MovieLens-1M数据分析

1  首先导入pandas包，然后读入数据，数据集从https://github.com/wesm/pydata-book上下载就行

import pandas as pd

unames = ['user_id', 'gender', 'age', 'occupation', 'zip']

users = pd.read_table('/movielens/users.dat', sep='::', header=None, names=unames, engine='python')

rnames = ['user_id', 'movie_id', 'rating', 'timestamp']

ratings = pd.read_table('/movielens/ratings.dat', sep='::', header=None, names=rnames, engine='python')

mnames = ['user_id', 'title', 'genres']

movies = pd.read_table('/movielens/movies.dat', sep='::', header=None, names=mnames, engine='python')

可以利用users[:5]等切片看看自己加载的数据集是否成功

2   用pandas的merge函数将ratings跟users合并到一起，然后将movies也合并进去

data = pd.merge(pd.merge(ratings, users), movies)

data.loc[0]   #查看第一个元素

计算电影平均分

mean_ratings=data.pivot_table('rating',index='title',columns='gender',aggfunc='mean')

ratings_by_title=data.groupby('title').size() #对title进行分组

active_titles=ratings_by_title.index[ratings_by_title>=250] # 获得评论数据大于250的电影

mean_ratings=mean_ratings.loc[active_titles]mean_ratings

mean_ratings=mean_ratings.rename(index={'Seven Samurai (The Magnificent Seven) (Shichinin no samurai) (1954)':'Seven Samurai (Shichinin no samurai) (1954)'})

top_female_ratings=mean_ratings.sort_index(by='F',ascending=False)# 获取女性观众最喜欢的电影

mean_ratings['diff'] = mean_ratings['M'] - mean_ratings['F'] #计算评分分歧

sorted_by_diff = mean_ratings.sort_values(by='diff')

rating_std_by_title = data.groupby('title')['rating'].std()  #根据电影名称分组得到标准差

rating_std_by_title = rating_std_by_title.loc[active_titles]  # 根据active_title进行过滤