RecSys_ALS_items.py

def recommend(customer_id, sparse_customer_item, customer_vecs, item_vecs, num_items=10):
    
    customer_interactions = sparse_customer_item[customer_id,:].toarray()
    customer_interactions = customer_interactions.reshape(-1) + 1
    customer_interactions[customer_interactions > 1] = 0
    
    rec_vector = customer_vecs[customer_id,:].dot(item_vecs.T).toarray()
    
    min_max = MinMaxScaler()
    rec_vector_scaled = min_max.fit_transform(rec_vector.reshape(-1,1))[:,0]
    recommend_vector = customer_interactions * rec_vector_scaled

    item_idx = np.argsort(recommend_vector)[::-1][:num_items]
    
    descriptions = []
    scores = []

    for idx in item_idx:
        descriptions.append(grouped_df.Description.loc[grouped_df.item_id == idx].iloc[0])
        scores.append(recommend_vector[idx])

    recommendations = pd.DataFrame({'description': descriptions, 'score': scores})

    return recommendations
    
customer_vecs = sparse.csr_matrix(model.user_factors)
item_vecs = sparse.csr_matrix(model.item_factors)
# Create recommendations for customer with id 2
customer_id = 2
recommendations = recommend(customer_id, sparse_customer_item, customer_vecs, item_vecs)

print(recommendations)

Hello Susan, I'm writing my bachelor thesis in recommender systems for e-commerce. I have had some issues trying to run this code on my dataframe. Is there a way to contact you and ask for some help to understand it better please? :) I'd really appreciate that