I have a time series, which comprises 31 observations per year (actually the observations for March, set in a time series with periodicity 31). My wish is to compact it to the daily average, i.e. end up with 31 observations, each of which represents the average value of that date throughout the available years. I therefore sought to compact it with "dataset compact 31", to which I was told "This conversion is not supported". I then tried other conversions, but it appears no expansion or compaction is accepted at all.

I assume this is due to the unorthodox periodicity, but my question is then: how can I successfully compact my data into 31 average values ?