Devicely: A Python package for reading, timeshifting and writing sensor data

A Python package for reading, timeshifting and writing sensor data

Different wearables come with different data formats which require different preprocessing steps. However, it should be easy for scientists to add data from a new wearable to an existing pipeline and easy for developers to add a new wearable to the devicely package. We achieved both by encapsulating data preparation for each wearable behind common methods: reading, deidentifying and writing data.

After reading, the data is accessible through the reader in common formats such as dataframes. Deidentification is achieved by timeshifting the data, either by providing a shifting interval or randomly. For writing back deidentified data we focused on keeping a format that can be read again using the same reader class. In almost all cases, this is the same format as the wearable provides. This enables sharing data with the community while keeping patient anonymity.