path = 'C:\\Users\\yi&lei\\Documents\\电子书\\pydata-book-1st-edition\\pydata-book-1st-edition\\ch02\\movielens'
a = path + '\\movies.dat'
b = path + '\\ratings.dat'
c = path + '\\users.dat'
a

'C:\\Users\\yi&lei\\Documents\\电子书\\pydata-book-1st-edition\\pydata-book-1st-edition\\ch02\\movielens\\movies.dat'

movie.head()

unames = ['userid','gender','age','occupation','zip']
user = pd.read_table(c,sep='::',header=None,names = unames,engine='python')
user.head()

rnames = ['userid','movieid','ratings','timestamp']
rating = pd.read_table(b,sep='::',header=None,names = rnames,engine='python')
rating.head()

data = rating.merge(user).merge(movie)
data.head()

data.iloc[0] #data.iloc[0]和data.loc[0]结果相同

userid                                             1
movieid                                         1193
ratings                                            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

import numpy as np
meanratings = pd.pivot_table(data,index=['title'],values='ratings',columns=['gender'],aggfunc=np.mean,fill_value=0)
meanratings[:10]

movie_rating = data.groupby(['title']).size()
movie_rating[:10]

title
$1,000,000 Duck (1971)                37
'Night Mother (1986)                  70
'Til There Was You (1997)             52
'burbs, The (1989)                   303
...And Justice for All (1979)        199
1-900 (1994)                           2
10 Things I Hate About You (1999)    700
101 Dalmatians (1961)                565
101 Dalmatians (1996)                364
12 Angry Men (1957)                  616
dtype: int64

movie_ix = movie_rating.index[movie_rating > 250]
movie_ix

Index([''burbs, The (1989)', '10 Things I Hate About You (1999)','101 Dalmatians (1961)', '101 Dalmatians (1996)', '12 Angry Men (1957)','13th Warrior, The (1999)', '2 Days in the Valley (1996)','20,000 Leagues Under the Sea (1954)', '2001: A Space Odyssey (1968)','2010 (1984)',...'X-Men (2000)', 'Year of Living Dangerously (1982)','Yellow Submarine (1968)', 'You've Got Mail (1998)','Young Frankenstein (1974)', 'Young Guns (1988)','Young Guns II (1990)', 'Young Sherlock Holmes (1985)','Zero Effect (1998)', 'eXistenZ (1999)'],dtype='object', name='title', length=1214)

mrating = meanratings.loc[movie_ix]
mrating.head()

mrating.sort_values(by=['F'],ascending=False).head()

##按男女评分差值的绝对值来统计
mrating['diff'] = np.abs(mrating['F']-mrating['M'])
mrating.sort_values(by=['diff'],ascending=False).head()

##按方差或标准差来计算
mrating['var'] = mrating[['F','M']].var(axis = 1)  ##计算方差
mrating.sort_values(by=['var'],ascending=False).head()

rating_std = data.groupby(by=['title'])['ratings'].std()
rating_std_n = rating_std.loc[movie_ix] ##按照前面超过250条评论的电影进行过滤
rating_std_n.head()

title
'burbs, The (1989)                   1.107760
10 Things I Hate About You (1999)    0.989815
101 Dalmatians (1961)                0.982103
101 Dalmatians (1996)                1.098717
12 Angry Men (1957)                  0.812731
Name: ratings, dtype: float64

rating_std_n.fillna(0).sort_values(ascending=False)[:10]

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
Eyes Wide Shut (1999)                    1.259624
Evita (1996)                             1.253631
Billy Madison (1995)                     1.249970
Fear and Loathing in Las Vegas (1998)    1.246408
Bicentennial Man (1999)                  1.245533
Name: ratings, dtype: float64