TST: Remove self.assert* from testing (#319)

Author: gfyoung

pandas_datareader/io/tests/test_jsdmx.py

@@ -16,52 +16,58 @@ def setUp(self):
 
     def test_tourism(self):
         # OECD -> Industry and Services -> Inbound Tourism
-        result = read_jsdmx(os.path.join(self.dirpath, 'jsdmx', 'tourism.json'))
-        self.assertTrue(isinstance(result, pd.DataFrame))
+        result = read_jsdmx(os.path.join(self.dirpath, 'jsdmx',
+                                         'tourism.json'))
+        assert isinstance(result, pd.DataFrame)
 
-        exp_col = pd.MultiIndex.from_product([['Japan'],
-                                              ['China', 'Hong Kong, China',
-                                               'Total international arrivals',
-                                               'Total international receipts',
-                                               'International passenger transport receipts',
-                                               'International travel receipts',
-                                               'Korea', 'Chinese Taipei', 'United States']],
-                                             names=['Country', 'Variable'])
-        exp_idx = pd.DatetimeIndex(['2004', '2005', '2006', '2007', '2008',
-                                    '2009', '2010', '2011', '2012'], name='Year')
+        exp_col = pd.MultiIndex.from_product(
+            [['Japan'], ['China', 'Hong Kong, China',
+                         'Total international arrivals',
+                         'Total international receipts',
+                         'International passenger transport receipts',
+                         'International travel receipts',
+                         'Korea', 'Chinese Taipei', 'United States']],
+            names=['Country', 'Variable'])
+        exp_idx = pd.DatetimeIndex(['2004', '2005', '2006', '2007',
+                                    '2008', '2009', '2010', '2011',
+                                    '2012'], name='Year')
 
-        values = np.array([[616, 300, 6138, 1550, 330, 1220, 1588, 1081, 760],
-                           [653, 299, 6728, 1710, 340, 1370, 1747, 1275, 822],
-                           [812, 352, 7334, 1330, 350, 980, 2117, 1309, 817],
-                           [942, 432, 8347, 1460, 360, 1100, 2601, 1385, 816],
-                           [1000, 550, 8351, 1430, 310, 1120, 2382, 1390, 768],
-                           [1006, 450, 6790, 1170, 210, 960, 1587, 1024, 700],
-                           [1413, 509, 8611, 1350, 190, 1160, 2440, 1268, 727],
-                           [1043, 365, 6219, 1000, 100, 900, 1658, 994, 566],
-                           [1430, 482, 8368, 1300, 100, 1200, 2044, 1467, 717]])
+        values = np.array([
+            [616, 300, 6138, 1550, 330, 1220, 1588, 1081, 760],
+            [653, 299, 6728, 1710, 340, 1370, 1747, 1275, 822],
+            [812, 352, 7334, 1330, 350, 980, 2117, 1309, 817],
+            [942, 432, 8347, 1460, 360, 1100, 2601, 1385, 816],
+            [1000, 550, 8351, 1430, 310, 1120, 2382, 1390, 768],
+            [1006, 450, 6790, 1170, 210, 960, 1587, 1024, 700],
+            [1413, 509, 8611, 1350, 190, 1160, 2440, 1268, 727],
+            [1043, 365, 6219, 1000, 100, 900, 1658, 994, 566],
+            [1430, 482, 8368, 1300, 100, 1200, 2044, 1467, 717]])
         expected = pd.DataFrame(values, index=exp_idx, columns=exp_col)
         tm.assert_frame_equal(result, expected)
 
     def test_land_use(self):
         # OECD -> Environment -> Resources Land Use
-        result = read_jsdmx(os.path.join(self.dirpath, 'jsdmx', 'land_use.json'))
-        self.assertTrue(isinstance(result, pd.DataFrame))
+        result = read_jsdmx(os.path.join(self.dirpath, 'jsdmx',
+                                         'land_use.json'))
+        assert isinstance(result, pd.DataFrame)
         result = result.ix['2010':'2011']
 
