pandas小节，电影，男女喜爱差异数据分析

pandas

电影喜爱分析

多个framedata合并

• pd.merge(ratings, users) 合并相同类的
• pd.concat([ratings,users,movies],axis=1) 横向不合并相同类的
• meand=data.table(‘rating’,index=‘title’,columns=‘gender’,aggfunc=‘mean’)
  取平均值，序列按index排列
• atings_by_title = data.groupby(‘title’).size() 统计title中相同的个数
• active_titles = ratings_by_title.index[ratings_by_title >= 250]
  索引布尔值为真数据

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

pd.options.display.max_rows	= 10

unames = ['user_id','gender','age','occupation','zip']
users = pd.read_table(r'C:\Users\Administrator\Desktop\网络模型\ml-1m\users.dat',sep='::',header=None,names=unames)
rnames	=	['user_id','movie_id','rating','timestamp']
ratings	=	pd.read_table(r'C:\Users\Administrator\Desktop\网络模型\ml-1m\ratings.dat',sep='::',header=None,names=rnames)
mnames	=	['movie_id','title','genres']
movies	=	pd.read_table(r'C:\Users\Administrator\Desktop\网络模型\ml-1m\movies.dat',sep='::',header=None,names=mnames)

E:\anaconda\envs\yolo\lib\site-packages\ipykernel_launcher.py:2: 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'.
  
E:\anaconda\envs\yolo\lib\site-packages\ipykernel_launcher.py:4: 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'.
  after removing the cwd from sys.path.
E:\anaconda\envs\yolo\lib\site-packages\ipykernel_launcher.py:6: 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'.

users[:3]

	user_id	gender	age	occupation	zip
0	1	F	1	10	48067
1	2	M	56	16	70072
2	3	M	25	15	55117

ratings[:3]

	user_id	movie_id	rating	timestamp
0	1	1193	5	978300760
1	1	661	3	978302109
2	1	914	3	978301968

movies[:3]

	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

data=pd.merge(pd.merge(ratings,	users),	movies)   #合并同类
pd.concat([ratings,users,movies],axis=1)[:3]  #不合并同类

	user_id	movie_id	rating	timestamp	user_id	gender	age	occupation	zip	movie_id	title	genres
0	1	1193	5	978300760	1.0	F	1.0	10.0	48067	1.0	Toy Story (1995)	Animation|Children's|Comedy
1	1	661	3	978302109	2.0	M	56.0	16.0	70072	2.0	Jumanji (1995)	Adventure|Children's|Fantasy
2	1	914	3	978301968	3.0	M	25.0	15.0	55117	3.0	Grumpier Old Men (1995)	Comedy|Romance

data[:3]

	user_id	movie_id	rating	timestamp	gender	age	occupation	zip	title	genres
0	1	1193	5	978300760	F	1	10	48067	One Flew Over the Cuckoo's Nest (1975)	Drama
1	2	1193	5	978298413	M	56	16	70072	One Flew Over the Cuckoo's Nest (1975)	Drama
2	12	1193	4	978220179	M	25	12	32793	One Flew Over the Cuckoo's Nest (1975)	Drama

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

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

ratings_by_title = data.groupby('title').size()

ratings_by_title[:4]

title
$1,000,000 Duck (1971)        37
'Night Mother (1986)          70
'Til There Was You (1997)     52
'burbs, The (1989)           303
dtype: int64

active_titles = ratings_by_title.index[ratings_by_title	>=	250]

pd.Series(active_titles)[:5]

0                   'burbs, The (1989)
1    10 Things I Hate About You (1999)
2                101 Dalmatians (1961)
3                101 Dalmatians (1996)
4                  12 Angry Men (1957)
Name: title, dtype: object

mean_ratings = mean_ratings.loc[active_titles]
mean_ratings[:5]

gender	F	M
title
'burbs, The (1989)	2.793478	2.962085
10 Things I Hate About You (1999)	3.646552	3.311966
101 Dalmatians (1961)	3.791444	3.500000
101 Dalmatians (1996)	3.240000	2.911215
12 Angry Men (1957)	4.184397	4.328421

top_female_ratings=mean_ratings.sort_values(by='F',ascending=False)  #对女性评分降序排列 ascending升序
top_female_ratings[:4]

gender	F	M	different
title
Close Shave, A (1995)	4.644444	4.473795	-0.170650
Wrong Trousers, The (1993)	4.588235	4.478261	-0.109974
Sunset Blvd. (a.k.a. Sunset Boulevard) (1950)	4.572650	4.464589	-0.108060
Wallace & Gromit: The Best of Aardman Animation (1996)	4.563107	4.385075	-0.178032

mean_ratings['different']=mean_ratings['M'] - mean_ratings['F']   #计算评分差异
sorted_by_diff = mean_ratings.sort_values(by='different')
sorted_by_diff[:4]  #分歧最大的，女生评分高的

gender	F	M	different
title
Dirty Dancing (1987)	3.790378	2.959596	-0.830782
Jumpin' Jack Flash (1986)	3.254717	2.578358	-0.676359
Grease (1978)	3.975265	3.367041	-0.608224
Little Women (1994)	3.870588	3.321739	-0.548849

rating_std_by_title	=	data.groupby('title')['rating'].std()
rating_std_by_title	=	rating_std_by_title.loc[active_titles]
rating_std_by_title.sort_values(ascending=False)[:5]   #排序

title
Dumb & Dumber (1994)                     1.321333
Blair Witch Project, The (1999)          1.316368
Natural Born Killers (1994)              1.307198
Tank Girl (1995)                         1.277695
Rocky Horror Picture Show, The (1975)    1.260177
Name: rating, dtype: float64