1. What is the meaning of the last 2 numbers after each attribute? Are they significant? I tried loading my own keywords (just a list format) from other sources and did not seem to work.
the number of documents in which the word occurred (the first number)
the number of documents in which the word occurred for each available class (second and following numbers, here you seem to have only one class)
ad 2) the input and output word lists ensure that the TFIDF calculations are comparable for training and application phase which is important for document classification
ad 3) RM 4.4 will be release tomorrow during the day
ad 1) the numbers in the word list state
- the number of documents in which the word occurred (the first number)
- the number of documents in which the word occurred for each available class (second and following numbers, here you seem to have only one class)
ad 2) the input and output word lists ensure that the TFIDF calculations are comparable for training and application phase which is important for document classificationad 3) RM 4.4 will be release tomorrow during the day
Cheers,
Ingo