I'm relatively new to data science, and I decided to stretch a bit and try a project with time series data. I downloaded the Human Activity Recognition from Continuous Ambient Sensor Data Data Set, and read the first file into a Pandas dataframe.

That dataset contains relative time data:

   lastSensorEventHours  lastSensorEventSeconds  lastSensorDayOfWeek
0                  10.0                 38464.0                  4.0
1                  10.0                 38465.0                  4.0
2                  10.0                 38578.0                  4.0
3                  10.0                 38582.0                  4.0
4                  10.0                 38582.0                  4.0

I've done some work with absolute time series--for example, analyzing stock data, using the time/date data as the index. With this, I'm not even sure where to start. I'm thinking to group into last sensor event length of time, but I don't know how that could be valuable.

Can anyone recommend some methods for how to tackle this data as a time series problem?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.