def test_features_df_serialization():
superpixels = generate_random_voronoi((100,200), 200)
rag = Rag( superpixels )
# For simplicity, just make values identical to superpixels
values = superpixels.astype(np.float32)
feature_names = ['standard_edge_mean', 'standard_edge_minimum', 'standard_edge_maximum']
features_df = rag.compute_features(values, feature_names)
tmpdir = tempfile.mkdtemp()
try:
with h5py.File( tmpdir + '/' + 'test_dataframe.h5', 'w' ) as f:
group = f.create_group('test_dataframe')
dataframe_to_hdf5( group, features_df )
with h5py.File( tmpdir + '/' + 'test_dataframe.h5', 'r' ) as f:
group = f['test_dataframe']
readback_features_df = dataframe_from_hdf5( group )
assert (readback_features_df.columns.values == features_df.columns.values).all()
assert (readback_features_df.values.shape == features_df.values.shape)
assert (readback_features_df.values == features_df.values).all()
finally:
shutil.rmtree(tmpdir)
def _serialize(self, group, name, slot):
if slot.level == 0:
# Is the cache up-to-date?
# if not, we'll just return (don't recompute the classifier just to save it)
slot_index = slot.operator.index(slot)
inner_op = self.cache.getLane(slot_index)
if inner_op._dirty:
return
dataframe = inner_op.Output.value
# Can be None if the user didn't actually compute features yet.
if dataframe is None:
return
df_group = group.create_group(name)
dataframe_to_hdf5(df_group, dataframe)
else:
subgroup = group.create_group(name)
for i, subslot in enumerate(slot):
subname = self.subname.format(i)
self._serialize(subgroup, subname, slot[i])
def _serialize(self, group, name, slot):
if slot.level == 0:
# Is the cache up-to-date?
# if not, we'll just return (don't recompute the classifier just to save it)
slot_index = slot.operator.index(slot)
inner_op = self.cache.getLane( slot_index )
if inner_op._dirty:
return
dataframe = inner_op.Output.value
# Can be None if the user didn't actually compute features yet.
if dataframe is None:
return
df_group = group.create_group( name )
dataframe_to_hdf5( df_group, dataframe )
else:
subgroup = group.create_group(name)
for i, subslot in enumerate(slot):
subname = self.subname.format(i)
self._serialize(subgroup, subname, slot[i])