Python macrodata.load_pandas函数代码示例

    def __init__(self):
        d = macrodata.load_pandas().data
        # growth rates
        d["gs_l_realinv"] = 400 * np.log(d["realinv"]).diff()
        d["gs_l_realgdp"] = 400 * np.log(d["realgdp"]).diff()
        d["lint"] = d["realint"].shift(1)
        d["tbilrate"] = d["tbilrate"].shift(1)

        d = d.dropna()
        self.d = d
        endogg = d["gs_l_realinv"]
        exogg = add_constant(d[["gs_l_realgdp", "lint"]])
        exogg2 = add_constant(d[["gs_l_realgdp", "tbilrate"]])
        exogg3 = add_constant(d[["gs_l_realgdp"]])

        res_ols = OLS(endogg, exogg).fit()
        res_ols2 = OLS(endogg, exogg2).fit()

        res_ols3 = OLS(endogg, exogg3).fit()

        self.res = res_ols
        self.res2 = res_ols2
        self.res3 = res_ols3
        self.endog = self.res.model.endog
        self.exog = self.res.model.exog

def test_stata_writer_pandas():
    buf = BytesIO()
    dta = macrodata.load_pandas().data
    dta4 = dta.copy()
    for col in ('year','quarter'):
        dta[col] = dta[col].astype(np.int64)
        dta4[col] = dta4[col].astype(np.int32)
    # dta is int64 'i8'  given to Stata writer
    with pytest.warns(FutureWarning):
        writer = StataWriter(buf, dta)

    with warnings.catch_warnings(record=True) as w:
        writer.write_file()
        assert len(w) == 0
    buf.seek(0)

    with pytest.warns(FutureWarning):
        dta2 = genfromdta(buf)

    dta5 = DataFrame.from_records(dta2)
    # dta2 is int32 'i4'  returned from Stata reader

    if dta5.dtypes[1] is np.dtype('int64'):
        ptesting.assert_frame_equal(dta.reset_index(), dta5)
    else:
        # don't check index because it has different size, int32 versus int64
        ptesting.assert_frame_equal(dta4, dta5[dta5.columns[1:]])

    def setup_class(cls):
        d = macrodata.load_pandas().data
        #growth rates
        d['gs_l_realinv'] = 400 * np.log(d['realinv']).diff()
        d['gs_l_realgdp'] = 400 * np.log(d['realgdp']).diff()
        d['lint'] = d['realint'].shift(1)
        d['tbilrate'] = d['tbilrate'].shift(1)

        d = d.dropna()
        cls.d = d
        endogg = d['gs_l_realinv']
        exogg = add_constant(d[['gs_l_realgdp', 'lint']])
        exogg2 = add_constant(d[['gs_l_realgdp', 'tbilrate']])
        exogg3 = add_constant(d[['gs_l_realgdp']])

        res_ols = OLS(endogg, exogg).fit()
        res_ols2 = OLS(endogg, exogg2).fit()

        res_ols3 = OLS(endogg, exogg3).fit()

        cls.res = res_ols
        cls.res2 = res_ols2
        cls.res3 = res_ols3
        cls.endog = cls.res.model.endog
        cls.exog = cls.res.model.exog

    def setup_class(cls):
        d2 = macrodata.load_pandas().data
        g_gdp = 400*np.diff(np.log(d2['realgdp'].values))
        g_inv = 400*np.diff(np.log(d2['realinv'].values))
        exogg = add_constant(np.c_[g_gdp, d2['realint'][:-1].values], prepend=False)

        cls.res1 = res_ols = OLS(g_inv, exogg).fit()

def test_genfromdta_pandas():
    from pandas.util.testing import assert_frame_equal
    dta = macrodata.load_pandas().data
    curdir = os.path.dirname(os.path.abspath(__file__))
    res1 = sm.iolib.genfromdta(curdir+'/../../datasets/macrodata/macrodata.dta',
                        pandas=True)
    res1 = res1.astype(float)
    assert_frame_equal(res1, dta)

def t_est_webuse_pandas():
    # test copied and adjusted from iolib/tests/test_foreign
    from pandas.util.testing import assert_frame_equal
    from statsmodels.datasets import macrodata
    dta = macrodata.load_pandas().data
    base_gh = "http://github.com/statsmodels/statsmodels/raw/master/statsmodels/datasets/macrodata/"
    res1 = webuse('macrodata', baseurl=base_gh)
    res1 = res1.astype(float)
    assert_frame_equal(res1, dta)

def test_hpfilter_pandas():
    dta = macrodata.load_pandas().data
    index = Index(dates_from_range('1959Q1', '2009Q3'))
    dta.index = index
    cycle, trend = hpfilter(dta["realgdp"])
    ndcycle, ndtrend = hpfilter(dta['realgdp'].values)
    assert_equal(cycle.values, ndcycle)
    assert_equal(cycle.index[0], datetime(1959, 3, 31))
    assert_equal(cycle.index[-1], datetime(2009, 9, 30))
    assert_equal(cycle.name, "realgdp")

