(판다스 시각화) 영화 평점 분석

영화 평점 분석 실습

import pandas as pd
from pandas import Series, DataFrame
import numpy as np

1. 영화 평점 데이터 적재 및 전처리

# 사용자 데이터 읽어오기
users = pd.read_csv('data/movielens/users.dat', sep = '::', engine = 'python',
                   names = ['사용자아이디', '성별','연령','직업','지역'])
users.head()

	사용자아이디	성별	연령	직업	지역
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

# 평점 데이터 읽어오기
ratings = pd.read_csv('data/movielens/ratings.dat', sep = '::', engine = 'python',
                   names = ['사용자아이디', '영화아이디','평점','타임스탬프'])
ratings.head()

	사용자아이디	영화아이디	평점	타임스탬프
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

# 영화데이터 읽어오기
movies = pd.read_csv('data/movielens/movies.dat', sep = '::', engine = 'python',
                   names = ['영화아이디','영화제목','장르'], encoding = 'latin-1')
movies.head()

	영화아이디	영화제목	장르
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

# 3개의 데이터프레임을 하나로 합치기
data = pd.merge(users, ratings)
data = pd.merge(data, movies)
data.head()

	사용자아이디	성별	연령	직업	지역	영화아이디	평점	타임스탬프	영화제목	장르
0	1	F	1	10	48067	1193	5	978300760	One Flew Over the Cuckoo's Nest (1975)	Drama
1	2	M	56	16	70072	1193	5	978298413	One Flew Over the Cuckoo's Nest (1975)	Drama
2	12	M	25	12	32793	1193	4	978220179	One Flew Over the Cuckoo's Nest (1975)	Drama
3	15	M	25	7	22903	1193	4	978199279	One Flew Over the Cuckoo's Nest (1975)	Drama
4	17	M	50	1	95350	1193	5	978158471	One Flew Over the Cuckoo's Nest (1975)	Drama

print('사용자 수:', len(users))
print('리뷰 수:', len(ratings)) #ratings.사용자아이디.count()
print('영화 수:', len(movies))

사용자 수: 6040
리뷰 수: 1000209
영화 수: 3883

# 모든 사용자가 리뷰를 했나?
ratings.사용자아이디.nunique() #모든 사용자가 영화 리뷰에 참여!

6040

# 리뷰가 없는 영화는 있는가?
ratings.nunique() #영화 수는 3883, 영화 아이디는 3706으로, 176개는 영화 리뷰가 없음!

사용자아이디      6040
영화아이디       3706
평점             5
타임스탬프     458455
dtype: int64

2. 보고 싶은 영화 찾기

영화들의 평점 평균을 구하여, 사람들에게 인정받는 (평점이 높은) 영화 찾기

data.head()

	사용자아이디	성별	연령	직업	지역	영화아이디	평점	타임스탬프	영화제목	장르
0	1	F	1	10	48067	1193	5	978300760	One Flew Over the Cuckoo's Nest (1975)	Drama
1	2	M	56	16	70072	1193	5	978298413	One Flew Over the Cuckoo's Nest (1975)	Drama
2	12	M	25	12	32793	1193	4	978220179	One Flew Over the Cuckoo's Nest (1975)	Drama
3	15	M	25	7	22903	1193	4	978199279	One Flew Over the Cuckoo's Nest (1975)	Drama
4	17	M	50	1	95350	1193	5	978158471	One Flew Over the Cuckoo's Nest (1975)	Drama

# 영화들의 평점 평균을 구하여, 평점이 높은 영화 찾기 
data.pivot_table(index='영화제목', aggfunc='mean', values='평점')\
                 .sort_values(by='평점', ascending=False).head(10)

	평점
영화제목
Ulysses (Ulisse) (1954)	5.0
Lured (1947)	5.0
Follow the Bitch (1998)	5.0
Bittersweet Motel (2000)	5.0
Song of Freedom (1936)	5.0
One Little Indian (1973)	5.0
Smashing Time (1967)	5.0
Schlafes Bruder (Brother of Sleep) (1995)	5.0
Gate of Heavenly Peace, The (1995)	5.0
Baby, The (1973)	5.0

data.pivot_table(index='영화제목', aggfunc='mean', values='평점').nlargest(10, '평점') #nsmallest

	평점
영화제목
Baby, The (1973)	5.0
Bittersweet Motel (2000)	5.0
Follow the Bitch (1998)	5.0
Gate of Heavenly Peace, The (1995)	5.0
Lured (1947)	5.0
One Little Indian (1973)	5.0
Schlafes Bruder (Brother of Sleep) (1995)	5.0
Smashing Time (1967)	5.0
Song of Freedom (1936)	5.0
Ulysses (Ulisse) (1954)	5.0

평균 평점이 만점인 영화들이 최상위에 위치함. 일반적으로 평점이 만점인 경우는 대부분 평점의 개수가 매우 적은 경우이므로, 이를 확인하기 위해 평점의 개수도 함께 구해본다.

