warchildmd/game2vec

TensorFlow implementation of word2vec applied on https://www.kaggle.com/tamber/steam-video-games dataset, using both CBOW and Skip-gram.

game2vec's Issues

Why use word2vec

I don't understand why you would use word2vec. I think what you want is to learn association rules. Association rules would answer a question like "given someone has played/purchased game x what other games have they played/purchased?" Word2vec is going to be sensitive to the order the games are presented in the data, which is probably not want you want here (seeing as the dataset has no information about what order the games were played/purchased in).

Association rules would not care about order, and would be able to consider the full set of games someone has played/purchased, rather than just the plays/purchases near the game in the possibly arbitrarily ordered data.

Also, if you're training word vectors with a dataset this small, you might want to use gensim--using tensorflow here is like bringing a nuclear missle to a knife fight.

Although maybe I've missed something--why didn't you use association rules? Why use word vectors when you have a set where order doesn't matter, especially with a dataset this small, where you certainly can't expect any problem scaling association rules. Why not use gensim?

random_multinomial_choice() function seems not right

I am confused about the random_multinomial_choice() function in your train_cbow_weighted.py file.
The condition of if sentence seems not right.. More likely, if y>=x: should be here.
In my opinion, if the play time of a game is quite bigger, this game should be return.
Am I right?
Waiting for your reply.

And here is your code.

def random_multinomial_choice(tuples):
    x = random.random()
    total = sum([hours for _, hours in tuples])
    for game, hours in tuples:
        y = hours / total
        if y <= x:
            return game
        x -= y
    return tuples[-1][0]