2. API References

2.1. recsys.ctr

ObiCTR

Online Bayesian Inference algorithm for Collaborative Topic Regression model (obi-CTR)

2.2. recsys.utils

cy_calc_multinomial_pvals	Calculate event probabilities of the conditional distribution of one variable $z_{jn}$ given others.
cy_calc_new_user_mean	Calculate new user mean vector $\mathbf{m}_{ui}^{*}$.
cy_calc_new_user_cov	Calculate new diagonals of the user covariance matrix $\Sigma_{ui}^{*}$.
cy_calc_new_item_mean	Calculate new item mean vector $\mathbf{m}_{vj}^{*}$.
cy_calc_new_item_cov	Calculate new diagonals of the item covariance matrix $\Sigma_{vj}^{*}$.
cy_update_topic_word_mat	Calculate new variational parameters of each “topic” dirichlet distribution $\{\Delta_k^{\star}\}_{k=1}^K$ in place.
cvt_to_word_ids	Convert sparse word count vector to word ids.
split_rating_mat	Split the rating matrix into two rating matrix with the same shape but difference number of ratings.