Project: Netflix Prize Data

Load packages

# numerical calculation & data frames
import numpy as np
import pandas as pd

# visualization
import matplotlib.pyplot as plt
import seaborn as sns
import seaborn.objects as so

# pandas options
pd.set_option('mode.copy_on_write', True)  # pandas 2.0
pd.options.display.float_format = '{:.3f}'.format  # pd.reset_option('display.float_format')
# pd.options.display.max_rows = 7  # max number of rows to display

# NumPy options
np.set_printoptions(precision = 2, suppress=True)  # suppress scientific notation
np.set_printoptions(legacy='1.25')  # numpy 1.25 표현 방식


# matplotlib options
from matplotlib import style
theme_dict = {**style.library['ggplot'], "grid.linestyle": ":", 'axes.facecolor': 'white', 'grid.color': '.6',}
so.Plot.config.theme.update(theme_dict)

# theme_dict = {**sns.axes_style("whitegrid"), "grid.linestyle": ":"}
# so.Plot.config.theme.update(theme_dict)

# For high resolution display
import matplotlib_inline
matplotlib_inline.backend_inline.set_matplotlib_formats("retina")

Cleaned Data

File: netflix_ratings.parquet

netflix = pd.read_parquet("data/netflix_ratings_titles.parquet")

netflix.info()

<class 'pandas.DataFrame'>
RangeIndex: 1246558 entries, 0 to 1246557
Data columns (total 17 columns):
 #   Column        Non-Null Count    Dtype         
---  ------        --------------    -----         
 0   viewer_id     1246558 non-null  Int32         
 1   rating        1246558 non-null  Int8          
 2   watch_date    1246558 non-null  datetime64[ns]
 3   release_year  1246558 non-null  int64         
 4   title         1246558 non-null  str           
 5   record_id     1246558 non-null  str           
 6   media_type    1246558 non-null  str           
 7   director      1245701 non-null  str           
 8   cast          1246558 non-null  str           
 9   country       1246109 non-null  str           
 10  date_added    1246558 non-null  str           
 11  MPAA_rating   1246558 non-null  str           
 12  duration      1246558 non-null  str           
 13  genre         1246558 non-null  object        
 14  description   1246558 non-null  str           
 15  runtime       1245701 non-null  Int32         
 16  num_episodes  857 non-null      Int32         
dtypes: Int32(3), Int8(1), datetime64[ns](1), int64(1), object(1), str(10)
memory usage: 593.3+ MB

netflix.head(3)

	viewer_id	rating	watch_date	release_year	title	record_id	media_type	director	cast	country	date_added	MPAA_rating	duration	genre	description	runtime	num_episodes
0	2191540	4	2004-06-23	2004	50 First Dates	s6019	Movie	Peter Segal	Adam Sandler, Drew Barrymore, Rob Schneider, S...	United States	December 1, 2020	PG-13	99 min	[Comedies, Romantic Movies]	After falling for a pretty art teacher who has...	99	<NA>
1	998702	2	2005-08-26	2002	Men in Black II	s7444	Movie	Barry Sonnenfeld	Tommy Lee Jones, Will Smith, Rip Torn, Lara Fl...	United States	October 1, 2019	PG-13	88 min	[Action & Adventure, Comedies, Sci-Fi & Fantasy]	Will Smith and Tommy Lee Jones reprise their r...	88	<NA>
2	1914163	4	2005-03-21	2004	50 First Dates	s6019	Movie	Peter Segal	Adam Sandler, Drew Barrymore, Rob Schneider, S...	United States	December 1, 2020	PG-13	99 min	[Comedies, Romantic Movies]	After falling for a pretty art teacher who has...	99	<NA>

Data Wrangling

참고서: Python for Data Analysis (3e) by Wes McKinney (파이썬 라이브러리를 활용한 데이터 분석)