#영화제목도 중복될 수 있으므로, 제대로 하려면 영화아이디로 해야 됨
# 중복된 영화제목이 있는지 확인

movies.영화제목.nunique() #위에서 구한 영화 수와 일치하므로 중복X

3883

movies.nunique()

영화아이디    3883
영화제목     3883
장르        301
dtype: int64

#data.pivot_table(index=['영화아이디','영화제목'], aggfunc='mean', values='평점')\ 
#                 .nlargest(10, '평점') #nsmallest

data.pivot_table(index='영화제목', aggfunc=['mean','count'], values='평점')

	mean	count
	평점	평점
영화제목
$1,000,000 Duck (1971)	3.027027	37
'Night Mother (1986)	3.371429	70
'Til There Was You (1997)	2.692308	52
'burbs, The (1989)	2.910891	303
...And Justice for All (1979)	3.713568	199
...	...	...
Zed & Two Noughts, A (1985)	3.413793	29
Zero Effect (1998)	3.750831	301
Zero Kelvin (Kjærlighetens kjøtere) (1995)	3.500000	2
Zeus and Roxanne (1997)	2.521739	23
eXistenZ (1999)	3.256098	410

3706 rows × 2 columns

data.pivot_table(index='영화제목', aggfunc=['mean','count'], values='평점')\
.nlargest(10, ('mean','평점')) #평점 높고, 개수도 많은 걸 찾자!

	mean	count
	평점	평점
영화제목
Baby, The (1973)	5.0	1
Bittersweet Motel (2000)	5.0	1
Follow the Bitch (1998)	5.0	1
Gate of Heavenly Peace, The (1995)	5.0	3
Lured (1947)	5.0	1
One Little Indian (1973)	5.0	1
Schlafes Bruder (Brother of Sleep) (1995)	5.0	1
Smashing Time (1967)	5.0	2
Song of Freedom (1936)	5.0	1
Ulysses (Ulisse) (1954)	5.0	1

#평점 평균이 4.5 이상이고, 평점의 개수가 1000개 이상인 영화를 보고싶은 영화로 지정!
영화평점 = data.pivot_table(index='영화제목', aggfunc=['mean','count'], values='평점')
영화평점.columns=['평점평균','평점개수']

영화평점

	평점평균	평점개수
영화제목
$1,000,000 Duck (1971)	3.027027	37
'Night Mother (1986)	3.371429	70
'Til There Was You (1997)	2.692308	52
'burbs, The (1989)	2.910891	303
...And Justice for All (1979)	3.713568	199
...	...	...
Zed & Two Noughts, A (1985)	3.413793	29
Zero Effect (1998)	3.750831	301
Zero Kelvin (Kjærlighetens kjøtere) (1995)	3.500000	2
Zeus and Roxanne (1997)	2.521739	23
eXistenZ (1999)	3.256098	410

3706 rows × 2 columns

영화평점[(영화평점.평점평균 >= 4.5) & (영화평점.평점개수 >=1000)]

	평점평균	평점개수
영화제목
Godfather, The (1972)	4.524966	2223
Schindler's List (1993)	4.510417	2304
Shawshank Redemption, The (1994)	4.554558	2227
Usual Suspects, The (1995)	4.517106	1783

[실습 #1] 여자들이 좋아하는 영화 찾기

- 여성 평점이 4.0 이상이고 여성 평점의 개수가 500개 이상인 영화

data_f = data[data['성별']=='F']
data_f

	사용자아이디	성별	연령	직업	지역	영화아이디	평점	타임스탬프	영화제목	장르
0	1	F	1	10	48067	1193	5	978300760	One Flew Over the Cuckoo's Nest (1975)	Drama
5	18	F	18	3	95825	1193	4	978156168	One Flew Over the Cuckoo's Nest (1975)	Drama
7	24	F	25	7	10023	1193	5	978136709	One Flew Over the Cuckoo's Nest (1975)	Drama
8	28	F	25	1	14607	1193	3	978125194	One Flew Over the Cuckoo's Nest (1975)	Drama
19	59	F	50	1	55413	1193	4	977934292	One Flew Over the Cuckoo's Nest (1975)	Drama
...	...	...	...	...	...	...	...	...	...	...
1000199	5334	F	56	13	46140	3382	5	960796159	Song of Freedom (1936)	Drama
1000200	5420	F	1	19	14850	1843	3	960156505	Slappy and the Stinkers (1998)	Children's|Comedy
1000201	5433	F	35	17	45014	286	3	960240881	Nemesis 2: Nebula (1995)	Action|Sci-Fi|Thriller
1000202	5494	F	35	17	94306	3530	4	959816296	Smoking/No Smoking (1993)	Comedy
1000207	5851	F	18	20	55410	3607	5	957756608	One Little Indian (1973)	Comedy|Drama|Western

246440 rows × 10 columns

여성평점 = data_f.pivot_table(index='영화제목', aggfunc=['mean','count'], values='평점')
여성평점.columns=['평점평균','평점개수']

여성평점[(여성평점.평점평균 >= 4.0) & (여성평점.평점개수 >=500)]

