong>Circular Block Bootstrap</strong>' + \
                   '(<strong>block size</strong>: 20, ' \
                   + '<strong>no. pos. inputs</strong>: 0, ' + \
                   '<strong>no. keyword inputs</strong>: 2,' + \
                   ' <strong>ID</strong>: ' + hex(id(bs)) + ')'
        assert_equal(bs._repr_html(), expected)

    def test_reuse(self):
        num_bootstrap = 100
        bs = IIDBootstrap(self.x)

        ci = bs.conf_int(self.func, reps=num_bootstrap)
        old_results = bs._results.copy()
        ci_reuse = bs.conf_int(self.func, reps=num_bootstrap, reuse=True)
        results = bs._results
        assert_equal(results, old_results)
        assert_equal(ci, ci_reuse)
        with warnings.catch_warnings(record=True) as w:
            warnings.simplefilter("always", RuntimeWarning)
            warnings.simplefilter("always")
            bs.conf_int(self.func, tail='lower', reps=num_bootstrap // 2, reuse=True)
            assert_equal(len(w), 1)

    def test_extra_kwargs(self):
        extra_kwargs = {'axis': 0}
        bs = IIDBootstrap(self.x)
        bs.seed(23456)
        num_bootstrap = 100

        def func(y, axis=0):
            return y.mean(axis=axis)

        bs.cov(func, reps=num_bootstrap, extra_kwargs=extra_kwargs)

        bs = IIDBootstrap(axis=self.x)
        bs.seed(23456)
        with pytest.raises(ValueError):
            bs.cov(func, reps=num_bootstrap, extra_kwargs=extra_kwargs)

    def test_conf_int_bias_corrected(self):
        num_bootstrap = 20
        bs = IIDBootstrap(self.x)
        bs.seed(23456)

        def func(y):
            return y.mean(axis=0)

        ci = bs.conf_int(func, reps=num_bootstrap, method='bc')
        bs.reset()
        ci_db = bs.conf_int(func, reps=num_bootstrap, method='debiased')
        assert_equal(ci, ci_db)
        base, results = bs._base, bs._results
        p = np.zeros(2)
        p[0] = np.mean(results[:, 0] < base[0])
        p[1] = np.mean(results[:, 1] < base[1])
        b = stats.norm.ppf(p)
        q = stats.norm.ppf(np.array([0.025, 0.975]))
        q = q[:, None]
        percentiles = 100 * stats.norm.cdf(2 * b + q)

        ci = np.zeros((2, 2))
        for i in range(2):
            ci[i] = np.percentile(results[:, i], list(percentiles[:, i]))
        ci = ci.T
        assert_allclose(ci_db, ci)

    def test_bca(self):
        num_bootstrap = 20
        bs = IIDBootstrap(self.x)
        bs.seed(23456)

        def func(y):
            return y.mean(axis=0)

        ci_direct = bs.conf_int(func, reps=num_bootstrap, method='bca')
        bs.reset()
        base, results = bs._base, bs._results
        p = np.zeros(2)
        p[0] = np.mean(results[:, 0] < base[0])
        p[1] = np.mean(results[:, 1] < base[1])
        b = stats.norm.ppf(p)
        b = b[:, None]
        q = stats.norm.ppf(np.array([0.025, 0.975]))

        base = func(self.x)
        nobs = self.x.shape[0]
        jk = _loo_jackknife(func, nobs, [self.x], {})
        u = (nobs - 1) * (jk - base)
        u2 = np.sum(u * u, 0)
        u3 = np.sum(u * u * u, 0)
        a = u3 / (6.0 * (u2 ** 1.5))
        a = a[:, None]
        percentiles = 100 * stats.norm.cdf(b + (b + q) / (1 - a * (b + q)))

        ci = np.zeros((2, 2))
        for i in range(2):
            ci[i] = np.percentile(results[:, i], list(percentiles[i]))
        ci = ci.T
        assert_allclose(ci_direct, ci)

    def test_apply(self):
        bs = IIDBootstrap(self.x)
        bs.seed(23456)

        results = bs.apply(self.func, 1000)
        bs.reset(23456)
        direct_results = []
        for pos, _ in bs.bootstrap(1000):
            direct_results.append(self.func(*pos))
        direct_results = np.array(direct_results)
        assert_equal(results, direct_results)

 def test_reset(self):
     bs = IIDBootstrap(np.arange(100))
     state = bs.get_state()
     for data, kwdata in bs.bootstrap(10):
         final = data[0]
     bs.reset()
     state_reset = bs.get_state()
     for data, kwdata in bs.bootstrap(10):
         final_reset = data[0]
     assert_equal(final, final_reset)
     assert_equal(state, state_reset)

    def test_errors(self):
        x = np.arange(10)
        y = np.arange(100)
        with pytest.raises(ValueError):
            IIDBootstrap(x, y)
        with pytest.raises(ValueError):
            IIDBootstrap(index=x)
        bs = IIDBootstrap(y)

        with pytest.raises(ValueError):
            bs.conf_int(self.func, method='unknown')
        with pytest.raises(ValueError):
            bs.conf_int(self.func, tail='dragon')
        with pytest.raises(ValueError):
            bs.conf_int(self.func, size=95)

    def test_apply_series(self):
        bs = IIDBootstrap(self.y_series)
        bs.seed(23456)

        def func(y):
            return y.mean(0)

        results = bs.apply(func, 1000)
        bs.reset(23456)
        direct_results = []
        for pos, kw in bs.bootstrap(1000):
            direct_results.append(func(*pos))
        direct_results = np.array(direct_results)
        direct_results = direct_results[:, None]
        assert_equal(results, direct_results)