tensorrec_getting_started_genres.py

# Map the MovieLens IDs to our internal IDs and keep track of the genres and titles
movie_genres_by_internal_id = {}
movie_titles_by_internal_id = {}
for row in raw_movie_metadata:
    row[0] = movielens_to_internal_item_ids[int(row[0])]  # Map to IDs
    row[2] = row[2].split('|')  # Split up the genres
    movie_genres_by_internal_id[row[0]] = row[2]
    movie_titles_by_internal_id[row[0]] = row[1]

# Look at an example movie metadata row
print("Raw metadata example:\n{}\n{}".format(raw_movie_metadata_header, 
                                             raw_movie_metadata[0]))

# Build a list of genres where the index is the internal movie ID and
# the value is a list of [Genre, Genre, ...]
movie_genres = [movie_genres_by_internal_id[internal_id]
                for internal_id in range(n_items)]

# Transform the genres into binarized labels using scikit's MultiLabelBinarizer
movie_genre_features = MultiLabelBinarizer().fit_transform(movie_genres)
n_genres = movie_genre_features.shape[1]
print("Binarized genres example for movie {}:\n{}".format(movie_titles_by_internal_id[0], 
                                                          movie_genre_features[0]))

# Coerce the movie genre features to a sparse matrix, which TensorRec expects
movie_genre_features = sparse.coo_matrix(movie_genre_features)