ensure build_vocab and train get same corpus

MediaUncovered / NewsAnalysis

use word embeddings to uncover bias in newspapers

5 stars 1 forks source link

ensure build_vocab and train get same corpus #15

Closed Tilana closed 6 years ago

Tilana commented 7 years ago

Are always the same documents in an iterator objects when using fetchmany() and postgresql database. Ensure that the same corpus is used for building the vocabulary and for training the word2vec model.