the-deep-learners/deep-learning-illustrated

natural_language_preprocessing.ipynb uses older attributes with gensim library for training word2vec

Closed this issue · 1 comments

tmmsagheer commented

  1. In section Run Word2Vec of notebook natural_language_preprocessing.ipynb
    model = Word2Vec(sentences=clean_sents, size=64, sg=1, window=10, iter=5, min_count=10, workers=4)
    is given, instead it should be
    model = Word2Vec(sentences=clean_sents, vector_size=64, sg=1, window=10, epochs=5, min_count=10, workers=4)

  2. model.wv.vocab should be replaced with model.wv.vectors

  3. model.wv.vocab.keys should be replaced with model.wv.index_to_key
    I believe the author used Gensim 3.x and the latest Gensim is 4.x

jonkrohn commented

Hi @tmmsagheer — thank you for your contribution, but I'm afraid this not a bug. This is deliberate.

I cannot change the code or library version in a physical, printed book, so we had to freeze the library versions in time. As specified in the Dockerfile for this repository by gensim==3.4.0, we have fixed the Gensim library at 3.4.0 in the book and in this repo indefinitely.

  • 👍1