I am trying to build an NLP model on this data set where I have data from some accidents where I need to predict the Accident Level. There are a total of 13 duplicate rows. But on looking into them I figure out that they are for different people involved in the same accident. I am not sure if I should drop or keep them.
I am new here. Please consider.
Here is a snapshot of those duplicate rows for the date 01-04-2016 00:00