-        exp_col = pd.MultiIndex.from_product([['Japan', 'United States'],
-                                              ['Arable land and permanent crops',
-                                               'Arable and cropland % land area',
-                                               'Total area', 'Forest', 'Forest % land area',
-                                               'Land area', 'Permanent meadows and pastures',
-                                               'Meadows and pastures % land area',
-                                               'Other areas', 'Other % land area']],
-                                             names=['Country', 'Variable'])
+        exp_col = pd.MultiIndex.from_product([
+            ['Japan', 'United States'],
+            ['Arable land and permanent crops',
+             'Arable and cropland % land area',
+             'Total area', 'Forest', 'Forest % land area',
+             'Land area', 'Permanent meadows and pastures',
+             'Meadows and pastures % land area', 'Other areas',
+             'Other % land area']], names=['Country', 'Variable'])
         exp_idx = pd.DatetimeIndex(['2010', '2011'], name='Year')
-        values = np.array([[45930, 12.601, 377950, 249790, 68.529, 364500, np.nan, np.nan,
-                            68780, 18.87, 1624330, 17.757, 9831510, 3040220, 33.236, 9147420,
-                            2485000, 27.166, 1997870, 21.841],
-                           [45610, 12.513, 377955, 249878, 68.554, 364500, np.nan, np.nan,
-                            69012, 18.933, 1627625, 17.793, 9831510, 3044048, 33.278, 9147420,
-                            2485000, 27.166, 1990747, 21.763]])
+        values = np.array([[45930, 12.601, 377950, 249790, 68.529, 364500,
+                            np.nan, np.nan, 68780, 18.87, 1624330, 17.757,
+                            9831510, 3040220, 33.236, 9147420, 2485000,
+                            27.166, 1997870, 21.841],
+                           [45610, 12.513, 377955, 249878, 68.554, 364500,
+                            np.nan, np.nan, 69012, 18.933, 1627625, 17.793,
+                            9831510, 3044048, 33.278, 9147420, 2485000,
+                            27.166, 1990747, 21.763]])
         expected = pd.DataFrame(values, index=exp_idx, columns=exp_col)
         tm.assert_frame_equal(result, expected)

pandas_datareader/io/tests/test_sdmx.py

@@ -18,17 +18,19 @@ def test_tourism(self):
         # Eurostat
         # Employed doctorate holders in non managerial and non professional
         # occupations by fields of science (%)
-        dsd = _read_sdmx_dsd(os.path.join(self.dirpath, 'sdmx', 'DSD_cdh_e_fos.xml'))
-        df = read_sdmx(os.path.join(self.dirpath, 'sdmx', 'cdh_e_fos.xml'), dsd=dsd)
+        dsd = _read_sdmx_dsd(os.path.join(self.dirpath, 'sdmx',
+                                          'DSD_cdh_e_fos.xml'))
+        df = read_sdmx(os.path.join(self.dirpath, 'sdmx',
+                                    'cdh_e_fos.xml'), dsd=dsd)
 
-        self.assertTrue(isinstance(df, pd.DataFrame))
-        self.assertEqual(df.shape, (2, 336))
+        assert isinstance(df, pd.DataFrame)
+        assert df.shape == (2, 336)
 
         df = df['Percentage']['Total']['Natural sciences']
         df = df[['Norway', 'Poland', 'Portugal', 'Russia']]
 
-        exp_col = pd.MultiIndex.from_product([['Norway', 'Poland', 'Portugal', 'Russia'],
-                                              ['Annual']],
+        exp_col = pd.MultiIndex.from_product([['Norway', 'Poland', 'Portugal',
+                                               'Russia'], ['Annual']],
                                              names=['GEO', 'FREQ'])
         exp_idx = pd.DatetimeIndex(['2009', '2006'], name='TIME_PERIOD')
 

pandas_datareader/tests/test_base.py

@@ -1,27 +1,28 @@
+import pytest
 import pandas.util.testing as tm
 import pandas_datareader.base as base
 
 
 class TestBaseReader(tm.TestCase):
     def test_valid_retry_count(self):
-        with tm.assertRaises(ValueError):
+        with pytest.raises(ValueError):
             base._BaseReader([], retry_count='stuff')
-        with tm.assertRaises(ValueError):
+        with pytest.raises(ValueError):
             base._BaseReader([], retry_count=-1)
 
     def test_invalid_url(self):
-        with tm.assertRaises(NotImplementedError):
+        with pytest.raises(NotImplementedError):
             base._BaseReader([]).url
 
     def test_invalid_format(self):
-        with tm.assertRaises(NotImplementedError):
+        with pytest.raises(NotImplementedError):
             b = base._BaseReader([])
             b._format = 'IM_NOT_AN_IMPLEMENTED_TYPE'
             b._read_one_data('a', None)
 
 
 class TestDailyBaseReader(tm.TestCase):
     def test_get_params(self):
-        with tm.assertRaises(NotImplementedError):
+        with pytest.raises(NotImplementedError):
             b = base._DailyBaseReader()
             b._get_params()

pandas_datareader/tests/test_data.py

@@ -1,3 +1,5 @@
+import pytest
+
 import pandas.util.testing as tm
 import pandas_datareader.data as web
 
@@ -20,10 +22,6 @@ def test_options_source_warning(self):
 
 
 class TestDataReader(tm.TestCase):
-    def test_is_s3_url(self):
-        from pandas.io.common import _is_s3_url
-        self.assertTrue(_is_s3_url("s3://pandas/somethingelse.com"))
-
     def test_read_yahoo(self):
         gs = DataReader("GS", "yahoo")
         assert isinstance(gs, DataFrame)
@@ -41,4 +39,5 @@ def test_read_fred(self):
         assert isinstance(vix, DataFrame)
 
     def test_not_implemented(self):
-        self.assertRaises(NotImplementedError, DataReader, "NA", "NA")
+        with pytest.raises(NotImplementedError):
+            DataReader("NA", "NA")

pandas_datareader/tests/test_edgar.py

@@ -32,10 +32,10 @@ def test_get_nonzip_index_and_low_date(self):
             ed = web.DataReader('daily', 'edgar-index', '1994-06-30',
                                 '1994-07-02')
             assert len(ed) > 200
+            assert ed.index.nlevels == 2
 
-            self.assertEqual(ed.index.nlevels, 2)
             dti = ed.index.get_level_values(0)
-            self.assertIsInstance(dti, pd.DatetimeIndex)
+            assert isinstance(dti, pd.DatetimeIndex)
             exp_columns = pd.Index(['company_name', 'form_type',
                                     'filename'], dtype='object')
             tm.assert_index_equal(ed.columns, exp_columns)
@@ -57,12 +57,12 @@ def test_6_digit_date(self):
             ed = web.DataReader('daily', 'edgar-index', start='1998-05-18',
                                 end='1998-05-18')
             assert len(ed) < 1200
+            assert ed.index.nlevels == 2
 
-            self.assertEqual(ed.index.nlevels, 2)
             dti = ed.index.get_level_values(0)
-            self.assertIsInstance(dti, pd.DatetimeIndex)
-            self.assertEqual(dti[0], pd.Timestamp('1998-05-18'))
-            self.assertEqual(dti[-1], pd.Timestamp('1998-05-18'))
+            assert isinstance(dti, pd.DatetimeIndex)
+            assert dti[0] == pd.Timestamp('1998-05-18')
+            assert dti[-1] == pd.Timestamp('1998-05-18')
 
             exp_columns = pd.Index(['company_name', 'form_type',
                                     'filename'], dtype='object')

pandas_datareader/tests/test_enigma.py

@@ -22,26 +22,24 @@ def test_enigma_datareader(self):
         try:
             df = web.DataReader('enigma.inspections.restaurants.fl',
                                 'enigma', access_key=TEST_API_KEY)
-            self.assertTrue('serialid' in df.columns)
+            assert 'serialid' in df.columns
         except HTTPError as e:  # pragma: no cover
             pytest.skip(e)
 
