def test_simple_expression(self):
df = pd.DataFrame({'Subject': ['subject-1', 'subject-1', 'subject-2'],
'SampleType': ['gut', 'tongue', 'gut']},
index=pd.Index(['S1', 'S2', 'S3'], name='id'))
metadata = Metadata(df)
where = "Subject='subject-1'"
actual = metadata.get_ids(where)
expected = {'S1', 'S2'}
self.assertEqual(actual, expected)
where = "Subject='subject-2'"
actual = metadata.get_ids(where)
expected = {'S3'}
self.assertEqual(actual, expected)
where = "Subject='subject-3'"
actual = metadata.get_ids(where)
expected = set()
self.assertEqual(actual, expected)
where = "SampleType='gut'"
actual = metadata.get_ids(where)
expected = {'S1', 'S3'}
self.assertEqual(actual, expected)
where = "SampleType='tongue'"
actual = metadata.get_ids(where)
expected = {'S2'}
self.assertEqual(actual, expected)
def test_simple_expression(self):
df = pd.DataFrame(
{
'Subject': ['subject-1', 'subject-1', 'subject-2'],
'SampleType': ['gut', 'tongue', 'gut']
},
index=pd.Index(['S1', 'S2', 'S3'], name='id'))
metadata = Metadata(df)
where = "Subject='subject-1'"
actual = metadata.get_ids(where)
expected = {'S1', 'S2'}
self.assertEqual(actual, expected)
where = "Subject='subject-2'"
actual = metadata.get_ids(where)
expected = {'S3'}
self.assertEqual(actual, expected)
where = "Subject='subject-3'"
actual = metadata.get_ids(where)
expected = set()
self.assertEqual(actual, expected)
where = "SampleType='gut'"
actual = metadata.get_ids(where)
expected = {'S1', 'S3'}
self.assertEqual(actual, expected)
where = "SampleType='tongue'"
actual = metadata.get_ids(where)
expected = {'S2'}
self.assertEqual(actual, expected)
def test_invalid_where(self):
df = pd.DataFrame({'Subject': ['subject-1', 'subject-1', 'subject-2'],
'SampleType': ['gut', 'tongue', 'gut']},
index=pd.Index(['S1', 'S2', 'S3'], name='sampleid'))
metadata = Metadata(df)
where = "not-a-column-name='subject-1'"
with self.assertRaises(ValueError):
metadata.get_ids(where)
def test_invalid_where(self):
df = pd.DataFrame({'Subject': ['subject-1', 'subject-1', 'subject-2'],
'SampleType': ['gut', 'tongue', 'gut']},
index=pd.Index(['S1', 'S2', 'S3'], name='sampleid'))
metadata = Metadata(df)
where = "not-a-column-name='subject-1'"
with self.assertRaises(ValueError):
metadata.get_ids(where)
def test_query_by_id(self):
df = pd.DataFrame({'Subject': ['subject-1', 'subject-1', 'subject-2'],
'SampleType': ['gut', 'tongue', 'gut']},
index=pd.Index(['S1', 'S2', 'S3'], name='id'))
metadata = Metadata(df)
actual = metadata.get_ids(where="id='S2' OR id='S1'")
expected = {'S1', 'S2'}
self.assertEqual(actual, expected)
def test_query_by_id(self):
df = pd.DataFrame({'Subject': ['subject-1', 'subject-1', 'subject-2'],
'SampleType': ['gut', 'tongue', 'gut']},
index=pd.Index(['S1', 'S2', 'S3'], name='id'))
metadata = Metadata(df)
actual = metadata.get_ids(where="id='S2' OR id='S1'")
expected = {'S1', 'S2'}
self.assertEqual(actual, expected)