import pandas as pd
pd.options.display.max_rows = 10
unames = ['user_id', 'gender', 'age', 'occupation', 'zip']
users = pd.read_table('datasets/movielens/users.dat', sep='::',
header=None, names=unames)
rnames = ['user_id', 'movie_id', 'rating', 'timestamp']
ratings = pd.read_table('datasets/movielens/ratings.dat', sep='::',
header=None, names=rnames)
mnames = ['movie_id', 'title', 'genres']
movies = pd.read_table('datasets/movielens/movies.dat', sep='::',
header=None, names=mnames)
E:\anaconda\lib\site-packages\ipykernel_launcher.py:7: ParserWarning: Falling back to the 'python' engine because the 'c' engine does not support regex separators (separators > 1 char and different from '\s+' are interpreted as regex); you can avoid this warning by specifying engine='python'.
import sys
E:\anaconda\lib\site-packages\ipykernel_launcher.py:11: ParserWarning: Falling back to the 'python' engine because the 'c' engine does not support regex separators (separators > 1 char and different from '\s+' are interpreted as regex); you can avoid this warning by specifying engine='python'.
# This is added back by InteractiveShellApp.init_path()
E:\anaconda\lib\site-packages\ipykernel_launcher.py:14: ParserWarning: Falling back to the 'python' engine because the 'c' engine does not support regex separators (separators > 1 char and different from '\s+' are interpreted as regex); you can avoid this warning by specifying engine='python'.
print(users[:5])
user_id gender age occupation zip
0 1 F 1 10 48067
1 2 M 56 16 70072
2 3 M 25 15 55117
3 4 M 45 7 02460
4 5 M 25 20 55455
print(ratings[:5]
)
user_id movie_id rating timestamp
0 1 1193 5 978300760
1 1 661 3 978302109
2 1 914 3 978301968
3 1 3408 4 978300275
4 1 2355 5 978824291
print(movies[:5])
movie_id title genres
0 1 Toy Story (1995) Animation|Children's|Comedy
1 2 Jumanji (1995) Adventure|Children's|Fantasy
2 3 Grumpier Old Men (1995) Comedy|Romance
3 4 Waiting to Exhale (1995) Comedy|Drama
4 5 Father of the Bride Part II (1995) Comedy
print(ratings)
user_id movie_id rating timestamp
0 1 1193 5 978300760
1 1 661 3 978302109
2 1 914 3 978301968
3 1 3408 4 978300275
4 1 2355 5 978824291
... ... ... ... ...
1000204 6040 1091 1 956716541
1000205 6040 1094 5 956704887
1000206 6040 562 5 956704746
1000207 6040 1096 4 956715648
1000208 6040 1097 4 956715569
[1000209 rows x 4 columns]
data = pd.merge(pd.merge(ratings, users), movies)
#pandas的merge可以把多个表合并在一起。
print(data)
user_id movie_id rating timestamp gender age occupation zip \
0 1 1193 5 978300760 F 1 10 48067
1 2 1193 5 978298413 M 56 16 70072
2 12 1193 4 978220179 M 25 12 32793
3 15 1193 4 978199279 M 25 7 22903
4 17 1193 5 978158471 M 50 1 95350
... ... ... ... ... ... ... ... ...
1000204 5949 2198 5 958846401 M 18 17 47901
1000205 5675 2703 3 976029116 M 35 14 30030
1000206 5780 2845 1 958153068 M 18 17 92886
1000207 5851 3607 5 957756608 F 18 20 55410
1000208 5938 2909 4 957273353 M 25 1 35401
title genres
0 One Flew Over the Cuckoo's Nest (1975) Drama
1 One Flew Over the Cuckoo's Nest (1975) Drama
2 One Flew Over the Cuckoo's Nest (1975) Drama
3 One Flew Over the Cuckoo's Nest (1975) Drama
4 One Flew Over the Cuckoo's Nest (1975) Drama
... ... ...
1000204 Modulations (1998) Documentary
1000205 Broken Vessels (1998) Drama
1000206 White Boys (1999) Drama
1000207 One Little Indian (1973) Comedy|Drama|Western
1000208 Five Wives, Three Secretaries and Me (1998) Documentary
[1000209 rows x 10 columns]
data.iloc[0]
user_id 1
movie_id 1193
rating 5
timestamp 978300760
gender F
age 1
occupation 10
zip 48067
title One Flew Over the Cuckoo's Nest (1975)
genres Drama
Name: 0, dtype: object
#用pivot_table方法可以添加参数计算相关的统计量
mean_ratings = data.pivot_table('rating', index='title',
columns='gender', aggfunc='mean')
print(mean_ratings[:5])
gender F M
title
$1,000,000 Duck (1971) 3.375000 2.761905
'Night Mother (1986) 3.388889 3.352941
'Til There Was You (1997) 2.675676 2.733333
'burbs, The (1989) 2.793478 2.962085
...And Justice for All (1979) 3.828571 3.689024
#在书中的例子中，去除了评论数少于250条的数据
ratings_by_title = data.groupby('title').size()#数据分组
active_titles = ratings_by_title.index[ratings_by_title >= 250]#数据判别
mean_ratings = mean_ratings.loc[active_titles]#子集在总计算中选取就好了
top_female_ratings = mean_ratings.sort_values(by='F', ascending=False)
#根据F(女生)列进行降序排列
print(top_female_ratings[:10])
gender F M
title
Close Shave, A (1995) 4.644444 4.473795
Wrong Trousers, The (1993) 4.588235 4.478261
Sunset Blvd. (a.k.a. Sunset Boulevard) (1950) 4.572650 4.464589
Wallace & Gromit: The Best of Aardman Animation... 4.563107 4.385075
Schindler's List (1993) 4.562602 4.491415
Shawshank Redemption, The (1994) 4.539075 4.560625
Grand Day Out, A (1992) 4.537879 4.293255
To Kill a Mockingbird (1962) 4.536667 4.372611
Creature Comforts (1990) 4.513889 4.272277
Usual Suspects, The (1995) 4.513317 4.518248