test_raw.csv was given for those who want to do their own preprocessing of the raw data or want to better understand the data with punctuations. If you decide to use test_raw.csv though, you must remove all punctuations, extra white spaces and new lines.
We are to test against test.csv
test_raw.csv was given for those who want to do their own preprocessing of the raw data or want to better understand the data with punctuations. If you decide to use test_raw.csv though, you must remove all punctuations, extra white spaces and new lines.
This is per my understanding, I stand corrected.
thanks, just to clarify then, in the submission file,the 'Clinician' field should have all punctuations and new lines removed right?
Yes exactly, just have single white spaces separating the words