#encoding:utf8import pandas as pd'''数据来源https://grouplens.org/datasets/movielens/READE是对数据文件的说明当量100W3个文件users.dat 评分用户    ID 性别 年龄 职业 邮编    1::F::1::10::48067    2::M::56::16::70072    3::M::25::15::55117    4::M::45::7::02460    5::M::25::20::55455    6::F::50::9::55117    7::M::35::1::06810    8::M::25::12::11413    9::M::25::17::61614    10::F::35::1::95370movies.dat 电影数据    1::Toy Story (1995)::Animation|Children's|Comedy    2::Jumanji (1995)::Adventure|Children's|Fantasy    3::Grumpier Old Men (1995)::Comedy|Romance    4::Waiting to Exhale (1995)::Comedy|Drama    5::Father of the Bride Part II (1995)::Comedy    6::Heat (1995)::Action|Crime|Thrillerratings.dat 电影评分   用户id 电影id 评分 时间戳    1::1193::5::978300760    1::661::3::978302109    1::914::3::978301968    1::3408::4::978300275    1::2355::5::978824291    1::1197::3::978302268    1::1287::5::978302039    1::2804::5::978300719    '''#加载数据#定义users.dat的列名unames = ['user_id','gender','age','occupation','zip']#定义ratings.dat的列名rating_names = ['user_id','movie_id','rating','timestamp']#定义movies.dat的列名movie_names = ['movie_id','title','geres']#注意分隔符users = pd.read_table('E:\\myproject\\data_analy\\ml-1m\\ml-1m\\users.dat',sep='::',header=None,names=unames)ratings = pd.read_table('E:\\myproject\\data_analy\\ml-1m\\ml-1m\\ratings.dat',sep='::',header=None,names=rating_names)movies = pd.read_table('E:\\myproject\\data_analy\\ml-1m\\ml-1m\\movies.dat',sep='::',header=None,names=movie_names)print(len(users))print(len(ratings))print(len(movies))#里面的代号在readme中有说明print(users.head(5))print(ratings.head(5))print(movies.head(5))#合并data = pd.merge(pd.merge(users,ratings),movies)print(len(data))print(data.head(5))#查看userid=1的用户print(data[data.user_id == 1])#统计男女对电影的评分差异最大的#得到男女评分的所有电影ratings_by_gender = data.pivot_table(values='rating',index='title',columns='gender',aggfunc='mean')print(ratings_by_gender.head(5))#加列用于男女评分相减ratings_by_gender['diff'] = ratings_by_gender.F - ratings_by_gender.Mprint(ratings_by_gender.head(5))#排序 降序和升序的不同体现的是男性和女性喜欢的电影print(ratings_by_gender.sort_values(by='diff',ascending=True).head(10))#定义评分人数最多(热门)ratings_by_title = data.groupby('title').size()print(ratings_by_title.head(10))print(ratings_by_title.sort_values(ascending=False).head(10))#热门电影,也就是评分最高的电影mean_ratings = data.pivot_table(values='rating',index='title',aggfunc='mean')print(mean_ratings.sort_values(ascending=False).head(10))#但是这里会有一个情况如果评分人很少但是分很高也不能算热门电影#取一个评分人数的排序也就是看的比较多的人top_10_hot = ratings_by_title.sort_values(ascending=False).head(10)#最热门的的10大电影的评分print(mean_ratings[top_10_hot.index])#评分最高的10大电影的评价次数 观影次数top_10_score = mean_ratings.sort_values(ascending=False).head(10)print(ratings_by_title[top_10_score.index])#找出热度足够高的电影,评价此处大于1000的hot_movies = ratings_by_title[ratings_by_title > 1000]#找出热门电影的评分数hot_movies_rating = mean_ratings[hot_movies.index]#对找出的热门电影评分进行降序排序top_10_good_movies = hot_movies_rating.sort_values(ascending=False).head(10)print(top_10_good_movies)#优化取出男女评分差异最大的#这里是得到男女评分差异的数据，但是没有排除掉观影人数过少的情况#首先合并三个数据data = pd.merge(pd.merge(users,ratings),movies)#得到评分的人数total_score = data.groupby('title').size()#做一个性别为列索引的透视hot_ratings_by_gender = data.pivot_table(values='rating',index='title',columns='gender',aggfunc='mean')#加上一列评分人数hot_ratings_by_gender['user_no'] = data.groupby('title').size()#加上一列性别的差异评分hot_ratings_by_gender['diff'] = ratings_by_gender.F - ratings_by_gender.M#取出评分人数大于1000hot_diff = hot_ratings_by_gender[hot_ratings_by_gender['score'] > 1000]#在大于评分人数1000的范围排序diff列这样就可以得到热门中男女评分差异最大的电影top_10_hot_diff = hot_diff.sort_values(by='diff',ascending=False).head(10)print(top_10_hot_diff)