a-agmon · March 29, 2021 13:57
diff --git a/w2v.py b/w2v.py
 # text_parts is a dictionary in which each key is a userID and the corresponding values are the items the user engaged with
 # vector_size  is the size of the embedding vector or the latent factors dimension
 # window should be set to the max # of items of the user with the greatest # of items
 model = Word2Vec(text_parts.values(), min_count=3, vector_size=20, window=36, sg=1, ns_exponent=-0.5)
	# text_parts is a dictionary in which each key is a userID and the corresponding values are the items the user engaged with
	# vector_size is the size of the embedding vector or the latent factors dimension
	# window should be set to the max # of items of the user with the greatest # of items
	model = Word2Vec(text_parts.values(), min_count=3, vector_size=20, window=36, sg=1, ns_exponent=-0.5)