Hi, I am using pytorch-forecasting for count time series. I have some date information such as hour of day, day of week, day of month etc…
when I assign these as categorical variables in TimeSeriesDataSet using time_varying_known_categoricals the training.data[‘categoricals’] values seem shuffled and not in the right order as the target. Why is that?
pandas dataframe has the columns below before going through TimeSeriesDataSet
[“_hour_of_day”,“_day_of_week”,“_day_of_month”,“_day_of_year”,“_week_of_year”,“_month_of_year”,“_year” ]
where _hour_of_day incrementally increases from 0 to 23 and cycle repeats. similarly for other columns.
After the following code the _hour_of_day column is no longer 0,1,2,3 but 0, 1, 12, 17. Why does this shuffle happen?
At the moment I tried to use time_varying_known_reals to keep the order correct.
THanks.