You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Describe the bug
If multiple variables are present in an interaction term (i.e. self.treatment = 'variable1:variable2'), each variable needs to be checked to be a type object. This is not currently implemented as it is not known how to return a list of variables from a Patsy formula neatly.
Additional context
First look into if Patsy can return a list of variables somehow, if not manual string splitting and iterating over them.
The text was updated successfully, but these errors were encountered:
I tried to run this with a more complex interaction term driving_score ~ I(completion_score * (1 - outside_route_lanes)) and it doesn't like it because the I basically just puts everything inside it into a block, so patsy doesn't recognise to pull out completion_score and outside_route_lanes as terms. It just has I(completion_score * (1 - outside_route_lanes)).
Describe the bug
If multiple variables are present in an interaction term (i.e. self.treatment = 'variable1:variable2'), each variable needs to be checked to be a type object. This is not currently implemented as it is not known how to return a list of variables from a Patsy formula neatly.
Additional context
First look into if Patsy can return a list of variables somehow, if not manual string splitting and iterating over them.
The text was updated successfully, but these errors were encountered: