0
$\begingroup$

I'm using Microsoft Azure automl to try and generate models for time series forecasting but I keep getting an error:

Error: Could not determine the data set time frequency. All series in the data set have one row and no freq parameter was provided. Please provide the freq (forecast frequency) parameter or review the time_series_id_column_names setting to decrease the number of time series.

My data set looks like:

          Date,       Temp,
1,2019-05-07 13:51:00,25.19,
2,2019-05-07 13:51:58,25.14,
3,2019-05-07 13:53:00,25.14,
4,2019-05-07 13:54:00,25.14,
5,2019-05-07 13:55:00,25.1,
6,2019-05-07 13:55:58,25.1,
7,2019-05-07 13:57:00,25.1,
8,2019-05-07 13:57:58,25.11,
9,2019-05-07 13:58:58,25.11,
10,2019-05-07 14:00:00,25.07,
11,2019-05-07 14:01:00,25.07,
12,2019-05-07 14:02:00,23.11,

I followed the steps on the ml.azure.com gui, I don't see a place for freq or time_series_id_column_names

Seems to be an issue with the data set, any ideas on how I can prevent/fix this error would be great, thanks!

$\endgroup$
1
$\begingroup$

The data either has duplicates or you may have some rows with empty values. I removed my rows at the bottom that had empty values separated by comma which resolved the issue

$\endgroup$
1
  • $\begingroup$ Thanks so much! $\endgroup$ – YJay Jan 7 at 18:27

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.