Create column sleeping and clean data
To do classification we will have to create the new column sleeping.
It can generally be assumed, that all of the current data will have the value of that new column set to False.
The entries where the value is True will have to be generated for every ID.
The idea is to create new data entries for every ID when the usual sleeping time is, for the days we have data entries there, and set the sleeping column to True there. A small overlapp of the True and False entries is within reason.
How many entry points to create and their density is up to the discretion of the people implementing it, if they are unsure consulting the team is recommended.
It should not be forgotten to first clear the data of unnecessary data entries.
Which data to clean and the usual sleeping times for every ID can be found in the presentation /sleeping_times/presentation/AnalyseSleepingtime.pptx as a summary or with a more in depth analysis in Issue #19 (closed)
The implementation should be done in sleeping_times/process/process_data.py and should not change the original csv file, there should be an option to save processed data into a new csv file for future usage.