	평점평균	평점개수
영화제목
American Beauty (1999)	4.238901	946
Being John Malkovich (1999)	4.159930	569
Braveheart (1995)	4.016484	546
Casablanca (1942)	4.300990	505
E.T. the Extra-Terrestrial (1982)	4.089850	601
Fargo (1996)	4.217656	657
Forrest Gump (1994)	4.045031	644
L.A. Confidential (1997)	4.106007	566
Matrix, The (1999)	4.128405	514
Princess Bride, The (1987)	4.342767	636
Pulp Fiction (1994)	4.071956	542
Raiders of the Lost Ark (1981)	4.332168	572
Saving Private Ryan (1998)	4.114783	575
Schindler's List (1993)	4.562602	615
Shakespeare in Love (1998)	4.181704	798
Shawshank Redemption, The (1994)	4.539075	627
Silence of the Lambs, The (1991)	4.271955	706
Sixth Sense, The (1999)	4.477410	664
Star Wars: Episode IV - A New Hope (1977)	4.302937	647
Star Wars: Episode V - The Empire Strikes Back (1980)	4.106481	648
Toy Story (1995)	4.187817	591
Wizard of Oz, The (1939)	4.355030	507

data[data['성별']=='F'].pivot_table(index='영화제목', 
                                  aggfunc=['mean','count'], values='평점')

	mean	count
	평점	평점
영화제목
$1,000,000 Duck (1971)	3.375000	16
'Night Mother (1986)	3.388889	36
'Til There Was You (1997)	2.675676	37
'burbs, The (1989)	2.793478	92
...And Justice for All (1979)	3.828571	35
...	...	...
Your Friends and Neighbors (1998)	2.888889	27
Zed & Two Noughts, A (1985)	3.500000	8
Zero Effect (1998)	3.864407	59
Zeus and Roxanne (1997)	2.777778	9
eXistenZ (1999)	3.098592	71

3481 rows × 2 columns

ex1 = data.pivot_table(index='영화제목', columns='성별',                       
                       aggfunc=['mean','count'], values='평점')
ex1

	mean		count
성별	F	M	F	M
영화제목
$1,000,000 Duck (1971)	3.375000	2.761905	16.0	21.0
'Night Mother (1986)	3.388889	3.352941	36.0	34.0
'Til There Was You (1997)	2.675676	2.733333	37.0	15.0
'burbs, The (1989)	2.793478	2.962085	92.0	211.0
...And Justice for All (1979)	3.828571	3.689024	35.0	164.0
...	...	...	...	...
Zed & Two Noughts, A (1985)	3.500000	3.380952	8.0	21.0
Zero Effect (1998)	3.864407	3.723140	59.0	242.0
Zero Kelvin (Kjærlighetens kjøtere) (1995)	NaN	3.500000	NaN	2.0
Zeus and Roxanne (1997)	2.777778	2.357143	9.0	14.0
eXistenZ (1999)	3.098592	3.289086	71.0	339.0

3706 rows × 4 columns

ex1[(ex1[('mean','F')]>= 4.0) & (ex1[('count','F')] >=500)]

	mean		count
성별	F	M	F	M
영화제목
American Beauty (1999)	4.238901	4.347301	946.0	2482.0
Being John Malkovich (1999)	4.159930	4.113636	569.0	1672.0
Braveheart (1995)	4.016484	4.297839	546.0	1897.0
Casablanca (1942)	4.300990	4.461340	505.0	1164.0
E.T. the Extra-Terrestrial (1982)	4.089850	3.920264	601.0	1668.0
Fargo (1996)	4.217656	4.267780	657.0	1856.0
Forrest Gump (1994)	4.045031	4.105806	644.0	1550.0
L.A. Confidential (1997)	4.106007	4.256678	566.0	1722.0
Matrix, The (1999)	4.128405	4.362235	514.0	2076.0
Princess Bride, The (1987)	4.342767	4.288942	636.0	1682.0
Pulp Fiction (1994)	4.071956	4.346839	542.0	1629.0
Raiders of the Lost Ark (1981)	4.332168	4.520597	572.0	1942.0
Saving Private Ryan (1998)	4.114783	4.398941	575.0	2078.0
Schindler's List (1993)	4.562602	4.491415	615.0	1689.0
Shakespeare in Love (1998)	4.181704	4.099936	798.0	1571.0
Shawshank Redemption, The (1994)	4.539075	4.560625	627.0	1600.0
Silence of the Lambs, The (1991)	4.271955	4.381944	706.0	1872.0
Sixth Sense, The (1999)	4.477410	4.379944	664.0	1795.0
Star Wars: Episode IV - A New Hope (1977)	4.302937	4.495307	647.0	2344.0
Star Wars: Episode V - The Empire Strikes Back (1980)	4.106481	4.344577	648.0	2342.0
Toy Story (1995)	4.187817	4.130552	591.0	1486.0
Wizard of Oz, The (1939)	4.355030	4.203138	507.0	1211.0

[실습 #2] 실습 #1에서 구한 영화(여성인기영화)의 장르를 분석해 보자.

여성인기영화의 장르 통계 구하기

예를 들어, 여성인기영화 중 Drama 장르의 영화는 10개, Action 영화는 3개, …

여성인기영화 = 여성평점[(여성평점.평점평균 >= 4.0) & (여성평점.평점개수 >=500)]
여성인기영화

	평점평균	평점개수
영화제목
American Beauty (1999)	4.238901	946
Being John Malkovich (1999)	4.159930	569
Braveheart (1995)	4.016484	546
Casablanca (1942)	4.300990	505
E.T. the Extra-Terrestrial (1982)	4.089850	601
Fargo (1996)	4.217656	657
Forrest Gump (1994)	4.045031	644
L.A. Confidential (1997)	4.106007	566
Matrix, The (1999)	4.128405	514
Princess Bride, The (1987)	4.342767	636
Pulp Fiction (1994)	4.071956	542
Raiders of the Lost Ark (1981)	4.332168	572
Saving Private Ryan (1998)	4.114783	575
Schindler's List (1993)	4.562602	615
Shakespeare in Love (1998)	4.181704	798
Shawshank Redemption, The (1994)	4.539075	627
Silence of the Lambs, The (1991)	4.271955	706
Sixth Sense, The (1999)	4.477410	664
Star Wars: Episode IV - A New Hope (1977)	4.302937	647
Star Wars: Episode V - The Empire Strikes Back (1980)	4.106481	648
Toy Story (1995)	4.187817	591
Wizard of Oz, The (1939)	4.355030	507

