implicit_feedback_als_5.py

# Let's say we want to recommend artists for user with ID 2023
user_id = 2023

#------------------------------
# GET ITEMS CONSUMED BY USER
#------------------------------

# Let's print out what the user has listened to
consumed_idx = data_sparse[user_id,:].nonzero()[1].astype(str)
consumed_items = item_lookup.loc[item_lookup.artist_id.isin(consumed_idx)]
print consumed_items


#------------------------------
# CREATE USER RECOMMENDATIONS
#------------------------------

def recommend(user_id, data_sparse, user_vecs, item_vecs, item_lookup, num_items=10):
    """Recommend items for a given user given a trained model
    
    Args:
        user_id (int): The id of the user we want to create recommendations for.
        
        data_sparse (csr_matrix): Our original training data.
        
        user_vecs (csr_matrix): The trained user x features vectors
        
        item_vecs (csr_matrix): The trained item x features vectors
        
        item_lookup (pandas.DataFrame): Used to map artist ids to artist names
        
        num_items (int): How many recommendations we want to return:
        
    Returns:
        recommendations (pandas.DataFrame): DataFrame with num_items artist names and scores
    
    """
  
    # Get all interactions by the user
    user_interactions = data_sparse[user_id,:].toarray()

    # We don't want to recommend items the user has consumed. So let's
    # set them all to 0 and the unknowns to 1.
    user_interactions = user_interactions.reshape(-1) + 1 #Reshape to turn into 1D array
    user_interactions[user_interactions > 1] = 0

    # This is where we calculate the recommendation by taking the 
    # dot-product of the user vectors with the item vectors.
    rec_vector = user_vecs[user_id,:].dot(item_vecs.T).toarray()

    # Let's scale our scores between 0 and 1 to make it all easier to interpret.
    min_max = MinMaxScaler()
    rec_vector_scaled = min_max.fit_transform(rec_vector.reshape(-1,1))[:,0]
    recommend_vector = user_interactions*rec_vector_scaled
   
    # Get all the artist indices in order of recommendations (descending) and
    # select only the top "num_items" items. 
    item_idx = np.argsort(recommend_vector)[::-1][:num_items]

    artists = []
    scores = []

    # Loop through our recommended artist indicies and look up the actial artist name
    for idx in item_idx:
        artists.append(item_lookup.artist.loc[item_lookup.artist_id == str(idx)].iloc[0])
        scores.append(recommend_vector[idx])

    # Create a new dataframe with recommended artist names and scores
    recommendations = pd.DataFrame({'artist': artists, 'score': scores})
    
    return recommendations

# Let's generate and print our recommendations
recommendations = recommend(user_id, data_sparse, user_vecs, item_vecs, item_lookup)
print recommendations