Most of this time has been spent understanding the TIM documentation. While the documentation for TIM is quite extensive, the Python API part of it is sparse, as is the documentation about the configuration settings (see below).
The data needs to be formatted correctly for TIM to deal with it. This is easily done using the Pandas library and it is a correctly formatted Pandas dataframe that has to be sent to the TIM API. However, the error messages that come back are not documented. I have had a meeting with Mike and Francis who have pointed me to the Swagger documentation for the API, but this does not help with error messages.
I have discovered that TIM can handle imputation of missing data but by default only in blocks of six and using either a linear method which is a straight line between the last point before the end of the missing block and the first point at the end of the missing block or using the last available data point and imputing that value into all of the data points that have missing values.
Neither of these seems logical for a tool that deals with Time series data that contains daily trends and seasonality. I need to try and find a better way to negate the effects of the missing data.