BookmarkSubscribeRSS Feed
sebastiangonzal
Calcite | Level 5

I have a transactional data set which I processed in enterprise guide with the task create time series in order to have the time series as is needed for forecast server, regarding the time ID variable, it came in format DDMMMYYYY and that is how it is exported after the workflow, I assign Day interval with the default settings. The format of the date variable of the table I will use in Forecast is as follows:

 

Format DATE9.

 

Reading format DDMMYY10.

 

But when I identify it in the forecast TimeID it says that there are few recordings of the variable and cant read it.

 

How can I make it read it?

 

Thanks

4 REPLIES 4
Reeza
Super User
Post the actual error you're receiving please. You can also contact SAS tech support directly.
rajib_nath
SAS Employee

Is possible to share or describe the data?

 

How many variables?

Number of missing and non-missing count etc.?

 

From the information given it is difficult to guess.

sebastiangonzal
Calcite | Level 5

I made a couple of samples with different forms of data and it turns out that the date should be:

 

1. The first column in the data set

2. It must not have date gaps

3. The complete date series must by unique in date (all values and breakdows must be aggregated by date before loading to forecast)

 

If I am mistaken feel free to correct me, but so far I think this was the problem

 

Thanks anyways 🙂

 

Reeza
Super User
I'm not sure about Number 1, but the rest sounds correct.

sas-innovate-2024.png

Available on demand!

Missed SAS Innovate Las Vegas? Watch all the action for free! View the keynotes, general sessions and 22 breakouts on demand.

 

Register now!

Multiple Linear Regression in SAS

Learn how to run multiple linear regression models with and without interactions, presented by SAS user Alex Chaplin.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 4 replies
  • 910 views
  • 0 likes
  • 3 in conversation