movies data analysis

import pandas as pd
unames = ['user_id', 'gender', 'age', 'occupation', 'zip']
users = pd.read_table('..pydata/ch02/movielens/users.dat', sep='::', header=None, names=unames, engine='python')

rnames = ['user_id', 'movie_id', 'rating', 'timestamp']
ratings = pd.read_table('..pydata/ch02/movielens/ratings.dat', sep='::', header=None, names=rnames, engine='python')

mnames = ['movie_id', 'title', 'genres']
movies = pd.read_table('..pydata/ch02/movielens/movies.dat', sep='::', header=None, names=mnames, engine='python')

#合并三个表格
data = pd.merge(pd.merge(ratings, users), movies)
#按性别计算每部电影的平均得分
mean_ratings = data.pivot_table(values='rating', index='title', columns='gender', aggfunc='mean')

mean_ratings