여성인기영화.index

Index(['American Beauty (1999)', 'Being John Malkovich (1999)',
       'Braveheart (1995)', 'Casablanca (1942)',
       'E.T. the Extra-Terrestrial (1982)', 'Fargo (1996)',
       'Forrest Gump (1994)', 'L.A. Confidential (1997)', 'Matrix, The (1999)',
       'Princess Bride, The (1987)', 'Pulp Fiction (1994)',
       'Raiders of the Lost Ark (1981)', 'Saving Private Ryan (1998)',
       'Schindler's List (1993)', 'Shakespeare in Love (1998)',
       'Shawshank Redemption, The (1994)', 'Silence of the Lambs, The (1991)',
       'Sixth Sense, The (1999)', 'Star Wars: Episode IV - A New Hope (1977)',
       'Star Wars: Episode V - The Empire Strikes Back (1980)',
       'Toy Story (1995)', 'Wizard of Oz, The (1939)'],
      dtype='object', name='영화제목')

movies.영화제목.values

array(['Toy Story (1995)', 'Jumanji (1995)', 'Grumpier Old Men (1995)',
       ..., 'Tigerland (2000)', 'Two Family House (2000)',
       'Contender, The (2000)'], dtype=object)

lst=[]
for i in 여성인기영화.index:
    if i in movies.영화제목.values:
        lst.append(i)
lst

['American Beauty (1999)',
 'Being John Malkovich (1999)',
 'Braveheart (1995)',
 'Casablanca (1942)',
 'E.T. the Extra-Terrestrial (1982)',
 'Fargo (1996)',
 'Forrest Gump (1994)',
 'L.A. Confidential (1997)',
 'Matrix, The (1999)',
 'Princess Bride, The (1987)',
 'Pulp Fiction (1994)',
 'Raiders of the Lost Ark (1981)',
 'Saving Private Ryan (1998)',
 "Schindler's List (1993)",
 'Shakespeare in Love (1998)',
 'Shawshank Redemption, The (1994)',
 'Silence of the Lambs, The (1991)',
 'Sixth Sense, The (1999)',
 'Star Wars: Episode IV - A New Hope (1977)',
 'Star Wars: Episode V - The Empire Strikes Back (1980)',
 'Toy Story (1995)',
 'Wizard of Oz, The (1939)']

여성인기영화장르 = movies[movies.영화제목.isin(lst)]
여성인기영화장르

	영화아이디	영화제목	장르
0	1	Toy Story (1995)	Animation|Children's|Comedy
108	110	Braveheart (1995)	Action|Drama|War
257	260	Star Wars: Episode IV - A New Hope (1977)	Action|Adventure|Fantasy|Sci-Fi
293	296	Pulp Fiction (1994)	Crime|Drama
315	318	Shawshank Redemption, The (1994)	Drama
352	356	Forrest Gump (1994)	Comedy|Romance|War
523	527	Schindler's List (1993)	Drama|War
589	593	Silence of the Lambs, The (1991)	Drama|Thriller
604	608	Fargo (1996)	Crime|Drama|Thriller
900	912	Casablanca (1942)	Drama|Romance|War
907	919	Wizard of Oz, The (1939)	Adventure|Children's|Drama|Musical
1081	1097	E.T. the Extra-Terrestrial (1982)	Children's|Drama|Fantasy|Sci-Fi
1178	1196	Star Wars: Episode V - The Empire Strikes Back...	Action|Adventure|Drama|Sci-Fi|War
1179	1197	Princess Bride, The (1987)	Action|Adventure|Comedy|Romance
1180	1198	Raiders of the Lost Ark (1981)	Action|Adventure
1575	1617	L.A. Confidential (1997)	Crime|Film-Noir|Mystery|Thriller
1959	2028	Saving Private Ryan (1998)	Action|Drama|War
2327	2396	Shakespeare in Love (1998)	Comedy|Romance
2502	2571	Matrix, The (1999)	Action|Sci-Fi|Thriller
2693	2762	Sixth Sense, The (1999)	Thriller
2789	2858	American Beauty (1999)	Comedy|Drama
2928	2997	Being John Malkovich (1999)	Comedy

k =[]
for i in 여성인기영화장르.장르:
    for j in i.split('|'):
        k.append(j)

k

['Animation',
 "Children's",
 'Comedy',
 'Action',
 'Drama',
 'War',
 'Action',
 'Adventure',
 'Fantasy',
 'Sci-Fi',
 'Crime',
 'Drama',
 'Drama',
 'Comedy',
 'Romance',
 'War',
 'Drama',
 'War',
 'Drama',
 'Thriller',
 'Crime',
 'Drama',
 'Thriller',
 'Drama',
 'Romance',
 'War',
 'Adventure',
 "Children's",
 'Drama',
 'Musical',
 "Children's",
 'Drama',
 'Fantasy',
 'Sci-Fi',
 'Action',
 'Adventure',
 'Drama',
 'Sci-Fi',
 'War',
 'Action',
 'Adventure',
 'Comedy',
 'Romance',
 'Action',
 'Adventure',
 'Crime',
 'Film-Noir',
 'Mystery',
 'Thriller',
 'Action',
 'Drama',
 'War',
 'Comedy',
 'Romance',
 'Action',
 'Sci-Fi',
 'Thriller',
 'Thriller',
 'Comedy',
 'Drama',
 'Comedy']

count={}
for i in k:
    try: count[i] += 1
    except: count[i]=1
print(count)

