def test_data_table(self):
DataEntry = create_data_entry(['foo', 'bar'])
entry1 = DataEntry(foo='baz', bar='qux')
entry2 = DataEntry(foo='quuz', bar='corge')
dt = DataTable(data=[entry1, entry2], columns=['foo', 'bar'])
obs_dict = dt.to_dict()
exp_dict = {
'data': [{
'foo': 'baz',
'bar': 'qux'
}, {
'foo': 'quuz',
'bar': 'corge'
}],
'columns': ['foo', 'bar'],
}
obs = json.dumps(obs_dict)
exp = json.dumps(exp_dict)
self.assertEqual(obs, exp)
def test_presence_data_table(self):
taxonomy = Taxonomy(self.table, self.taxonomy_greengenes_df,
self.table_vars)
obs = taxonomy.presence_data_table(['sample-1', 'sample-2'])
exp_columns = [
'sampleId', 'Kingdom', 'Phylum', 'Class', 'Order', 'Family',
'Genus', 'Species', 'relativeAbundance'
]
DataEntry = create_data_entry(exp_columns)
exp = DataTable(
data=[
DataEntry(
**{
'sampleId': 'sample-1',
'Kingdom': 'a',
'Phylum': 'b',
'Class': None,
'Order': 'c',
'Family': 'd',
'Genus': 'e',
'Species': None,
'relativeAbundance': 2. / 5,
}),
DataEntry(
**{
'sampleId': 'sample-1',
'Kingdom': 'a',
'Phylum': 'f',
'Class': None,
'Order': 'g',
'Family': 'h',
'Genus': None,
'Species': None,
'relativeAbundance': 3. / 5,
}),
DataEntry(
**{
'sampleId': 'sample-2',
'Kingdom': 'a',
'Phylum': 'b',
'Class': None,
'Order': 'c',
'Family': None,
'Genus': None,
'Species': None,
'relativeAbundance': 1. / 5,
}),
DataEntry(
**{
'sampleId': 'sample-2',
'Kingdom': 'a',
'Phylum': 'b',
'Class': None,
'Order': 'c',
'Family': 'd',
'Genus': 'e',
'Species': None,
'relativeAbundance': 4. / 5,
}),
],
columns=exp_columns,
)
self.assertListEqual([{
'data': col
} for col in exp.columns], obs.columns)
# wouldn't want to do this on a huge dataframe..., but it checks if
# there is a row of obs corresponding to each row of exp...
exp_df = pd.DataFrame(exp.data)
obs_df = pd.DataFrame(obs.data)
obs_df_copy = obs_df.copy()
for e_idx, row_exp in exp_df.iterrows():
for o_idx, row_obs in obs_df.iterrows():
if row_exp.eq(row_obs).all():
obs_df_copy.drop(index=o_idx, inplace=True)
break
self.assertTrue(obs_df_copy.empty)
def test_group_data_table(self):
response = self.client.post(
'/api/taxonomy/present/group/'
'table2-greengenes',
content_type='application/json',
data=json.dumps({'sample_ids': ['sample-1', 'sample-2']}))
self.assertEqual(response.status_code, 200)
obs = json.loads(response.data)
exp_columns = [
'sampleId', 'Kingdom', 'Phylum', 'Class', 'Order', 'Family',
'Genus', 'Species', 'relativeAbundance'
]
DataEntry = create_data_entry(exp_columns)
exp = DataTable(
data=[
DataEntry(
**{
'sampleId': 'sample-1',
'Kingdom': 'a',
'Phylum': 'b',
'Class': None,
'Order': 'c',
'Family': 'd',
'Genus': 'e',
'Species': None,
'relativeAbundance': 2. / 5,
}),
DataEntry(
**{
'sampleId': 'sample-1',
'Kingdom': 'a',
'Phylum': 'f',
'Class': None,
'Order': 'g',
'Family': 'h',
'Genus': None,
'Species': None,
'relativeAbundance': 3. / 5,
}),
DataEntry(
**{
'sampleId': 'sample-2',
'Kingdom': 'a',
'Phylum': 'b',
'Class': None,
'Order': 'c',
'Family': None,
'Genus': None,
'Species': None,
'relativeAbundance': 1. / 5,
}),
DataEntry(
**{
'sampleId': 'sample-2',
'Kingdom': 'a',
'Phylum': 'b',
'Class': None,
'Order': 'c',
'Family': 'd',
'Genus': 'e',
'Species': None,
'relativeAbundance': 4. / 5,
}),
],
columns=[{
'data': col
} for col in exp_columns],
).to_dict()
self.assertListEqual(exp['columns'], obs['columns'])
# wouldn't want to do this on a huge dataframe..., but it checks if
# there is a row of obs corresponding to each row of exp...
exp_df = pd.DataFrame(exp['data'])
obs_df = pd.DataFrame(obs['data'])
obs_df_copy = obs_df.copy()
for e_idx, row_exp in exp_df.iterrows():
for o_idx, row_obs in obs_df.iterrows():
if row_exp.eq(row_obs).all():
obs_df_copy.drop(index=o_idx, inplace=True)
break
self.assertTrue(obs_df_copy.empty)