tensorrec_getting_started_loading.py

# Open and read in the ratings file
print('Loading ratings')
with open('ratings.csv', 'r') as ratings_file:
    ratings_file_reader = csv.reader(ratings_file)
    raw_ratings = list(ratings_file_reader)
    raw_ratings_header = raw_ratings.pop(0)

# Iterate through the input to map MovieLens IDs to new internal IDs
# The new internal IDs will be created by the defaultdict on insertion
movielens_to_internal_user_ids = defaultdict(lambda: len(movielens_to_internal_user_ids))
movielens_to_internal_item_ids = defaultdict(lambda: len(movielens_to_internal_item_ids))
for row in raw_ratings:
    row[0] = movielens_to_internal_user_ids[int(row[0])]
    row[1] = movielens_to_internal_item_ids[int(row[1])]
    row[2] = float(row[2])
n_users = len(movielens_to_internal_user_ids)
n_items = len(movielens_to_internal_item_ids)