def test_aggregate_skew():
data_target = numpy.array(
[
[0.0, 0.0],
[0.0, 0.0],
[0.0, 0.0],
[0.0, 0.0],
[0.0, 0.0],
[0.0, 0.0],
[0.0, 0.0],
[0.0, 0.0],
[0.0, 0.0],
[0.0, 0.0],
[0.0, 0.0],
]
).T
container = FeatureContainer(
data=data
)
agg = Aggregator(
win_length_frames=2,
hop_length_frames=1,
recipe=['skew']
)
data_aggregated = agg.aggregate(data=container)
numpy.testing.assert_array_equal(data_target, data_aggregated.data)
def test_aggregate_mean():
data_target = numpy.array(
[
[0, 0],
[0.5, 0.5],
[1.5, 1.5],
[2.5, 2.5],
[3.5, 3.5],
[4.5, 4.5],
[5.5, 5.5],
[6.5, 6.5],
[7.5, 7.5],
[8.5, 8.5],
[9.5, 9.5],
]
).T
container = FeatureContainer(
data=data
)
agg = Aggregator(
win_length_frames=2,
hop_length_frames=1,
recipe=['mean']
)
data_aggregated = agg.aggregate(data=container)
numpy.testing.assert_array_equal(data_target, data_aggregated.data)
def test_aggregate_flatten():
data_target = numpy.array(
[
[0, 0, 0, 0],
[0, 0, 1, 1],
[1, 1, 2, 2],
[2, 2, 3, 3],
[3, 3, 4, 4],
[4, 4, 5, 5],
[5, 5, 6, 6],
[6, 6, 7, 7],
[7, 7, 8, 8],
[8, 8, 9, 9],
[9, 9, 10, 10],
]
).T
container = FeatureContainer(
data=data
)
agg = Aggregator(
win_length_frames=2,
hop_length_frames=1,
recipe=['flatten']
)
data_aggregated = agg.aggregate(data=container)
numpy.testing.assert_array_equal(data_target, data_aggregated.data)
def test_save():
data_target = numpy.array(
[
[0, 0, 0, 0],
[0, 0, 1, 1],
[1, 1, 2, 2],
[2, 2, 3, 3],
[3, 3, 4, 4],
[4, 4, 5, 5],
[5, 5, 6, 6],
[6, 6, 7, 7],
[7, 7, 8, 8],
[8, 8, 9, 9],
[9, 9, 10, 10],
]
).T
container = FeatureContainer(
data=data
)
tmp = tempfile.NamedTemporaryFile('r+', suffix='.cpickle', dir=tempfile.gettempdir(), delete=False)
try:
agg = Aggregator(
win_length_frames=2,
hop_length_frames=1,
recipe=['flatten']
).save(filename=tmp.name).load()
data_aggregated = agg.aggregate(data=container)
numpy.testing.assert_array_equal(data_target, data_aggregated.data)
finally:
try:
tmp.close()
os.unlink(tmp.name)
except:
pass
class RepositoryAggregationProcessor(Processor):
"""Data aggregation processor"""
input_type = ProcessingChainItemType.DATA_REPOSITORY #: Input data type
output_type = ProcessingChainItemType.DATA_REPOSITORY #: Output data type
def __init__(self,
win_length_frames=10,
hop_length_frames=1,
recipe=None,
**kwargs):
"""Constructor
Parameters
----------
recipe : list of dict or list of str
Aggregation recipe, supported methods [mean, std, cov, kurtosis, skew, flatten].
win_length_frames : int
Window length in feature frames
hop_length_frames : int
Hop length in feature frames
"""
if recipe is None and kwargs.get('aggregation_recipe',
None) is not None:
recipe = kwargs.get('aggregation_recipe', None)
# Inject initialization parameters back to kwargs
kwargs.update({
'win_length_frames': win_length_frames,
'hop_length_frames': hop_length_frames,
'recipe': recipe
})
# Run super init to call init of mixins too
super(RepositoryAggregationProcessor, self).__init__(**kwargs)
self.aggregator = Aggregator(**self.init_parameters)
def process(self, data=None, store_processing_chain=False, **kwargs):
"""Process
Parameters
----------
data : DataRepository
Data
store_processing_chain : bool
Store processing chain to data container returned
Default value False
Returns
-------
DataMatrix3DContainer
"""
if isinstance(data, RepositoryContainer):
# Label exists in data repository
for label in data:
for stream_id in data[label]:
# Do processing
data.set_container(label=label,
stream_id=stream_id,
container=self.aggregator.aggregate(
data=data.get_container(
label=label,
stream_id=stream_id),
**kwargs))
if store_processing_chain:
# Get processing chain item
processing_chain_item = self.get_processing_chain_item()
# Push chain item into processing chain stored in the container
data.processing_chain.push_processor(**processing_chain_item)
return data
else:
message = '{name}: Wrong input data type, type required [{input_type}].'.format(
name=self.__class__.__name__, input_type=self.input_type)
self.logger.exception(message)
raise ValueError(message)
class AggregationProcessor(Processor):
"""Data aggregation processor"""
input_type = ProcessingChainItemType.DATA_CONTAINER #: Input data type
output_type = ProcessingChainItemType.DATA_CONTAINER #: Output data type
def __init__(self,
win_length_frames=10,
hop_length_frames=1,
recipe=None,
**kwargs):
"""Constructor
Parameters
----------
recipe : list of dict or list of str
Aggregation recipe, supported methods [mean, std, cov, kurtosis, skew, flatten].
