gmmm_calc.py

# First cluster the item data and return the model
items_model, items_labels, items_cluster_centers = cluster_gmm(exp_model.wv.vectors, k=8)

# [user_means] is a list of vectors, each represents the mean of the item vectors each user has listened to

# then use the model to create a new user vector to each user 
#based on their probability of being part of each item cluster

# this is the empty array
ar_users_clusters = np.zeros((len(user_means), items_cluster_centers.shape[0]))
# for each user mean, we need to estimate its probability of being part of each item cluster or distribution
# recall that user mean is a mean of item vectors so they share the same space
for ix, user_key in enumerate(user_means):
    user_mean = user_means[user_key]
    # predict_proba will give us an array whereas each element represents 
    #the probability of the user vector being part of the cluster
    ar_users_clusters[ix] = items_model.predict_proba([user_mean])