Reproduction of the 20 Newsgroup experiments

[wxy929]

Hi,

I'm trying to reproducing the 20 Newsgroup experiments following the "Newsgroup.ipynb". And it seems that there is an undefined "Y_cleaned" variable in the fourth cell.

Updates: I found the code following to generate the Y_cleaned, sorry for the inconvenience. And I also tried to add

import nltk
nltk.download('stopwords')

in the fifth cell to define the "stopwords", and finally got the same dimension of mat2data(data_cleaned_new).

Thank you very much!