def test_hpfilter_pandas():
    dta = macrodata.load_pandas().data
    index = DatetimeIndex(start='1959-01-01', end='2009-10-01', freq='Q')
    dta.index = index
    cycle, trend = hpfilter(dta["realgdp"])
    ndcycle, ndtrend = hpfilter(dta['realgdp'].values)
    assert_equal(cycle.values, ndcycle)
    assert_equal(cycle.index[0], datetime(1959, 3, 31))
    assert_equal(cycle.index[-1], datetime(2009, 9, 30))
    assert_equal(cycle.name, "realgdp")

def test_genfromdta_pandas():
    from pandas.util.testing import assert_frame_equal
    dta = macrodata.load_pandas().data
    curdir = os.path.dirname(os.path.abspath(__file__))

    with pytest.warns(FutureWarning):
        res1 = genfromdta(curdir+'/../../datasets/macrodata/macrodata.dta',
                          pandas=True)

    res1 = res1.astype(float)
    assert_frame_equal(res1, dta.astype(float))

    def setup_class(cls):
        d2 = macrodata.load_pandas().data
        g_gdp = 400*np.diff(np.log(d2['realgdp'].values))
        g_inv = 400*np.diff(np.log(d2['realinv'].values))
        exogg = add_constant(np.c_[g_gdp, d2['realint'][:-1].values], prepend=False)

        mod1 = GLSAR(g_inv, exogg, 1)
        cls.res = mod1.iterative_fit(5)

        from .results.macro_gr_corc_stata import results
        cls.results = results

def test_webuse_pandas():
    # test copied and adjusted from iolib/tests/test_foreign
    from pandas.util.testing import assert_frame_equal
    from statsmodels.datasets import macrodata
    dta = macrodata.load_pandas().data
    base_gh = "http://github.com/statsmodels/statsmodels/raw/master/statsmodels/datasets/macrodata/"
    internet_available = check_internet(base_gh)
    if not internet_available:
        raise SkipTest('Unable to retrieve file - skipping test')
    res1 = webuse('macrodata', baseurl=base_gh)
    res1 = res1.astype(float)
    assert_frame_equal(res1, dta)

    def test_grangercausality(self):
        # some example data
        mdata = macrodata.load_pandas().data
        mdata = mdata[['realgdp', 'realcons']].values
        data = mdata.astype(float)
        data = np.diff(np.log(data), axis=0)

        #R: lmtest:grangertest
        r_result = [0.243097, 0.7844328, 195, 2]  # f_test
        gr = grangercausalitytests(data[:, 1::-1], 2, verbose=False)
        assert_almost_equal(r_result, gr[2][0]['ssr_ftest'], decimal=7)
        assert_almost_equal(gr[2][0]['params_ftest'], gr[2][0]['ssr_ftest'], decimal=7)

def test_webuse_pandas():
    # test copied and adjusted from iolib/tests/test_foreign
    from pandas.util.testing import assert_frame_equal
    from statsmodels.datasets import macrodata
    dta = macrodata.load_pandas().data
    base_gh = "https://github.com/statsmodels/statsmodels/raw/master/" \
              "statsmodels/datasets/macrodata/"
    internet_available = check_internet(base_gh)
    if not internet_available:
        pytest.skip('Unable to retrieve file - skipping test')
    try:
        res1 = webuse('macrodata', baseurl=base_gh)
    except (HTTPError, URLError, SSLError, timeout):
        pytest.skip('Failed with HTTP Error, these are random')
    res1 = res1.astype(float)
    assert_frame_equal(res1, dta.astype(float))

    def setup_class(cls):
        import pandas as pd
        from statsmodels.datasets import macrodata, co2
        dta = macrodata.load_pandas().data
        index = pd.PeriodIndex(start='1959Q1', end='2009Q3', freq='Q')
        dta.index = index
        cls.quarterly_data = dta.dropna()

        dta = co2.load_pandas().data
        dta['co2'] = dta.co2.interpolate()
        cls.monthly_data = dta.resample('M')
        # change in pandas 0.18 resample is deferred object
        if not isinstance(cls.monthly_data, (pd.DataFrame, pd.Series)):
            cls.monthly_data = cls.monthly_data.mean()

        cls.monthly_start_data = dta.resample('MS')
        if not isinstance(cls.monthly_start_data, (pd.DataFrame, pd.Series)):
            cls.monthly_start_data = cls.monthly_start_data.mean()

    def setupClass(cls):
        if not _have_x13:
            raise SkipTest("X13/X12 not available")

        import pandas as pd
        from statsmodels.datasets import macrodata, co2

        dta = macrodata.load_pandas().data
        dates = dates_from_range("1959Q1", "2009Q3")
        index = pd.DatetimeIndex(dates)
        dta.index = index
        cls.quarterly_data = dta.dropna()

        dta = co2.load_pandas().data
        dta["co2"] = dta.co2.interpolate()
        cls.monthly_data = dta.resample("M")

        cls.monthly_start_data = dta.resample("MS")