most_similar.R

cosine_similarity <- function(a,b){
    # assuming unit vectors
    # the cosine is just the dot-product
    a %*% b
}


most_similar <- function(embeddings, ref_item, n_top = 10){
    # calculate cos similarity to ref_item for all elements
    cos_sims <- eapply(embeddings, cosine_similarity, b = ref_item)
    
    # only look at cos values smaller than 1
    # this will ignore the same element
    cos_sims <- cos_sims[cos_sims < 1]
    
    # return top elements
    cos_sims[order(unlist(cos_sims),decreasing=TRUE)][1:n_top]
}