대략 다음과 같은 transform들을 조합하여 분석에 필요한 상태로 바꿈

변수들(열)과 관측치(행)를 선택: subsetting
조건에 맞는 부분(관측치, 행)만 필터링: query()
조건에 맞도록 행을 재정렬: sort_values()
변수들과 함수들을 이용하여 새로운 변수를 생성: assign()
카테고리별로 나뉘어진 데이터에 대한 통계치를 생성: groupby(), agg(), apply()

netflix_1990 = (
    netflix
    .loc[:, ["title", "rating", "watch_date", "release_year"]]  # 특정 열을 선택
    .query("release_year >= 1990")                              # 조건에 맞는 행만 필터링
    .assign(                                                    # 새로운 열/변수를 생성
        decade=lambda x: x["release_year"] // 10 * 10,          # 10년 단위
        weekday=lambda x: x["watch_date"].dt.day_name().str[:3] # 요일
    )
    .sort_values("release_year")                                # 조건에 따라 행을 정렬
)
netflix_1990

	title	rating	watch_date	release_year	decade	weekday
406248	Rocky V	3	2004-02-20	1990	1990	Fri
847433	Rocky V	1	2004-02-13	1990	1990	Fri
268823	Rocky V	2	2005-05-18	1990	1990	Wed
...	...	...	...	...	...	...
476261	King's Ransom	2	2005-08-31	2005	2000	Wed
476074	Coach Carter	2	2005-09-14	2005	2000	Wed
109441	The Amityville Horror	3	2005-11-07	2005	2000	Mon

1149195 rows × 6 columns

표시줄 수 지정

# max number of rows to display
pd.options.display.max_rows = 6

# reset
pd.options.display.max_rows = 0

subsetting

변수들(열)과 관측치(행)를 선택

Bracket []
Dot-notation .
iloc, loc

# Bracket [strings]
netflix[["title", "rating"]]

	title	rating
0	50 First Dates	4
1	Men in Black II	2
2	50 First Dates	4
...	...	...
1246555	Bad Boys II	3
1246556	Something's Gotta Give	4
1246557	The American President	5

1246558 rows × 2 columns

# Bracket [slicing]
netflix[:3]

	viewer_id	rating	watch_date	release_year	title	record_id	media_type	director	cast	country	date_added	MPAA_rating	duration	genre	description	runtime	num_episodes
0	2191540	4	2004-06-23	2004	50 First Dates	s6019	Movie	Peter Segal	Adam Sandler, Drew Barrymore, Rob Schneider, S...	United States	December 1, 2020	PG-13	99 min	[Comedies, Romantic Movies]	After falling for a pretty art teacher who has...	99	<NA>
1	998702	2	2005-08-26	2002	Men in Black II	s7444	Movie	Barry Sonnenfeld	Tommy Lee Jones, Will Smith, Rip Torn, Lara Fl...	United States	October 1, 2019	PG-13	88 min	[Action & Adventure, Comedies, Sci-Fi & Fantasy]	Will Smith and Tommy Lee Jones reprise their r...	88	<NA>
2	1914163	4	2005-03-21	2004	50 First Dates	s6019	Movie	Peter Segal	Adam Sandler, Drew Barrymore, Rob Schneider, S...	United States	December 1, 2020	PG-13	99 min	[Comedies, Romantic Movies]	After falling for a pretty art teacher who has...	99	<NA>

# dot-notation
netflix.title

0                  50 First Dates
1                 Men in Black II
2                  50 First Dates
                    ...          
1246555               Bad Boys II
1246556    Something's Gotta Give
1246557    The American President
Name: title, Length: 1246558, dtype: str

# `loc`: label-based indexing
netflix.loc[:, ["title", "rating"]]

	title	rating
0	50 First Dates	4
1	Men in Black II	2
2	50 First Dates	4
...	...	...
1246555	Bad Boys II	3
1246556	Something's Gotta Give	4
1246557	The American President	5

1246558 rows × 2 columns

# `iloc`: position-based indexing
netflix.iloc[100:103, :2]

	viewer_id	rating
100	563447	4
101	2233688	4
102	2174838	2

`query()`

조건에 맞는 부분(관측치, 행)만 필터링

Conditional operators
>, >=, <, <=,
== (equal to), != (not equal to)
and, & (and)
or, | (or)
not, ~ (not)
in (includes), not in (not included)

netflix.query("release_year >= 1990 & release_year < 2000")