{'Animation': 1, "Children's": 3, 'Comedy': 6, 'Action': 7, 'Drama': 12, 'War': 6, 'Adventure': 5, 'Fantasy': 2, 'Sci-Fi': 4, 'Crime': 3, 'Romance': 4, 'Thriller': 5, 'Musical': 1, 'Film-Noir': 1, 'Mystery': 1}

ex2 = ex1[(ex1[('mean','F')]>= 4.0) & (ex1[('count','F')] >=500)].index

ex2

Index(['American Beauty (1999)', 'Being John Malkovich (1999)',
       'Braveheart (1995)', 'Casablanca (1942)',
       'E.T. the Extra-Terrestrial (1982)', 'Fargo (1996)',
       'Forrest Gump (1994)', 'L.A. Confidential (1997)', 'Matrix, The (1999)',
       'Princess Bride, The (1987)', 'Pulp Fiction (1994)',
       'Raiders of the Lost Ark (1981)', 'Saving Private Ryan (1998)',
       'Schindler's List (1993)', 'Shakespeare in Love (1998)',
       'Shawshank Redemption, The (1994)', 'Silence of the Lambs, The (1991)',
       'Sixth Sense, The (1999)', 'Star Wars: Episode IV - A New Hope (1977)',
       'Star Wars: Episode V - The Empire Strikes Back (1980)',
       'Toy Story (1995)', 'Wizard of Oz, The (1939)'],
      dtype='object', name='영화제목')

ex2_df = movies[movies.영화제목.isin(ex2)]
ex2_df

	영화아이디	영화제목	장르
0	1	Toy Story (1995)	Animation|Children's|Comedy
108	110	Braveheart (1995)	Action|Drama|War
257	260	Star Wars: Episode IV - A New Hope (1977)	Action|Adventure|Fantasy|Sci-Fi
293	296	Pulp Fiction (1994)	Crime|Drama
315	318	Shawshank Redemption, The (1994)	Drama
352	356	Forrest Gump (1994)	Comedy|Romance|War
523	527	Schindler's List (1993)	Drama|War
589	593	Silence of the Lambs, The (1991)	Drama|Thriller
604	608	Fargo (1996)	Crime|Drama|Thriller
900	912	Casablanca (1942)	Drama|Romance|War
907	919	Wizard of Oz, The (1939)	Adventure|Children's|Drama|Musical
1081	1097	E.T. the Extra-Terrestrial (1982)	Children's|Drama|Fantasy|Sci-Fi
1178	1196	Star Wars: Episode V - The Empire Strikes Back...	Action|Adventure|Drama|Sci-Fi|War
1179	1197	Princess Bride, The (1987)	Action|Adventure|Comedy|Romance
1180	1198	Raiders of the Lost Ark (1981)	Action|Adventure
1575	1617	L.A. Confidential (1997)	Crime|Film-Noir|Mystery|Thriller
1959	2028	Saving Private Ryan (1998)	Action|Drama|War
2327	2396	Shakespeare in Love (1998)	Comedy|Romance
2502	2571	Matrix, The (1999)	Action|Sci-Fi|Thriller
2693	2762	Sixth Sense, The (1999)	Thriller
2789	2858	American Beauty (1999)	Comedy|Drama
2928	2997	Being John Malkovich (1999)	Comedy

ex2_df.장르.str.split('|')

0               [Animation, Children's, Comedy]
108                        [Action, Drama, War]
257        [Action, Adventure, Fantasy, Sci-Fi]
293                              [Crime, Drama]
315                                     [Drama]
352                      [Comedy, Romance, War]
523                                [Drama, War]
589                           [Drama, Thriller]
604                    [Crime, Drama, Thriller]
900                       [Drama, Romance, War]
907     [Adventure, Children's, Drama, Musical]
1081       [Children's, Drama, Fantasy, Sci-Fi]
1178    [Action, Adventure, Drama, Sci-Fi, War]
1179       [Action, Adventure, Comedy, Romance]
1180                        [Action, Adventure]
1575      [Crime, Film-Noir, Mystery, Thriller]
1959                       [Action, Drama, War]
2327                          [Comedy, Romance]
2502                 [Action, Sci-Fi, Thriller]
2693                                 [Thriller]
2789                            [Comedy, Drama]
2928                                   [Comedy]
Name: 장르, dtype: object

