def test_all_missing_data(self):
mdc = NumericMetadataColumn(pd.Series(
[np.nan, np.nan, np.nan], name='col1',
index=pd.Index(['a', 'b', 'c'], name='id')))
obs = mdc.to_series()
exp = pd.Series(
[np.nan, np.nan, np.nan], name='col1',
index=pd.Index(['a', 'b', 'c'], name='id'))
pdt.assert_series_equal(obs, exp)
self.assertEqual(obs.dtype, np.float64)
def test_all_missing_data(self):
mdc = NumericMetadataColumn(
pd.Series([np.nan, np.nan, np.nan],
name='col1',
index=pd.Index(['a', 'b', 'c'], name='id')))
obs = mdc.to_series()
exp = pd.Series([np.nan, np.nan, np.nan],
name='col1',
index=pd.Index(['a', 'b', 'c'], name='id'))
pdt.assert_series_equal(obs, exp)
self.assertEqual(obs.dtype, np.float64)
def test_supported_dtype_float(self):
series = pd.Series([1.23, np.nan, 4.56, -7.891],
name='my column',
index=pd.Index(['a', 'b', 'c', 'd'], name='id'))
mdc = NumericMetadataColumn(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, np.float64)
def test_supported_dtype_float(self):
series = pd.Series(
[1.23, np.nan, 4.56, -7.891], name='my column',
index=pd.Index(['a', 'b', 'c', 'd'], name='id'))
mdc = NumericMetadataColumn(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, np.float64)
def test_missing_data_normalized(self):
# Different missing data representations should be normalized to np.nan
mdc = NumericMetadataColumn(pd.Series(
[np.nan, 4.2, float('nan'), -5.678], name='col1',
index=pd.Index(['a', 'b', 'c', 'd'], name='id')))
obs = mdc.to_series()
exp = pd.Series(
[np.nan, 4.2, np.nan, -5.678], name='col1',
index=pd.Index(['a', 'b', 'c', 'd'], name='id'))
pdt.assert_series_equal(obs, exp)
self.assertEqual(obs.dtype, np.float64)
self.assertTrue(np.isnan(obs['a']))
self.assertTrue(np.isnan(obs['c']))
def test_missing_data_normalized(self):
# Different missing data representations should be normalized to np.nan
mdc = NumericMetadataColumn(
pd.Series([np.nan, 4.2, float('nan'), -5.678],
name='col1',
index=pd.Index(['a', 'b', 'c', 'd'], name='id')))
obs = mdc.to_series()
exp = pd.Series([np.nan, 4.2, np.nan, -5.678],
name='col1',
index=pd.Index(['a', 'b', 'c', 'd'], name='id'))
pdt.assert_series_equal(obs, exp)
self.assertEqual(obs.dtype, np.float64)
self.assertTrue(np.isnan(obs['a']))
self.assertTrue(np.isnan(obs['c']))
def test_supported_dtype_int(self):
series = pd.Series([0, 1, 42, -2],
name='my column',
index=pd.Index(['a', 'b', 'c', 'd'], name='id'))
mdc = NumericMetadataColumn(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()
exp_series = pd.Series([0.0, 1.0, 42.0, -2.0],
name='my column',
index=pd.Index(['a', 'b', 'c', 'd'], name='id'))
pdt.assert_series_equal(obs_series, exp_series)
self.assertEqual(obs_series.dtype, np.float64)
def test_supported_dtype_int(self):
series = pd.Series(
[0, 1, 42, -2], name='my column',
index=pd.Index(['a', 'b', 'c', 'd'], name='id'))
mdc = NumericMetadataColumn(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()
exp_series = pd.Series(
[0.0, 1.0, 42.0, -2.0], name='my column',
index=pd.Index(['a', 'b', 'c', 'd'], name='id'))
pdt.assert_series_equal(obs_series, exp_series)
self.assertEqual(obs_series.dtype, np.float64)