I am wondering if parish values are always st. philip ie. the area the data was collected from. If not, how do we identify the parish value from the image(It is hard to do this as Train.csv only has st. philip)
what if the image has no st. philip in the address and so the model is not sure what the parish is because the train data only has st philip as the parish
'/%3e%3c/svg%3e)
With Current data that would be the assumption, but you have to make sure all your values are predictions from the model.
what if the image has no st. philip in the address and so the model is not sure what the parish is because the train data only has st philip as the parish
I have seen and instance of St. Olivia, if your model can generelize better then that would be the prediction, if not seen it can be empty
interesting. measured the impact of empty predictions on LB?