ex2_df = ex2_df.장르.str.split('|', expand=True)
ex2_df

	0	1	2	3	4
0	Animation	Children's	Comedy	None	None
108	Action	Drama	War	None	None
257	Action	Adventure	Fantasy	Sci-Fi	None
293	Crime	Drama	None	None	None
315	Drama	None	None	None	None
352	Comedy	Romance	War	None	None
523	Drama	War	None	None	None
589	Drama	Thriller	None	None	None
604	Crime	Drama	Thriller	None	None
900	Drama	Romance	War	None	None
907	Adventure	Children's	Drama	Musical	None
1081	Children's	Drama	Fantasy	Sci-Fi	None
1178	Action	Adventure	Drama	Sci-Fi	War
1179	Action	Adventure	Comedy	Romance	None
1180	Action	Adventure	None	None	None
1575	Crime	Film-Noir	Mystery	Thriller	None
1959	Action	Drama	War	None	None
2327	Comedy	Romance	None	None	None
2502	Action	Sci-Fi	Thriller	None	None
2693	Thriller	None	None	None	None
2789	Comedy	Drama	None	None	None
2928	Comedy	None	None	None	None

장르1 = ex2_df[0].value_counts()
장르2 = ex2_df[1].value_counts()
장르3 = ex2_df[2].value_counts()
장르4 = ex2_df[3].value_counts()
장르5 = ex2_df[4].value_counts()

#장르1+장르2+장르3+장르4+장르5
장르1.add(장르2, fill_value=0).add(장르3, fill_value=0).add(장르4, fill_value=0).add(장르5, fill_value=0)

Action         7.0
Adventure      5.0
Animation      1.0
Children's     3.0
Comedy         6.0
Crime          3.0
Drama         12.0
Fantasy        2.0
Film-Noir      1.0
Musical        1.0
Mystery        1.0
Romance        4.0
Sci-Fi         4.0
Thriller       5.0
War            6.0
dtype: float64

sr = Series()
for col in ex2_df.columns:
    sr = sr.add(ex2_df[col].value_counts(), fill_value=0)
sr

C:\anaconda\envs\test3\lib\site-packages\ipykernel_launcher.py:1: DeprecationWarning: The default dtype for empty Series will be 'object' instead of 'float64' in a future version. Specify a dtype explicitly to silence this warning.
  """Entry point for launching an IPython kernel.





Action         7.0
Adventure      5.0
Animation      1.0
Children's     3.0
Comedy         6.0
Crime          3.0
Drama         12.0
Fantasy        2.0
Film-Noir      1.0
Musical        1.0
Mystery        1.0
Romance        4.0
Sci-Fi         4.0
Thriller       5.0
War            6.0
dtype: float64

sr.sort_values(ascending=False)

Drama         12.0
Action         7.0
Comedy         6.0
War            6.0
Adventure      5.0
Thriller       5.0
Romance        4.0
Sci-Fi         4.0
Children's     3.0
Crime          3.0
Fantasy        2.0
Animation      1.0
Film-Noir      1.0
Musical        1.0
Mystery        1.0
dtype: float64

[실습 #3] 남자와 여자의 호불호가 크게 갈리는 영화 10개 찾기

전체 평점의 개수가 500개 이상인 영화만 대상으로 함.

data_f = data[data['성별']=='F']
data_f

	사용자아이디	성별	연령	직업	지역	영화아이디	평점	타임스탬프	영화제목	장르
0	1	F	1	10	48067	1193	5	978300760	One Flew Over the Cuckoo's Nest (1975)	Drama
5	18	F	18	3	95825	1193	4	978156168	One Flew Over the Cuckoo's Nest (1975)	Drama
7	24	F	25	7	10023	1193	5	978136709	One Flew Over the Cuckoo's Nest (1975)	Drama
8	28	F	25	1	14607	1193	3	978125194	One Flew Over the Cuckoo's Nest (1975)	Drama
19	59	F	50	1	55413	1193	4	977934292	One Flew Over the Cuckoo's Nest (1975)	Drama
...	...	...	...	...	...	...	...	...	...	...
1000199	5334	F	56	13	46140	3382	5	960796159	Song of Freedom (1936)	Drama
1000200	5420	F	1	19	14850	1843	3	960156505	Slappy and the Stinkers (1998)	Children's|Comedy
1000201	5433	F	35	17	45014	286	3	960240881	Nemesis 2: Nebula (1995)	Action|Sci-Fi|Thriller
1000202	5494	F	35	17	94306	3530	4	959816296	Smoking/No Smoking (1993)	Comedy
1000207	5851	F	18	20	55410	3607	5	957756608	One Little Indian (1973)	Comedy|Drama|Western

246440 rows × 10 columns

여성평점 = data_f.pivot_table(index='영화제목', aggfunc=['mean','count'], values='평점')
여성평점.columns=['평점평균_f','평점개수_f']
여성평점 = 여성평점[여성평점.평점개수_f >=500]
여성평점