     def test_enigma_get_data_enigma(self):
         try:
             df = pdr.get_data_enigma(
                 'enigma.inspections.restaurants.fl', TEST_API_KEY)
-            self.assertTrue('serialid' in df.columns)
+            assert 'serialid' in df.columns
         except HTTPError as e:  # pragma: no cover
             pytest.skip(e)
 
     def test_bad_key(self):
-        with tm.assertRaises(HTTPError):
+        with pytest.raises(HTTPError):
             web.DataReader('enigma.inspections.restaurants.fl',
-                           'enigma',
-                           access_key=TEST_API_KEY + 'xxx')
+                           'enigma', access_key=TEST_API_KEY + 'xxx')
 
     def test_bad_url(self):
-        with tm.assertRaises(HTTPError):
+        with pytest.raises(HTTPError):
             web.DataReader('enigma.inspections.restaurants.fllzzy',
-                           'enigma',
-                           access_key=TEST_API_KEY)
+                           'enigma', access_key=TEST_API_KEY)

pandas_datareader/tests/test_eurostat.py

@@ -13,8 +13,8 @@ def test_get_cdh_e_fos(self):
                             start=pd.Timestamp('2005-01-01'),
                             end=pd.Timestamp('2010-01-01'))
 
-        self.assertTrue(isinstance(df, pd.DataFrame))
-        self.assertEqual(df.shape, (2, 336))
+        assert isinstance(df, pd.DataFrame)
+        assert df.shape == (2, 336)
 
         df = df['Percentage']['Total']['Natural sciences']
         df = df[['Norway', 'Poland', 'Portugal', 'Russia']]
@@ -40,7 +40,8 @@ def test_get_sts_cobp_a(self):
                             name='TIME_PERIOD')
         ne_name = ('Index, 2010=100',
                    'Building permits - m2 of useful floor area',
-                   'Unadjusted data (i.e. neither seasonally adjusted nor calendar adjusted data)',
+                   'Unadjusted data (i.e. neither seasonally adjusted nor '
+                   'calendar adjusted data)',
                    'Non-residential buildings, except office buildings',
                    'Netherlands', 'Annual')
         ne_values = [200.0, 186.5, 127.3, 130.7, 143.3, 147.8, 176.7,
@@ -49,7 +50,8 @@ def test_get_sts_cobp_a(self):
 
         uk_name = ('Index, 2010=100',
                    'Building permits - m2 of useful floor area',
-                   'Unadjusted data (i.e. neither seasonally adjusted nor calendar adjusted data)',
+                   'Unadjusted data (i.e. neither seasonally adjusted nor '
+                   'calendar adjusted data)',
                    'Non-residential buildings, except office buildings',
                    'United Kingdom', 'Annual')
         uk_values = [112.5, 113.3, 110.2, 112.1, 119.1, 112.7, 113.1,

pandas_datareader/tests/test_famafrench.py

@@ -18,24 +18,24 @@ def test_get_data(self):
 
         for name in keys:
             ff = web.DataReader(name, 'famafrench')
-            self.assertTrue('DESCR' in ff)
-            self.assertTrue(len(ff) > 1)
+            assert 'DESCR' in ff
+            assert len(ff) > 1
 
     def test_get_available_datasets(self):
         pytest.importorskip("lxml")
         l = get_available_datasets()
-        self.assertTrue(len(l) > 100)
+        assert len(l) > 100
 
     def test_index(self):
         ff = web.DataReader('F-F_Research_Data_Factors', 'famafrench')
-        self.assertEqual(ff[0].index.freq, 'M')
-        self.assertEqual(ff[1].index.freq, 'A-DEC')
+        assert ff[0].index.freq == 'M'
+        assert ff[1].index.freq == 'A-DEC'
 
     def test_f_f_research(self):
         results = web.DataReader("F-F_Research_Data_Factors", "famafrench",
                                  start='2010-01-01', end='2010-12-01')
-        self.assertTrue(isinstance(results, dict))
-        self.assertEqual(len(results), 3)
+        assert isinstance(results, dict)
+        assert len(results) == 3
 
