Python Artificial Intelligence Projects for Beginners by Joshua Eckroth

Author:Joshua Eckroth
Language: eng
Format: epub, pdf
Publisher: Packt Publishing
Published: 2018-07-31T08:11:17+00:00

So, in each case, in each file, we simply make a TaggedDocument object with the words from that document or that review plus a tag, which is simply the filename. This is important so that it learns that all these words go together in the same document, and that these words are somehow related to each other. After loading, we have 175,000 training examples from different documents:

Now let's have a look at the first 10 sentences in the following screenshot:

We shuffle these documents and then feed them into our Doc2Vec trainer, using Doc2Vec(permuter, dm=0, hs=1, size=50), where we finally do the training of the Doc2Vec model and where it learns the document vectors for all the different documents. dm=0 and hs=1 are just parameters to say how to do the training. These are just things that I found were the most accurate. dm=0 is where we are using the model that was shown in the last section, which means it receives a filename and it predicts the words:

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.