win_length_frames : int
Window length in feature frames
hop_length_frames : int
Hop length in feature frames
"""
if recipe is None and kwargs.get('aggregation_recipe',
None) is not None:
recipe = kwargs.get('aggregation_recipe', None)
# Inject initialization parameters back to kwargs
kwargs.update({
'win_length_frames': win_length_frames,
'hop_length_frames': hop_length_frames,
'recipe': recipe
})
# Run super init to call init of mixins too
super(AggregationProcessor, self).__init__(**kwargs)
self.aggregator = Aggregator(**self.init_parameters)
def process(self, data=None, store_processing_chain=False, **kwargs):
"""Process
Parameters
----------
data : DataContainer
Data to be aggregated
store_processing_chain : bool
Store processing chain to data container returned
Default value False
Returns
-------
DataContainer
"""
from dcase_util.containers import ContainerMixin
if isinstance(data, ContainerMixin):
# Do processing
container = self.aggregator.aggregate(data=data, **kwargs)
if store_processing_chain:
# Get processing chain item
processing_chain_item = self.get_processing_chain_item()
# Update current processing parameters into chain item
processing_chain_item.update({'process_parameters': kwargs})
# Push chain item into processing chain stored in the container
container.processing_chain.push_processor(
**processing_chain_item)
return container
else:
message = '{name}: Wrong input data type, type required [{input_type}].'.format(
name=self.__class__.__name__, input_type=self.input_type)
self.logger.exception(message)
raise ValueError(message)
def test_aggregate():
data_target = numpy.array(
[
[0.5, 0.5],
[1.5, 1.5],
[2.5, 2.5],
[3.5, 3.5],
[4.5, 4.5],
[5.5, 5.5],
[6.5, 6.5],
[7.5, 7.5],
[8.5, 8.5],
[9.5, 9.5],
]
).T
container = FeatureContainer(
data=data
)
agg = Aggregator(
win_length_frames=2,
hop_length_frames=1,
recipe=['mean'],
center=False,
padding=False,
)
data_aggregated = agg.aggregate(data=container)
numpy.testing.assert_array_equal(data_target, data_aggregated.data)
data_target = numpy.array(
[
[5.0, 5.0]
]
).T
container = FeatureContainer(
data=data
)
agg = Aggregator(
win_length_frames=11,
hop_length_frames=11,
recipe=['mean'],
center=False,
padding=False,
)
data_aggregated = agg.aggregate(data=container)
numpy.testing.assert_array_equal(data_target, data_aggregated.data)
data_target = numpy.array(
[
[1.5, 1.5],
[5.5, 5.5],
]
).T
container = FeatureContainer(
data=data
)
agg = Aggregator(
win_length_frames=4,
hop_length_frames=4,
recipe=['mean'],
center=False,
padding=False,
)
data_aggregated = agg.aggregate(data=container)
numpy.testing.assert_array_equal(data_target, data_aggregated.data)
data_target = numpy.array(
[
[3.5, 3.5],
[7.5, 7.5],
]
).T
container = FeatureContainer(
data=data
)
agg = Aggregator(
win_length_frames=4,
hop_length_frames=4,
recipe=['mean'],
center=True,
padding=False,
)
data_aggregated = agg.aggregate(data=container)
numpy.testing.assert_array_equal(data_target, data_aggregated.data)
data_target = numpy.array(
[
[0.25, 0.25],
[3.5, 3.5],
[7.5, 7.5],
]
).T
container = FeatureContainer(
data=data
)
agg = Aggregator(
win_length_frames=4,
hop_length_frames=4,
recipe=['mean'],
center=True,
padding=True,
)
data_aggregated = agg.aggregate(data=container)
numpy.testing.assert_array_equal(data_target, data_aggregated.data)