def test_with_artifacts(self):
artifact1 = Artifact.import_data('Mapping', {'a': '1', 'b': '2'})
artifact2 = Artifact.import_data('Mapping', {'d': '4'})
md_from_artifact1 = Metadata.from_artifact(artifact1)
md_from_artifact2 = Metadata.from_artifact(artifact2)
md_no_artifact = Metadata(
pd.DataFrame({'c': ['3', '42']},
index=pd.Index(['0', '1'], name='id')))
# Merge three metadata objects -- the first has an artifact, the second
# does not, and the third has an artifact.
obs_md = md_from_artifact1.merge(md_no_artifact, md_from_artifact2)
exp_df = pd.DataFrame({
'a': '1',
'b': '2',
'c': '3',
'd': '4'
},
index=pd.Index(['0'], name='id'))
exp_md = Metadata(exp_df)
exp_md._add_artifacts((artifact1, artifact2))
self.assertEqual(obs_md, exp_md)
self.assertEqual(obs_md.artifacts, (artifact1, artifact2))
def test_artifact_mismatch(self):
# Metadata created from different artifacts shouldn't compare equal,
# even if the data is the same.
artifact1 = Artifact.import_data('Mapping', {'a': '1', 'b': '2'})
artifact2 = Artifact.import_data('Mapping', {'a': '1', 'b': '2'})
md1 = Metadata.from_artifact(artifact1)
md2 = Metadata.from_artifact(artifact2)
pdt.assert_frame_equal(md1.to_dataframe(), md2.to_dataframe())
self.assertReallyNotEqual(md1, md2)
def test_source_mismatch(self):
# Metadata created from an artifact vs not shouldn't compare equal,
# even if the data is the same.
artifact = Artifact.import_data('Mapping', {'a': '1', 'b': '2'})
md_from_artifact = Metadata.from_artifact(artifact)
md_no_artifact = Metadata(md_from_artifact.to_dataframe())
pdt.assert_frame_equal(md_from_artifact.to_dataframe(),
md_no_artifact.to_dataframe())
self.assertReallyNotEqual(md_from_artifact, md_no_artifact)
def test_artifacts_are_propagated(self):
A = Artifact.import_data('Mapping', {'a': '1', 'b': '3'})
md = Metadata.from_artifact(A)
obs = md.get_column('b')
# TODO update to use MetadataColumn.__eq__
self.assertEqual(obs.artifacts, (A, ))
pdt.assert_series_equal(
obs.to_series(),
pd.Series(['3'], index=pd.Index(['0'], name='id'), name='b'))
def test_from_artifact(self):
A = Artifact.import_data('Mapping', {'a': '1', 'b': '3'})
obs_md = Metadata.from_artifact(A)
exp_df = pd.DataFrame({
'a': '1',
'b': '3'
},
index=pd.Index(['0'], name='id', dtype=object),
dtype=object)
exp_md = Metadata(exp_df)
exp_md._add_artifacts([A])
self.assertEqual(obs_md, exp_md)
def test_equality_with_artifact(self):
artifact = Artifact.import_data('Mapping', {'a': '1', 'b': '2'})
md1 = Metadata.from_artifact(artifact)
md2 = Metadata.from_artifact(artifact)
self.assertReallyEqual(md1, md2)
def test_artifacts(self):
A = Artifact.import_data('Mapping', {'a': 'abc', 'b': '-42'})
md = Metadata.from_artifact(A)
obs = md.artifacts
self.assertEqual(obs, (A, ))
def test_from_bad_artifact(self):
A = Artifact.import_data('IntSequence1', [1, 2, 3, 4])
with self.assertRaisesRegex(ValueError, 'Artifact has no metadata'):
Metadata.from_artifact(A)