Forecast on non-datetime temporal indicator

[qui8t]

Description

I'm using the following to forecast using nixtla client:

nixtla_client.forecast(df=df, h=10, time_col=[See the following], target_col="Measurement")

My use-case involves two temporal series:

• A time series with measurement at irregular intervals. The above method gives the following error:

  RuntimeError: Could not infer the frequency of the time column. This could be due to inconsistent intervals. Please check your data for missing, duplicated or irregular timestamps

• A sequence of measurement not timestamped, with the precedence of measurement defined using an integer. Similarly, the above method throws the following error:

  AttributeError: Can only use .dt accessor with datetimelike values

Link

No response

[elephaint]

Hi, that's unfortunate.

Did you try the irregular timestamps tutorial?