	viewer_id	rating	watch_date	release_year	title	record_id	media_type	director	cast	country	date_added	MPAA_rating	duration	genre	description	runtime	num_episodes
3	2041113	3	2003-12-30	1995	Bad Boys	s6212	Movie	Michael Bay	Will Smith, Martin Lawrence, Téa Leoni, Tchéky...	United States	October 1, 2019	R	119 min	[Action & Adventure, Comedies]	In this fast-paced actioner, two Miami narcoti...	119	<NA>
4	948394	4	2005-04-01	1996	Dragonheart	s6642	Movie	Rob Cohen	Sean Connery, Dennis Quaid, David Thewlis, Pet...	United States	January 1, 2020	PG-13	103 min	[Action & Adventure, Sci-Fi & Fantasy]	In ancient times when majestic fire-breathers ...	103	<NA>
8	79898	4	2005-06-24	1999	Superstar	s8131	Movie	Bruce McCulloch	Molly Shannon, Will Ferrell, Elaine Hendrix, H...	United States	November 20, 2019	PG-13	82 min	[Comedies]	A socially awkward Catholic schoolgirl vows to...	82	<NA>
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1246552	1161577	4	2004-06-06	1995	Bad Boys	s6212	Movie	Michael Bay	Will Smith, Martin Lawrence, Téa Leoni, Tchéky...	United States	October 1, 2019	R	119 min	[Action & Adventure, Comedies]	In this fast-paced actioner, two Miami narcoti...	119	<NA>
1246553	26124	3	2005-09-02	1996	The Mirror Has Two Faces	s819	Movie	Barbra Streisand	Barbra Streisand, Jeff Bridges, Lauren Bacall,...	United States	June 2, 2021	PG-13	127 min	[Comedies, Dramas, Romantic Movies]	Tired of being single, middle-aged professor R...	127	<NA>
1246557	811068	5	2004-08-26	1995	The American President	s8188	Movie	Rob Reiner	Michael Douglas, Annette Bening, Martin Sheen,...	United States	January 1, 2021	PG-13	113 min	[Comedies, Dramas, Romantic Movies]	The widowed president strikes up a romance wit...	113	<NA>

428354 rows × 17 columns

netflix.query("rating in [1, 5]")

	viewer_id	rating	watch_date	release_year	title	record_id	media_type	director	cast	country	date_added	MPAA_rating	duration	genre	description	runtime	num_episodes
9	268405	5	2005-11-02	2004	A Cinderella Story	s128	Movie	Mark Rosman	Hilary Duff, Chad Michael Murray, Jennifer Coo...	United States, Canada	September 1, 2021	PG	95 min	[Children & Family Movies, Comedies]	Teen Sam meets the boy of her dreams at a danc...	95	<NA>
15	914520	1	2004-06-14	2003	S.W.A.T.	s7913	Movie	Clark Johnson	Samuel L. Jackson, Colin Farrell, Michelle Rod...	United States	January 1, 2021	PG-13	117 min	[Action & Adventure]	A veteran cop is tasked with drafting and trai...	117	<NA>
18	86305	5	2005-10-24	2005	The Amityville Horror	s8189	Movie	Andrew Douglas	Ryan Reynolds, Melissa George, Chloë Grace Mor...	United States	January 1, 2020	R	89 min	[Horror Movies]	This hair-raising remake of the 1979 horror hi...	89	<NA>
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1246548	2612134	5	2003-12-23	2003	Bad Boys II	s6213	Movie	Michael Bay	Will Smith, Martin Lawrence, Jordi Mollà, Gabr...	United States	October 1, 2019	R	147 min	[Action & Adventure, Comedies]	In this hyperkinetic sequel, a pair of Miami n...	147	<NA>
1246551	340807	5	2003-08-12	1999	American Beauty	s6136	Movie	Sam Mendes	Kevin Spacey, Annette Bening, Thora Birch, Wes...	United States	January 1, 2020	R	122 min	[Dramas]	While struggling to endure his tightly wound w...	122	<NA>
1246557	811068	5	2004-08-26	1995	The American President	s8188	Movie	Rob Reiner	Michael Douglas, Annette Bening, Martin Sheen,...	United States	January 1, 2021	PG-13	113 min	[Comedies, Dramas, Romantic Movies]	The widowed president strikes up a romance wit...	113	<NA>

