def test_write_v4_archive(self):
fp = os.path.join(self.temp_dir.name, 'artifact_v1.qza')
with artifact_version(4):
artifact = Artifact._from_view(FourInts, [-1, 42, 0, 43], list,
self.provenance_capture)
artifact.save(fp)
root_dir = str(artifact.uuid)
expected = {
'VERSION',
'metadata.yaml',
'data/file1.txt',
'data/file2.txt',
'data/nested/file3.txt',
'data/nested/file4.txt',
'provenance/metadata.yaml',
'provenance/VERSION',
'provenance/citations.bib',
'provenance/action/action.yaml',
}
self.assertArchiveMembers(fp, root_dir, expected)
with zipfile.ZipFile(fp, mode='r') as zf:
version = zf.read(os.path.join(root_dir, 'VERSION'))
self.assertRegex(str(version), '^.*archive: 4.*$')
def test_from_view_and_save(self):
fp = os.path.join(self.test_dir.name, 'artifact.qza')
# Using four-ints data layout because it has multiple files, some of
# which are in a nested directory.
artifact = Artifact._from_view(FourInts, [-1, 42, 0, 43], list,
self.provenance_capture)
artifact.save(fp)
root_dir = str(artifact.uuid)
expected = {
'VERSION',
'checksums.md5',
'metadata.yaml',
'data/file1.txt',
'data/file2.txt',
'data/nested/file3.txt',
'data/nested/file4.txt',
'provenance/metadata.yaml',
'provenance/VERSION',
'provenance/citations.bib',
'provenance/action/action.yaml'
}
self.assertArchiveMembers(fp, root_dir, expected)
def test_from_view_and_save(self):
fp = os.path.join(self.test_dir.name, 'artifact.qza')
# Using four-ints data layout because it has multiple files, some of
# which are in a nested directory.
artifact = Artifact._from_view(FourInts, [-1, 42, 0, 43], list,
self.provenance_capture)
artifact.save(fp)
root_dir = str(artifact.uuid)
expected = {
'VERSION',
'checksums.md5',
'metadata.yaml',
'data/file1.txt',
'data/file2.txt',
'data/nested/file3.txt',
'data/nested/file4.txt',
'provenance/metadata.yaml',
'provenance/VERSION',
'provenance/citations.bib',
'provenance/action/action.yaml'
}
self.assertArchiveMembers(fp, root_dir, expected)
def test_write_v1_archive(self):
fp = os.path.join(self.temp_dir.name, 'artifact_v1.qza')
with artifact_version(1):
artifact = Artifact._from_view(FourInts, [-1, 42, 0, 43], list,
self.provenance_capture)
artifact.save(fp)
root_dir = str(artifact.uuid)
expected = {
'VERSION',
'metadata.yaml',
'data/file1.txt',
'data/file2.txt',
'data/nested/file3.txt',
'data/nested/file4.txt',
'provenance/metadata.yaml',
'provenance/VERSION',
'provenance/action/action.yaml',
}
self.assertArchiveMembers(fp, root_dir, expected)
with zipfile.ZipFile(fp, mode='r') as zf:
version = zf.read(os.path.join(root_dir, 'VERSION'))
self.assertRegex(str(version), '^.*archive: 1.*$')
def test_writer_transformer(self):
# `Artifact._from_view` invokes transformer that handles `dataframe` ->
# `WinnowedFormat` with all input, because the `WinnowedDirectoryFormat` has
# been registered as the directory format for the semantic type.
artifact = Artifact._from_view(Winnowed, [(exp_featureOrdering, exp_auc, exp_permanova)],
list, archive.ImportProvenanceCapture())
# Test that the directory and file format can be read again.
got_featureOrdering, got_auc, got_permanova = artifact.view( list )[0]
pd.testing.assert_frame_equal(
got_featureOrdering.astype(str),
exp_featureOrdering.astype(str),
check_dtype=False
) # Avoid checking values since reading df stores as objects while, hard coding in does not
# ex) bool(False) == Object(False) in pandas is False although the values function the same.
pd.testing.assert_frame_equal(
got_auc.astype(str),
exp_auc.astype(str),
check_dtype=False
)
pd.testing.assert_frame_equal(
got_permanova.astype(str),
exp_permanova.astype(str),
check_dtype=False
)
def test_from_view(self):
artifact = Artifact._from_view(FourInts, [-1, 42, 0, 43], list,
self.provenance_capture)
self.assertEqual(artifact.type, FourInts)
# We don't know what the UUID is because it's generated within
# Artifact._from_view.
self.assertIsInstance(artifact.uuid, uuid.UUID)
self.assertEqual(artifact.view(list), [-1, 42, 0, 43])
