Azure automl time series forecasting error
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!
Topic automl forecasting azure-ml time-series dataset
Category Data Science