I am preparing time series data for to build an RNN model (LSTM). The data is collected from sensors installed in a mechanical plant. Consider I have data for input and output temperature of a compressor along with the time stamps. Like this there is data for around 20 parameters recorded along with their time stamps. Problem is there is differnece in the time stamps at which data is collected. So how do I ideally match the time stamps to create a single dataframe with all the parameters and a single time stamp

  • $\begingroup$ What do you mean by difference in time stamps? Could you please be more specific? Different formats? Irregular time stamps? $\endgroup$ – Danny Feb 12 '19 at 12:05
  • $\begingroup$ The data is collected at 5 mins intervals,consider if at the inlet time stamp is 00:05:20 , the time stamp is 00:05:34. some times if the inlet time stamp is 00:20:54, the time stamp at outlet is 00:21:04. so when i merge inlet and outlet by flooring the time stamp to minutes level, i am loosing some data , because inlet is floored to 00:20:00 and outlet is floored to 00:21:00 $\endgroup$ – cvg Feb 12 '19 at 14:28
  • $\begingroup$ So do you want the difference between the inlet time stamp and the time stamp? $\endgroup$ – Danny Feb 12 '19 at 14:40
  • $\begingroup$ no, i want to convert the time stamps such as 00:21:00,00:36:00 to 00:20:00,00:35:00 respectively $\endgroup$ – cvg Feb 12 '19 at 15:24
  • $\begingroup$ This should help you converting the date times to the nearest minute you want. stackoverflow.com/questions/3463930/… $\endgroup$ – Danny Feb 12 '19 at 16:09

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.