def test_webuse(): # test copied and adjusted from iolib/tests/test_foreign from statsmodels.iolib.tests.results.macrodata import macrodata_result as res2 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, as_df=False) assert_array_equal(res1, res2)
def test_get_rdataset(): # smoke test test_url = "https://raw.githubusercontent.com/vincentarelbundock/Rdatasets/master/csv/datasets/cars.csv" internet_available = check_internet(test_url) if not internet_available: raise SkipTest('Unable to retrieve file - skipping test') duncan = get_rdataset("Duncan", "car", cache=cur_dir) assert_(isinstance(duncan, utils.Dataset)) assert_(duncan.from_cache)
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_get_rdataset(): test_url = "https://raw.githubusercontent.com/vincentarelbundock/" \ "Rdatasets/master/csv/datasets/cars.csv" internet_available = check_internet(test_url) if not internet_available: pytest.skip('Unable to retrieve file - skipping test') try: duncan = get_rdataset("Duncan", "carData", cache=cur_dir) except IGNORED_EXCEPTIONS: pytest.skip('Failed with HTTPError or URLError, these are random') assert_(isinstance(duncan, utils.Dataset)) duncan = get_rdataset("Duncan", "carData", cache=cur_dir) assert_(duncan.from_cache)
def test_get_rdataset(): test_url = "https://raw.githubusercontent.com/vincentarelbundock/" \ "Rdatasets/master/csv/datasets/cars.csv" internet_available = check_internet(test_url) if not internet_available: pytest.skip('Unable to retrieve file - skipping test') try: duncan = get_rdataset("Duncan", "carData", cache=cur_dir) except (HTTPError, URLError, SSLError, timeout): pytest.skip('Failed with HTTPError or URLError, these are random') assert_(isinstance(duncan, utils.Dataset)) duncan = get_rdataset("Duncan", "carData", cache=cur_dir) assert_(duncan.from_cache)
def test_webuse(): # test copied and adjusted from iolib/tests/test_foreign from statsmodels.iolib.tests.results.macrodata import macrodata_result res2 = np.array([list(row) for row in macrodata_result]) 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, as_df=False) except IGNORED_EXCEPTIONS: pytest.skip('Failed with HTTPError or URLError, these are random') assert_array_equal(res1, res2)
def test_get_rdataset(): # smoke test test_url = "https://raw.githubusercontent.com/vincentarelbundock/Rdatasets/master/csv/datasets/cars.csv" internet_available = check_internet(test_url) if not internet_available: raise SkipTest('Unable to retrieve file - skipping test') duncan = get_rdataset("Duncan", "car", cache=cur_dir) assert_(isinstance(duncan, utils.Dataset)) if not PY3: #NOTE: there's no way to test both since the cached files were #created with Python 2.x, they're strings, but Python 3 expects #bytes and the index file path is hard-coded so both can't live #side by side assert_(duncan.from_cache)
def test_webuse(): # test copied and adjusted from iolib/tests/test_foreign from statsmodels.iolib.tests.results.macrodata import macrodata_result res2 = np.array([list(row) for row in macrodata_result]) 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, as_df=False) except (HTTPError, URLError, SSLError, timeout): pytest.skip('Failed with HTTPError or URLError, these are random') assert_array_equal(res1, res2)
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 IGNORED_EXCEPTIONS: pytest.skip('Failed with HTTP Error, these are random') res1 = res1.astype(float) assert_frame_equal(res1, dta.astype(float))
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 test_get_rdataset(): # smoke test test_url = "https://raw.githubusercontent.com/vincentarelbundock/Rdatasets/master/csv/datasets/cars.csv" internet_available = check_internet(test_url) if not internet_available: raise SkipTest('Unable to retrieve file - skipping test') duncan = get_rdataset("Duncan", "car", cache=cur_dir) assert_(isinstance(duncan, utils.Dataset)) assert_(duncan.from_cache) # test writing and reading cache guerry = get_rdataset("Guerry", "HistData", cache=cur_dir) assert_(guerry.from_cache is False) guerry2 = get_rdataset("Guerry", "HistData", cache=cur_dir) assert_(guerry2.from_cache is True) fn = "raw.github.com,vincentarelbundock,Rdatasets,master,csv,HistData,Guerry.csv.zip" os.remove(os.path.join(cur_dir, fn)) fn = "raw.github.com,vincentarelbundock,Rdatasets,master,doc,HistData,rst,Guerry.rst.zip" os.remove(os.path.join(cur_dir, fn))