Data utils

Utility classes related to data handling.


Data sequencer class to process data matrix into sequences (images). Sequences can overlap. Sequencing grid can be altered between calls.

DataSequencer(\*args, \*\*kwargs) Data sequencer
DataSequencer.process(data) Process
DataSequencer.increase_shifting([shift_step]) Increase temporal shifting


Data processor class to process raw features into data suitable for machine learning algorithms. Feature processing chain and data processing chain are defined during the class construction, and these processing chains are applied to the input data.

DataProcessor(\*args, \*\*kwargs) Data processors with feature and data processing chains
DataProcessor.load(feature_filename_dict[, ...]) Load feature item
DataProcessor.process(feature_data[, ...]) Process feature data
DataProcessor.process_features(feature_data) Process feature data
DataProcessor.process_activity_data(...) Process activity data
DataProcessor.process_data(data[, metadata]) Process data
DataProcessor.call_method(method_name[, ...]) Call class method in the processing chain items


Data buffering class, which can be used to store data and meta data associated to the item. Item data is accessed through item key. When internal buffer is filled, oldest item is replaced.

DataBuffer(\*args, \*\*kwargs) Data buffer (FIFO)
DataBuffer.count() Buffer usage
DataBuffer.full() Buffer full
DataBuffer.key_exists(key) Check that key exists in the buffer
DataBuffer.set(key[, data, meta]) Insert item to the buffer
DataBuffer.get(key) Get item based on key
DataBuffer.clear() Empty the buffer


Data processing chain class, inherited from list.

ProcessingChain.process(data) Process the data with processing chain
ProcessingChain.call_method(method_name[, ...]) Call class method in the processing chain items