Could we ask for a short explanation of the columns included in the dataset? Just for curiosity, for example, I would like to ask what the following attributes mean:
* main_working_id, total_bumps_energy, total_tremors_energy, ..., latest_maximum_meter (first 13 columns)
* count_e2, count_e3, ..., sum_e2, ..., sum_e6plus, ...
* max_gactivity, max_genergy, avg_difference_in_genergy, ...
Perhaps knowing what these variables stand for won't help much as the data should speak for itself. Nevertheless it would be interesting to know.
Also, if possible, could you please clarify "working_site_metadata.csv" file? So that we have an idea how to possibly use this information too.
we added a file with explanation of column names to the Data files folder.
I hope that it helps!
Thanks for this question :-)
In all cases x.24 corresponds to the latest reading, i.e. the reading just before the start of the forecasting period.
I would have an additional question: what is the chronology of hourly time series? Say, we have a series x.1, x.2, ..., x.24. I want to know whether x.1 or x.24 is the most recent recording. I couldn't infer this information from the description.