def test_merge_outlines(metadata, dataframe, out_dir):
metadata.loadSingle(os.path.join(out_dir, 'test.csv'), 'default', int)
outlines = pd.DataFrame(
{
'Metadata_Plate': __rand_array(),
'Metadata_Well': __rand_array(),
'Metadata_Site': __rand_array()
},
dtype=int)
metadata.mergeOutlines(outlines)
merged = pd.merge(metadata.data,
outlines,
on=["Metadata_Plate", "Metadata_Well", "Metadata_Site"])
pd.testing.assert_frame_equal(metadata.data, merged)
def test_filter_records(metadata, dataframe, out_dir):
metadata.loadSingle(os.path.join(out_dir, 'test.csv'), 'default', int)
rule = lambda data: map(lambda row: any(row % 2 == 0), data.values)
metadata.filterRecords(rule)
filtered = dataframe.loc[rule(dataframe), :]
pd.testing.assert_frame_equal(metadata.data, filtered)
def test_load_single(metadata, dataframe, out_dir):
filename = os.path.join(out_dir, 'test.csv')
assert os.path.exists(filename)
metadata.loadSingle(filename, 'default', int)
pd.testing.assert_frame_equal(metadata.data, dataframe)
def test_split_metadata(metadata, dataframe, out_dir):
metadata.loadSingle(os.path.join(out_dir, 'test.csv'), 'default', int)
train_rule = lambda data: data['Metadata_Plate'] < 50
val_rule = lambda data: data['Metadata_Plate'] >= 50
metadata.splitMetadata(train_rule, val_rule)
assert len(metadata.train) + len(metadata.val) == len(metadata.data)