	평점평균_f	평점개수_f
영화제목
American Beauty (1999)	4.238901	946
Babe (1995)	3.953368	579
Back to the Future (1985)	3.932707	639
Being John Malkovich (1999)	4.159930	569
Braveheart (1995)	4.016484	546
Casablanca (1942)	4.300990	505
E.T. the Extra-Terrestrial (1982)	4.089850	601
Fargo (1996)	4.217656	657
Forrest Gump (1994)	4.045031	644
Ghostbusters (1984)	3.833962	530
Groundhog Day (1993)	3.735562	658
Jurassic Park (1993)	3.579407	573
L.A. Confidential (1997)	4.106007	566
Matrix, The (1999)	4.128405	514
Men in Black (1997)	3.817844	538
Princess Bride, The (1987)	4.342767	636
Pulp Fiction (1994)	4.071956	542
Raiders of the Lost Ark (1981)	4.332168	572
Saving Private Ryan (1998)	4.114783	575
Schindler's List (1993)	4.562602	615
Shakespeare in Love (1998)	4.181704	798
Shawshank Redemption, The (1994)	4.539075	627
Silence of the Lambs, The (1991)	4.271955	706
Sixth Sense, The (1999)	4.477410	664
Star Wars: Episode IV - A New Hope (1977)	4.302937	647
Star Wars: Episode V - The Empire Strikes Back (1980)	4.106481	648
Star Wars: Episode VI - Return of the Jedi (1983)	3.865237	653
Toy Story (1995)	4.187817	591
Wizard of Oz, The (1939)	4.355030	507

data_m = data[data['성별']=='M']
data_m

	사용자아이디	성별	연령	직업	지역	영화아이디	평점	타임스탬프	영화제목	장르
1	2	M	56	16	70072	1193	5	978298413	One Flew Over the Cuckoo's Nest (1975)	Drama
2	12	M	25	12	32793	1193	4	978220179	One Flew Over the Cuckoo's Nest (1975)	Drama
3	15	M	25	7	22903	1193	4	978199279	One Flew Over the Cuckoo's Nest (1975)	Drama
4	17	M	50	1	95350	1193	5	978158471	One Flew Over the Cuckoo's Nest (1975)	Drama
6	19	M	1	10	48073	1193	5	982730936	One Flew Over the Cuckoo's Nest (1975)	Drama
...	...	...	...	...	...	...	...	...	...	...
1000203	5556	M	45	6	92103	2198	3	959445515	Modulations (1998)	Documentary
1000204	5949	M	18	17	47901	2198	5	958846401	Modulations (1998)	Documentary
1000205	5675	M	35	14	30030	2703	3	976029116	Broken Vessels (1998)	Drama
1000206	5780	M	18	17	92886	2845	1	958153068	White Boys (1999)	Drama
1000208	5938	M	25	1	35401	2909	4	957273353	Five Wives, Three Secretaries and Me (1998)	Documentary

753769 rows × 10 columns

남성평점 = data_m.pivot_table(index='영화제목', aggfunc=['mean','count'], values='평점')
남성평점.columns=['평점평균_m','평점개수_m']
남성평점 = 남성평점[남성평점.평점개수_m >=500]
남성평점

	평점평균_m	평점개수_m
영화제목
13th Warrior, The (1999)	3.168000	625
2001: A Space Odyssey (1968)	4.129738	1372
Abyss, The (1989)	3.689507	1401
Ace Ventura: Pet Detective (1994)	3.197917	576
Addams Family, The (1991)	3.163498	526
...	...	...
Wrong Trousers, The (1993)	4.478261	644
X-Files: Fight the Future, The (1998)	3.493797	806
X-Men (2000)	3.851702	1234
You've Got Mail (1998)	3.275591	508
Young Frankenstein (1974)	4.239177	924

436 rows × 2 columns

여남평점 = pd.concat([여성평점, 남성평점],axis=1)
여남평점['평점차이'] = abs(여남평점['평점평균_f']-여남평점['평점평균_m'])
여남평점.nlargest(10, ('평점차이'))

	평점평균_f	평점개수_f	평점평균_m	평점개수_m	평점차이
영화제목
Groundhog Day (1993)	3.735562	658.0	4.041358	1620	0.305796
Saving Private Ryan (1998)	4.114783	575.0	4.398941	2078	0.284159
Braveheart (1995)	4.016484	546.0	4.297839	1897	0.281355
Pulp Fiction (1994)	4.071956	542.0	4.346839	1629	0.274883
Star Wars: Episode V - The Empire Strikes Back (1980)	4.106481	648.0	4.344577	2342	0.238096
Jurassic Park (1993)	3.579407	573.0	3.814197	2099	0.234791
Matrix, The (1999)	4.128405	514.0	4.362235	2076	0.233830
Star Wars: Episode VI - Return of the Jedi (1983)	3.865237	653.0	4.069058	2230	0.203821
Star Wars: Episode IV - A New Hope (1977)	4.302937	647.0	4.495307	2344	0.192371
Raiders of the Lost Ark (1981)	4.332168	572.0	4.520597	1942	0.188429

ex3 = data.pivot_table(index = '영화제목', columns= '성별',
                      values = '평점', aggfunc = ['mean', 'count'])

ex3 = ex3[ex3[('count','F')]+ex3[('count','M')]>=500]
ex3

	mean		count
성별	F	M	F	M
영화제목
10 Things I Hate About You (1999)	3.646552	3.311966	232.0	468.0
101 Dalmatians (1961)	3.791444	3.500000	187.0	378.0
12 Angry Men (1957)	4.184397	4.328421	141.0	475.0
13th Warrior, The (1999)	3.112000	3.168000	125.0	625.0
20,000 Leagues Under the Sea (1954)	3.670103	3.709205	97.0	478.0
...	...	...	...	...
X-Files: Fight the Future, The (1998)	3.489474	3.493797	190.0	806.0
X-Men (2000)	3.682310	3.851702	277.0	1234.0
You've Got Mail (1998)	3.542424	3.275591	330.0	508.0
Young Frankenstein (1974)	4.289963	4.239177	269.0	924.0
Young Guns (1988)	3.371795	3.425620	78.0	484.0

