In twenty_newsgroups/data, I can't run preprocess.py since a file is missing. It's stuck at the following code block:
# Fill in the pretrained word vectors
n_dim = 300
fn_wordvc = 'GoogleNews-vectors-negative300.bin'
vectors, s, f = corpus.compact_word_vectors(vocab, filename=fn_wordvc)
In
twenty_newsgroups/data
, I can't runpreprocess.py
since a file is missing. It's stuck at the following code block: