def test_index_and_column_merge_order(self):
md1 = Metadata(
pd.DataFrame([[1], [2], [3], [4]],
index=pd.Index(['id1', 'id2', 'id3', 'id4'],
name='id'),
columns=['a']))
md2 = Metadata(
pd.DataFrame([[5], [6], [7]],
index=pd.Index(['id4', 'id3', 'id1'], name='id'),
columns=['b']))
md3 = Metadata(
pd.DataFrame([[8], [9], [10]],
index=pd.Index(['id1', 'id4', 'id3'], name='id'),
columns=['c']))
obs = md1.merge(md2, md3)
exp = Metadata(
pd.DataFrame([[1, 7, 8], [3, 6, 10], [4, 5, 9]],
index=pd.Index(['id1', 'id3', 'id4'], name='id'),
columns=['a', 'b', 'c']))
self.assertEqual(obs, exp)
# Merging in different order produces different ID/column order.
obs = md2.merge(md1, md3)
exp = Metadata(
pd.DataFrame([[5, 4, 9], [6, 3, 10], [7, 1, 8]],
index=pd.Index(['id4', 'id3', 'id1'], name='id'),
columns=['b', 'a', 'c']))
self.assertEqual(obs, exp)
def test_inner_join(self):
md1 = Metadata(pd.DataFrame(
{'a': [1, 2, 3], 'b': [4, 5, 6]},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
md2 = Metadata(pd.DataFrame(
{'c': [7, 8, 9], 'd': [10, 11, 12]},
index=pd.Index(['id2', 'X', 'Y'], name='id')))
md3 = Metadata(pd.DataFrame(
{'e': [13, 14, 15], 'f': [16, 17, 18]},
index=pd.Index(['X', 'id3', 'id2'], name='id')))
# Single shared ID.
obs = md1.merge(md2, md3)
exp = Metadata(pd.DataFrame(
{'a': [2], 'b': [5], 'c': [7], 'd': [10], 'e': [15], 'f': [18]},
index=pd.Index(['id2'], name='id')))
self.assertEqual(obs, exp)
# Multiple shared IDs.
obs = md1.merge(md3)
exp = Metadata(pd.DataFrame(
{'a': [2, 3], 'b': [5, 6], 'e': [15, 14], 'f': [18, 17]},
index=pd.Index(['id2', 'id3'], name='id')))
self.assertEqual(obs, exp)
def test_inner_join(self):
md1 = Metadata(pd.DataFrame(
{'a': [1, 2, 3], 'b': [4, 5, 6]},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
md2 = Metadata(pd.DataFrame(
{'c': [7, 8, 9], 'd': [10, 11, 12]},
index=pd.Index(['id2', 'X', 'Y'], name='id')))
md3 = Metadata(pd.DataFrame(
{'e': [13, 14, 15], 'f': [16, 17, 18]},
index=pd.Index(['X', 'id3', 'id2'], name='id')))
# Single shared ID.
obs = md1.merge(md2, md3)
exp = Metadata(pd.DataFrame(
{'a': [2], 'b': [5], 'c': [7], 'd': [10], 'e': [15], 'f': [18]},
index=pd.Index(['id2'], name='id')))
self.assertEqual(obs, exp)
# Multiple shared IDs.
obs = md1.merge(md3)
exp = Metadata(pd.DataFrame(
{'a': [2, 3], 'b': [5, 6], 'e': [15, 14], 'f': [18, 17]},
index=pd.Index(['id2', 'id3'], name='id')))
self.assertEqual(obs, exp)
def test_index_and_column_merge_order(self):
md1 = Metadata(pd.DataFrame(
[[1], [2], [3], [4]],
index=pd.Index(['id1', 'id2', 'id3', 'id4'], name='id'),
columns=['a']))
md2 = Metadata(pd.DataFrame(
[[5], [6], [7]], index=pd.Index(['id4', 'id3', 'id1'], name='id'),
columns=['b']))
md3 = Metadata(pd.DataFrame(
[[8], [9], [10]], index=pd.Index(['id1', 'id4', 'id3'], name='id'),
columns=['c']))
obs = md1.merge(md2, md3)
exp = Metadata(pd.DataFrame(
[[1, 7, 8], [3, 6, 10], [4, 5, 9]],
index=pd.Index(['id1', 'id3', 'id4'], name='id'),
columns=['a', 'b', 'c']))
self.assertEqual(obs, exp)
