def test_all_missing_data(self):
mdc = CategoricalMetadataColumn(pd.Series(
np.array([np.nan, np.nan, np.nan], dtype=object), name='col1',
index=pd.Index(['a', 'b', 'c'], name='id')))
obs = mdc.to_series()
exp = pd.Series(
np.array([np.nan, np.nan, np.nan], dtype=object), name='col1',
index=pd.Index(['a', 'b', 'c'], name='id'))
pdt.assert_series_equal(obs, exp)
self.assertEqual(obs.dtype, object)
def test_all_missing_data(self):
mdc = CategoricalMetadataColumn(
pd.Series(np.array([np.nan, np.nan, np.nan], dtype=object),
name='col1',
index=pd.Index(['a', 'b', 'c'], name='id')))
obs = mdc.to_series()
exp = pd.Series(np.array([np.nan, np.nan, np.nan], dtype=object),
name='col1',
index=pd.Index(['a', 'b', 'c'], name='id'))
pdt.assert_series_equal(obs, exp)
self.assertEqual(obs.dtype, object)
def test_numeric_strings_preserved_as_strings(self):
series = pd.Series(['1', np.nan, '2.5', '3.0'],
name='my column',
index=pd.Index(['a', 'b', 'c', 'd'], name='id'))
mdc = CategoricalMetadataColumn(series)
self.assertEqual(mdc.id_count, 4)
self.assertEqual(mdc.id_header, 'id')
self.assertEqual(mdc.ids, ('a', 'b', 'c', 'd'))
self.assertEqual(mdc.name, 'my column')
obs_series = mdc.to_series()
pdt.assert_series_equal(obs_series, series)
self.assertEqual(obs_series.dtype, object)
def test_supported_dtype(self):
series = pd.Series(['foo', np.nan, 'bar', 'foo'],
name='my column',
index=pd.Index(['a', 'b', 'c', 'd'], name='id'))
mdc = CategoricalMetadataColumn(series)
self.assertEqual(mdc.id_count, 4)
self.assertEqual(mdc.id_header, 'id')
self.assertEqual(mdc.ids, ('a', 'b', 'c', 'd'))
self.assertEqual(mdc.name, 'my column')
obs_series = mdc.to_series()
pdt.assert_series_equal(obs_series, series)
self.assertEqual(obs_series.dtype, object)
def test_numeric_strings_preserved_as_strings(self):
series = pd.Series(
['1', np.nan, '2.5', '3.0'], name='my column',
index=pd.Index(['a', 'b', 'c', 'd'], name='id'))
mdc = CategoricalMetadataColumn(series)
self.assertEqual(mdc.id_count, 4)
self.assertEqual(mdc.id_header, 'id')
self.assertEqual(mdc.ids, ('a', 'b', 'c', 'd'))
self.assertEqual(mdc.name, 'my column')
obs_series = mdc.to_series()
pdt.assert_series_equal(obs_series, series)
self.assertEqual(obs_series.dtype, object)
def test_supported_dtype(self):
series = pd.Series(
['foo', np.nan, 'bar', 'foo'], name='my column',
index=pd.Index(['a', 'b', 'c', 'd'], name='id'))
mdc = CategoricalMetadataColumn(series)
self.assertEqual(mdc.id_count, 4)
self.assertEqual(mdc.id_header, 'id')
self.assertEqual(mdc.ids, ('a', 'b', 'c', 'd'))
self.assertEqual(mdc.name, 'my column')
obs_series = mdc.to_series()
pdt.assert_series_equal(obs_series, series)
self.assertEqual(obs_series.dtype, object)
def test_missing_data_normalized(self):
# Different missing data representations should be normalized to np.nan
mdc = CategoricalMetadataColumn(pd.Series(
[np.nan, 'foo', float('nan'), None], name='col1',
index=pd.Index(['a', 'b', 'c', 'd'], name='id')))
obs = mdc.to_series()
exp = pd.Series(
[np.nan, 'foo', np.nan, np.nan], name='col1',
index=pd.Index(['a', 'b', 'c', 'd'], name='id'))
pdt.assert_series_equal(obs, exp)
self.assertEqual(obs.dtype, object)
self.assertTrue(np.isnan(obs['a']))
self.assertTrue(np.isnan(obs['c']))
self.assertTrue(np.isnan(obs['d']))
def test_missing_data_normalized(self):
# Different missing data representations should be normalized to np.nan
mdc = CategoricalMetadataColumn(
pd.Series([np.nan, 'foo', float('nan'), None],
name='col1',
index=pd.Index(['a', 'b', 'c', 'd'], name='id')))
obs = mdc.to_series()
exp = pd.Series([np.nan, 'foo', np.nan, np.nan],
name='col1',
index=pd.Index(['a', 'b', 'c', 'd'], name='id'))
pdt.assert_series_equal(obs, exp)
self.assertEqual(obs.dtype, object)
self.assertTrue(np.isnan(obs['a']))
self.assertTrue(np.isnan(obs['c']))
self.assertTrue(np.isnan(obs['d']))