         exp = pd.DataFrame({'Mkt-RF': [-3.36, 3.4, 6.31, 2., -7.89, -5.56,
                                        6.93, -4.77, 9.54, 3.88, 0.6, 6.82],
@@ -45,38 +45,45 @@ def test_f_f_research(self):
                                     -1.96, -3.12, -2.52, -0.91, 3.78],
                             'RF': [0., 0., 0.01, 0.01, 0.01, 0.01, 0.01,
                                    0.01, 0.01, 0.01, 0.01, 0.01]},
-                           index=pd.period_range('2010-01-01', '2010-12-01', freq='M', name='Date'),
+                           index=pd.period_range('2010-01-01', '2010-12-01',
+                                                 freq='M', name='Date'),
                            columns=['Mkt-RF', 'SMB', 'HML', 'RF'])
         tm.assert_frame_equal(results[0], exp)
 
     def test_me_breakpoints(self):
         results = web.DataReader("ME_Breakpoints", "famafrench",
                                  start='2010-01-01', end='2010-12-01')
-        self.assertTrue(isinstance(results, dict))
-        self.assertEqual(len(results), 2)
-        self.assertEqual(results[0].shape, (12, 21))
-
-        exp_columns = pd.Index(['Count', (0, 5), (5, 10), (10, 15), (15, 20), (20, 25),
-                                (25, 30), (30, 35), (35, 40), (40, 45), (45, 50), (50, 55),
-                                (55, 60), (60, 65), (65, 70), (70, 75), (75, 80), (80, 85),
-                                (85, 90), (90, 95), (95, 100)], dtype='object')
+        assert isinstance(results, dict)
+        assert len(results) == 2
+        assert results[0].shape == (12, 21)
+
+        exp_columns = pd.Index(['Count', (0, 5), (5, 10), (10, 15), (15, 20),
+                                (20, 25), (25, 30), (30, 35), (35, 40),
+                                (40, 45), (45, 50), (50, 55), (55, 60),
+                                (60, 65), (65, 70), (70, 75), (75, 80),
+                                (80, 85), (85, 90), (90, 95), (95, 100)],
+                               dtype='object')
         tm.assert_index_equal(results[0].columns, exp_columns)
 
-        exp_index = pd.period_range('2010-01-01', '2010-12-01', freq='M', name='Date')
+        exp_index = pd.period_range('2010-01-01', '2010-12-01',
+                                    freq='M', name='Date')
         tm.assert_index_equal(results[0].index, exp_index)
 
     def test_prior_2_12_breakpoints(self):
         results = web.DataReader("Prior_2-12_Breakpoints", "famafrench",
                                  start='2010-01-01', end='2010-12-01')
-        self.assertTrue(isinstance(results, dict))
-        self.assertEqual(len(results), 2)
-        self.assertEqual(results[0].shape, (12, 22))
-
-        exp_columns = pd.Index(['<=0', '>0', (0, 5), (5, 10), (10, 15), (15, 20), (20, 25),
-                                (25, 30), (30, 35), (35, 40), (40, 45), (45, 50), (50, 55),
-                                (55, 60), (60, 65), (65, 70), (70, 75), (75, 80), (80, 85),
-                                (85, 90), (90, 95), (95, 100)], dtype='object')
+        assert isinstance(results, dict)
+        assert len(results) == 2
+        assert results[0].shape == (12, 22)
+
+        exp_columns = pd.Index(['<=0', '>0', (0, 5), (5, 10), (10, 15),
+                                (15, 20), (20, 25), (25, 30), (30, 35),
+                                (35, 40), (40, 45), (45, 50), (50, 55),
+                                (55, 60), (60, 65), (65, 70), (70, 75),
+                                (75, 80), (80, 85), (85, 90), (90, 95),
+                                (95, 100)], dtype='object')
         tm.assert_index_equal(results[0].columns, exp_columns)
 
-        exp_index = pd.period_range('2010-01-01', '2010-12-01', freq='M', name='Date')
+        exp_index = pd.period_range('2010-01-01', '2010-12-01',
+                                    freq='M', name='Date')
         tm.assert_index_equal(results[0].index, exp_index)