# Merging in different order produces different ID/column order.
obs = md2.merge(md1, md3)
exp = Metadata(pd.DataFrame(
[[5, 4, 9], [6, 3, 10], [7, 1, 8]],
index=pd.Index(['id4', 'id3', 'id1'], name='id'),
columns=['b', 'a', 'c']))
self.assertEqual(obs, exp)
def test_duplicate_columns_self_merge(self):
md = Metadata(pd.DataFrame(
{'a': [1, 2], 'b': [3, 4]},
index=pd.Index(['id1', 'id2'], name='id')))
with self.assertRaisesRegex(ValueError, "columns overlap: 'a', 'b'"):
md.merge(md)
def test_duplicate_columns_self_merge(self):
md = Metadata(pd.DataFrame(
{'a': [1, 2], 'b': [3, 4]},
index=pd.Index(['id1', 'id2'], name='id')))
with self.assertRaisesRegex(ValueError, "columns overlap: 'a', 'b'"):
md.merge(md)
def test_merging_nothing(self):
md = Metadata(pd.DataFrame(
{'a': [1, 2, 3], 'b': [4, 5, 6]},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
with self.assertRaisesRegex(ValueError,
'At least one Metadata.*nothing to merge'):
md.merge()
def test_merging_nothing(self):
md = Metadata(pd.DataFrame(
{'a': [1, 2, 3], 'b': [4, 5, 6]},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
with self.assertRaisesRegex(ValueError,
'At least one Metadata.*nothing to merge'):
md.merge()
def test_duplicate_columns(self):
md1 = Metadata(pd.DataFrame(
{'a': [1, 2], 'b': [3, 4]},
index=pd.Index(['id1', 'id2'], name='id')))
md2 = Metadata(pd.DataFrame(
{'c': [5, 6], 'b': [7, 8]},
index=pd.Index(['id1', 'id2'], name='id')))
with self.assertRaisesRegex(ValueError, "columns overlap: 'b'"):
md1.merge(md2)
def test_disjoint_indices(self):
md1 = Metadata(pd.DataFrame(
{'a': [1, 2, 3], 'b': [4, 5, 6]},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
md2 = Metadata(pd.DataFrame(
{'c': [7, 8, 9], 'd': [10, 11, 12]},
index=pd.Index(['X', 'Y', 'Z'], name='id')))
with self.assertRaisesRegex(ValueError, 'no IDs shared'):
md1.merge(md2)
def test_disjoint_indices(self):
md1 = Metadata(pd.DataFrame(
{'a': [1, 2, 3], 'b': [4, 5, 6]},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
md2 = Metadata(pd.DataFrame(
{'c': [7, 8, 9], 'd': [10, 11, 12]},
index=pd.Index(['X', 'Y', 'Z'], name='id')))
with self.assertRaisesRegex(ValueError, 'no IDs shared'):
md1.merge(md2)
def test_duplicate_columns(self):
md1 = Metadata(pd.DataFrame(
{'a': [1, 2], 'b': [3, 4]},
index=pd.Index(['id1', 'id2'], name='id')))
md2 = Metadata(pd.DataFrame(
{'c': [5, 6], 'b': [7, 8]},
index=pd.Index(['id1', 'id2'], name='id')))
with self.assertRaisesRegex(ValueError, "columns overlap: 'b'"):
md1.merge(md2)
def test_merging_unaligned_indices(self):
md1 = Metadata(
pd.DataFrame({
'a': [1, 2, 3],
'b': [4, 5, 6]
},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
md2 = Metadata(
pd.DataFrame({
'c': [9, 8, 7],
'd': [12, 11, 10]
},
index=pd.Index(['id3', 'id2', 'id1'], name='id')))
md3 = Metadata(
pd.DataFrame({
'e': [13, 15, 14],
'f': [16, 18, 17]
},
index=pd.Index(['id1', 'id3', 'id2'], name='id')))
obs = md1.merge(md2, md3)
exp = Metadata(
pd.DataFrame(
{
'a': [1, 2, 3],
'b': [4, 5, 6],
'c': [7, 8, 9],
'd': [10, 11, 12],
'e': [13, 14, 15],
'f': [16, 17, 18]
},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
self.assertEqual(obs, exp)
def test_merging_two(self):
md1 = Metadata(
pd.DataFrame({
'a': [1, 2, 3],
'b': [4, 5, 6]
},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
md2 = Metadata(
pd.DataFrame({
'c': [7, 8, 9],
'd': [10, 11, 12]
},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
obs = md1.merge(md2)
exp = Metadata(
pd.DataFrame(
{
'a': [1, 2, 3],
'b': [4, 5, 6],
'c': [7, 8, 9],
'd': [10, 11, 12]
