Week 14

My task: Doc2Vec model

I am still working on separating the sentences in the Wikipedia training data sets in such a way that creates a .txt document for each article and the sentences pulled from that article, certain and uncertain, and saving them to the same folder so the .txt documents can be used in the doc2vec model. I did think that I would be done by the end of this week; however, this task is much, much harder than I anticipated. I hope to be finished soon. Next week is finals week, so I do not see myself spending much time on the project then.