movielens_preprocess.py 文件源码

def main():
    # read and preprocess the movie data
    movie = pd.read_table('movies.dat', sep='::', names=['movie_id', 'movie_name', 'tag'], engine='python')
    movie = movie_preprocessing(movie)

    # read the ratings data and merge it with movie data
    rating = pd.read_table("ratings.dat", sep="::",
                           names=["user_id", "movie_id", "rating", "timestamp"], engine='python')
    data = pd.merge(rating, movie, on="movie_id")

    # extract feature from our data set
    streaming_batch, user_feature, actions, reward_list = feature_extraction(data)
    streaming_batch.to_csv("streaming_batch.csv", sep='\t', index=False)
    user_feature.to_csv("user_feature.csv", sep='\t')
    pd.DataFrame(actions, columns=['movie_id']).to_csv("actions.csv", sep='\t', index=False)
    reward_list.to_csv("reward_list.csv", sep='\t', index=False)

    action_context = movie[movie['movie_id'].isin(actions)]
    action_context.to_csv("action_context.csv", sep='\t', index = False)