},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
self.assertEqual(obs, exp)
def test_no_artifacts(self):
md1 = Metadata(pd.DataFrame(
{'a': [1, 2]}, index=pd.Index(['id1', 'id2'], name='id')))
md2 = Metadata(pd.DataFrame(
{'b': [3, 4]}, index=pd.Index(['id1', 'id2'], name='id')))
metadata = md1.merge(md2)
self.assertEqual(metadata.artifacts, ())
def test_no_artifacts(self):
md1 = Metadata(pd.DataFrame(
{'a': [1, 2]}, index=pd.Index(['id1', 'id2'], name='id')))
md2 = Metadata(pd.DataFrame(
{'b': [3, 4]}, index=pd.Index(['id1', 'id2'], name='id')))
metadata = md1.merge(md2)
self.assertEqual(metadata.artifacts, ())
def test_merging_one(self):
md = Metadata(
pd.DataFrame({
'a': [1, 2, 3],
'b': [4, 5, 6]
},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
obs = md.merge()
self.assertIsNot(obs, md)
self.assertEqual(obs, md)
def test_id_column_only(self):
md1 = Metadata(
pd.DataFrame({}, index=pd.Index(['id1', 'id2', 'id3'], name='id')))
md2 = Metadata(
pd.DataFrame({}, index=pd.Index(['id2', 'X', 'id1'], name='id')))
md3 = Metadata(
pd.DataFrame({}, index=pd.Index(['id1', 'id3', 'id2'], name='id')))
obs = md1.merge(md2, md3)
exp = Metadata(
pd.DataFrame({}, index=pd.Index(['id1', 'id2'], name='id')))
self.assertEqual(obs, exp)
def test_id_column_only(self):
md1 = Metadata(pd.DataFrame({},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
md2 = Metadata(pd.DataFrame({},
index=pd.Index(['id2', 'X', 'id1'], name='id')))
md3 = Metadata(pd.DataFrame({},
index=pd.Index(['id1', 'id3', 'id2'], name='id')))
obs = md1.merge(md2, md3)
exp = Metadata(
pd.DataFrame({}, index=pd.Index(['id1', 'id2'], name='id')))
self.assertEqual(obs, exp)
def test_merged_id_column_name(self):
md1 = Metadata(pd.DataFrame(
{'a': [1, 2]},
index=pd.Index(['id1', 'id2'], name='sample ID')))
md2 = Metadata(pd.DataFrame(
{'b': [3, 4]},
index=pd.Index(['id1', 'id2'], name='feature ID')))
obs = md1.merge(md2)
exp = Metadata(pd.DataFrame(
{'a': [1, 2], 'b': [3, 4]},
index=pd.Index(['id1', 'id2'], name='id')))
self.assertEqual(obs, exp)
def test_merged_id_column_name(self):
md1 = Metadata(pd.DataFrame(
{'a': [1, 2]},
index=pd.Index(['id1', 'id2'], name='sample ID')))
md2 = Metadata(pd.DataFrame(
{'b': [3, 4]},
index=pd.Index(['id1', 'id2'], name='feature ID')))
obs = md1.merge(md2)
exp = Metadata(pd.DataFrame(
{'a': [1, 2], 'b': [3, 4]},
index=pd.Index(['id1', 'id2'], name='id')))
self.assertEqual(obs, exp)
def test_merging_two(self):
md1 = Metadata(pd.DataFrame(
{'a': [1, 2, 3], 'b': [4, 5, 6]},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
md2 = Metadata(pd.DataFrame(
{'c': [7, 8, 9], 'd': [10, 11, 12]},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
obs = md1.merge(md2)
exp = Metadata(pd.DataFrame(
{'a': [1, 2, 3], 'b': [4, 5, 6],
'c': [7, 8, 9], 'd': [10, 11, 12]},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
self.assertEqual(obs, exp)
def test_merging_unaligned_indices(self):
md1 = Metadata(pd.DataFrame(
{'a': [1, 2, 3], 'b': [4, 5, 6]},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
md2 = Metadata(pd.DataFrame(
{'c': [9, 8, 7], 'd': [12, 11, 10]},
index=pd.Index(['id3', 'id2', 'id1'], name='id')))
md3 = Metadata(pd.DataFrame(
{'e': [13, 15, 14], 'f': [16, 18, 17]},
index=pd.Index(['id1', 'id3', 'id2'], name='id')))
obs = md1.merge(md2, md3)
exp = Metadata(pd.DataFrame(
{'a': [1, 2, 3], 'b': [4, 5, 6],
'c': [7, 8, 9], 'd': [10, 11, 12],
'e': [13, 14, 15], 'f': [16, 17, 18]},
index=pd.Index(['id1', 'id2', 'id3'], name='id')))
self.assertEqual(obs, exp)