# Can produce same view if called again.
self.assertEqual(artifact.view(list), [-1, 42, 0, 43])
def test_from_view(self):
artifact = Artifact._from_view(FourInts, [-1, 42, 0, 43], list,
self.provenance_capture)
self.assertEqual(artifact.type, FourInts)
# We don't know what the UUID is because it's generated within
# Artifact._from_view.
self.assertIsInstance(artifact.uuid, uuid.UUID)
self.assertEqual(artifact.view(list), [-1, 42, 0, 43])
# Can produce same view if called again.
self.assertEqual(artifact.view(list), [-1, 42, 0, 43])
def test_writer_transformer(self):
# `Artifact._from_view` invokes transformer that handles `dict` ->
# `MappingFormat`, because the `MappingDirectoryFormat` has
# been registered as the directory format for the semantic type.
# We didn't define a `MappingDirectoryFormat` ->
# `MappingFormat` tranformer because
# `model.SingleFileDirectoryFormat` handles that transformation for
# us.
artifact = Artifact._from_view(Mapping, {'abc': 'cat', 'def': 'dog'},
dict, archive.ImportProvenanceCapture())
# Test that the directory and file format can be read again.
self.assertEqual(artifact.view(dict), {'abc': 'cat', 'def': 'dog'})
def test_writer_transformer(self):
for type in IntSequence1, IntSequence2:
# `Artifact._from_view` invokes transformer that handles `list` ->
# `SingleIntFormat`, because the `SingleIntDirectoryFormat` has
# been registered as the directory format for the semantic type.
# We didn't define a `SingleIntDirectoryFormat` ->
# `SingleIntFormat` tranformer because
# `model.SingleFileDirectoryFormat` handles that transformation for
# us.
artifact = Artifact._from_view(type, [1, 2, 42, -999, 42, 0], list,
archive.ImportProvenanceCapture())
# Test that the directory and file format can be read again.
self.assertEqual(artifact.view(list), [1, 2, 42, -999, 42, 0])
def test_writer_transformer(self):
for type in IntSequence1, IntSequence2:
# `Artifact._from_view` invokes transformer that handles `list` ->
# `SingleIntFormat`, because the `SingleIntDirectoryFormat` has
# been registered as the directory format for the semantic type.
# We didn't define a `SingleIntDirectoryFormat` ->
# `SingleIntFormat` tranformer because
# `model.SingleFileDirectoryFormat` handles that transformation for
# us.
artifact = Artifact._from_view(type, [1, 2, 42, -999, 42, 0], list,
archive.ImportProvenanceCapture())
# Test that the directory and file format can be read again.
self.assertEqual(artifact.view(list), [1, 2, 42, -999, 42, 0])
def test_writer_transformer(self):
# `Artifact._from_view` invokes transformer that handles `dict` ->
# `MappingFormat`, because the `MappingDirectoryFormat` has
# been registered as the directory format for the semantic type.
# We didn't define a `MappingDirectoryFormat` ->
# `MappingFormat` tranformer because
# `model.SingleFileDirectoryFormat` handles that transformation for
# us.
artifact = Artifact._from_view(Mapping, {
'abc': 'cat',
'def': 'dog'
}, dict, archive.ImportProvenanceCapture())
# Test that the directory and file format can be read again.
self.assertEqual(artifact.view(dict), {'abc': 'cat', 'def': 'dog'})
def test_from_view_different_type_with_multiple_view_types(self):
artifact = Artifact._from_view(IntSequence1, [42, 42, 43, -999, 42],
list, self.provenance_capture)
self.assertEqual(artifact.type, IntSequence1)
self.assertIsInstance(artifact.uuid, uuid.UUID)
self.assertEqual(artifact.view(list),
[42, 42, 43, -999, 42])
self.assertEqual(artifact.view(list),
[42, 42, 43, -999, 42])
self.assertEqual(artifact.view(collections.Counter),
collections.Counter({42: 3, 43: 1, -999: 1}))
self.assertEqual(artifact.view(collections.Counter),
collections.Counter({42: 3, 43: 1, -999: 1}))
def test_from_view_different_type_with_multiple_view_types(self):
artifact = Artifact._from_view(IntSequence1, [42, 42, 43, -999, 42],
list, self.provenance_capture)
self.assertEqual(artifact.type, IntSequence1)
self.assertIsInstance(artifact.uuid, uuid.UUID)
self.assertEqual(artifact.view(list),
[42, 42, 43, -999, 42])
self.assertEqual(artifact.view(list),
[42, 42, 43, -999, 42])
self.assertEqual(artifact.view(collections.Counter),
collections.Counter({42: 3, 43: 1, -999: 1}))
self.assertEqual(artifact.view(collections.Counter),
collections.Counter({42: 3, 43: 1, -999: 1}))