618 rows × 4 columns

ex3[ex3['count'].sum(axis=1) >= 500]

	mean		count
성별	F	M	F	M
영화제목
10 Things I Hate About You (1999)	3.646552	3.311966	232.0	468.0
101 Dalmatians (1961)	3.791444	3.500000	187.0	378.0
12 Angry Men (1957)	4.184397	4.328421	141.0	475.0
13th Warrior, The (1999)	3.112000	3.168000	125.0	625.0
20,000 Leagues Under the Sea (1954)	3.670103	3.709205	97.0	478.0
...	...	...	...	...
X-Files: Fight the Future, The (1998)	3.489474	3.493797	190.0	806.0
X-Men (2000)	3.682310	3.851702	277.0	1234.0
You've Got Mail (1998)	3.542424	3.275591	330.0	508.0
Young Frankenstein (1974)	4.289963	4.239177	269.0	924.0
Young Guns (1988)	3.371795	3.425620	78.0	484.0

618 rows × 4 columns

abs(ex3[('mean','F')] - ex3[('mean','M')]).nlargest(10)

영화제목
Dirty Dancing (1987)                      0.830782
Good, The Bad and The Ugly, The (1966)    0.726351
Dumb & Dumber (1994)                      0.638608
Evil Dead II (Dead By Dawn) (1987)        0.611985
Grease (1978)                             0.608224
Caddyshack (1980)                         0.573602
Animal House (1978)                       0.538286
Exorcist, The (1973)                      0.529605
Rocky Horror Picture Show, The (1975)     0.512885
Big Trouble in Little China (1986)        0.497078
dtype: float64

[실습 #4] 연령대 별로 영화 평점 분석하기

연령대(10대 미만, 10대, 20대, …50대) 컬럼을 추가한 후, 영화별 연령대별 영화평점 구하기

def generate_ages(x):
    if x<10:
        return '10대 미만'
    elif x<20:
        return '10대'
    elif x<30:
        return '20대'
    elif x<40:
        return '30대'
    elif x<50:
        return '40대'
    elif x<60:
        return '50대 이상'

generate_ages(56)

'50대 이상'

data['연령대'] = data.연령.apply(generate_ages)

data

	사용자아이디	성별	연령	직업	지역	영화아이디	평점	타임스탬프	영화제목	장르	연령대
0	1	F	1	10	48067	1193	5	978300760	One Flew Over the Cuckoo's Nest (1975)	Drama	10대 미만
1	2	M	56	16	70072	1193	5	978298413	One Flew Over the Cuckoo's Nest (1975)	Drama	50대 이상
2	12	M	25	12	32793	1193	4	978220179	One Flew Over the Cuckoo's Nest (1975)	Drama	20대
3	15	M	25	7	22903	1193	4	978199279	One Flew Over the Cuckoo's Nest (1975)	Drama	20대
4	17	M	50	1	95350	1193	5	978158471	One Flew Over the Cuckoo's Nest (1975)	Drama	50대 이상
...	...	...	...	...	...	...	...	...	...	...	...
1000204	5949	M	18	17	47901	2198	5	958846401	Modulations (1998)	Documentary	10대
1000205	5675	M	35	14	30030	2703	3	976029116	Broken Vessels (1998)	Drama	30대
1000206	5780	M	18	17	92886	2845	1	958153068	White Boys (1999)	Drama	10대
1000207	5851	F	18	20	55410	3607	5	957756608	One Little Indian (1973)	Comedy|Drama|Western	10대
1000208	5938	M	25	1	35401	2909	4	957273353	Five Wives, Three Secretaries and Me (1998)	Documentary	20대

1000209 rows × 11 columns

연령평점 = data.pivot_table(index='영화제목', columns='연령대', 
                        aggfunc=['mean'], values='평점')

연령평점

	mean
연령대	10대	10대 미만	20대	30대	40대	50대 이상
영화제목
$1,000,000 Duck (1971)	3.000000	NaN	3.090909	3.133333	2.000000	2.750000
'Night Mother (1986)	4.666667	2.000000	3.423077	2.904762	3.833333	3.750000
'Til There Was You (1997)	2.500000	3.500000	2.666667	2.900000	2.333333	2.600000
'burbs, The (1989)	3.244444	4.500000	2.652174	2.818182	2.545455	3.100000
...And Justice for All (1979)	3.428571	3.000000	3.724138	3.657143	4.100000	3.674419
...	...	...	...	...	...	...
Zed & Two Noughts, A (1985)	3.000000	1.000000	3.375000	3.777778	4.000000	3.000000
Zero Effect (1998)	3.883333	4.125000	3.715278	3.608696	3.764706	3.769231
Zero Kelvin (Kjærlighetens kjøtere) (1995)	NaN	NaN	NaN	3.500000	NaN	NaN
Zeus and Roxanne (1997)	2.500000	1.500000	2.833333	3.500000	1.000000	NaN
eXistenZ (1999)	3.289157	3.142857	3.234973	3.364865	3.222222	3.103448

3706 rows × 6 columns