320750 rows × 17 columns

# title에 game이 포함되어 있는 행만 필터링
netflix.loc[netflix.title.str.contains("Game"), :]  # .str: 문자열 처리

# 동일한 작업을 query()를 이용해 필터링
netflix.query("title.str.contains('Game')")

	viewer_id	rating	watch_date	release_year	title	record_id	media_type	director	cast	country	date_added	MPAA_rating	duration	genre	description	runtime	num_episodes
108	1611338	4	2003-02-27	1997	The Game	s601	Movie	David Fincher	Michael Douglas, Sean Penn, Deborah Kara Unger...	United States	July 1, 2021	R	129 min	[Thrillers]	An aloof investment banker's life spirals into...	129	<NA>
187	2634345	5	2005-06-28	1997	The Game	s601	Movie	David Fincher	Michael Douglas, Sean Penn, Deborah Kara Unger...	United States	July 1, 2021	R	129 min	[Thrillers]	An aloof investment banker's life spirals into...	129	<NA>
245	465580	3	2004-02-09	1997	The Game	s601	Movie	David Fincher	Michael Douglas, Sean Penn, Deborah Kara Unger...	United States	July 1, 2021	R	129 min	[Thrillers]	An aloof investment banker's life spirals into...	129	<NA>
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1246315	715480	4	2005-08-13	1997	The Game	s601	Movie	David Fincher	Michael Douglas, Sean Penn, Deborah Kara Unger...	United States	July 1, 2021	R	129 min	[Thrillers]	An aloof investment banker's life spirals into...	129	<NA>
1246407	2567821	2	2003-05-18	1997	The Game	s601	Movie	David Fincher	Michael Douglas, Sean Penn, Deborah Kara Unger...	United States	July 1, 2021	R	129 min	[Thrillers]	An aloof investment banker's life spirals into...	129	<NA>
1246415	1154697	4	2004-11-17	1997	The Game	s601	Movie	David Fincher	Michael Douglas, Sean Penn, Deborah Kara Unger...	United States	July 1, 2021	R	129 min	[Thrillers]	An aloof investment banker's life spirals into...	129	<NA>

19341 rows × 17 columns

`sort_values()`

조건에 맞도록 행을 재정렬

netflix.sort_values("release_year")  # year에 대해 오름차순 정렬
netflix.sort_values("release_year", ascending=False)  # year에 대해 내림차순 정렬
netflix.sort_values(["release_year", "rating"], ascending=False)  # year 다음 rating에 대해 내림차순 정렬

	viewer_id	rating	watch_date	release_year	title	record_id	media_type	director	cast	country	date_added	MPAA_rating	duration	genre	description	runtime	num_episodes
18	86305	5	2005-10-24	2005	The Amityville Horror	s8189	Movie	Andrew Douglas	Ryan Reynolds, Melissa George, Chloë Grace Mor...	United States	January 1, 2020	R	89 min	[Horror Movies]	This hair-raising remake of the 1979 horror hi...	89	<NA>
31	666338	5	2005-08-19	2005	Coach Carter	s6511	Movie	Thomas Carter	Samuel L. Jackson, Rob Brown, Robert Ri'chard,...	United States, Germany	January 1, 2020	PG-13	137 min	[Dramas, Sports Movies]	Controversial basketball coach Ken Carter puts...	137	<NA>
189	642572	5	2005-07-27	2005	Coach Carter	s6511	Movie	Thomas Carter	Samuel L. Jackson, Rob Brown, Robert Ri'chard,...	United States, Germany	January 1, 2020	PG-13	137 min	[Dramas, Sports Movies]	Controversial basketball coach Ken Carter puts...	137	<NA>
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1230179	2537543	1	2005-12-02	1965	The Cincinnati Kid	s8250	Movie	Norman Jewison	Steve McQueen, Edward G. Robinson, Ann-Margret...	United States	November 1, 2019	TV-14	103 min	[Classic Movies, Dramas]	In Depression-era New Orleans, cocksure stud p...	103	<NA>
1232551	455843	1	2004-01-12	1965	Doctor Zhivago	s6620	Movie	David Lean	Omar Sharif, Julie Christie, Geraldine Chaplin...	United States, Italy, United Kingdom, Liechten...	November 1, 2019	PG-13	200 min	[Classic Movies, Dramas, Romantic Movies]	A young physician and his beautiful mistress g...	200	<NA>
1240585	2185183	1	2005-06-07	1965	Doctor Zhivago	s6620	Movie	David Lean	Omar Sharif, Julie Christie, Geraldine Chaplin...	United States, Italy, United Kingdom, Liechten...	November 1, 2019	PG-13	200 min	[Classic Movies, Dramas, Romantic Movies]	A young physician and his beautiful mistress g...	200	<NA>

1246558 rows × 17 columns

`assign()`

변수들과 함수들을 이용하여 새로운 변수를 생성

가령, 1990년대, 2000년대 등등과 같이 10년 단위로 새로운 값을 생성하려면,

netflix["release_year"]  # pandas Series 객체, 그 값들은 NumPy array

0          2004
1          2002
2          2004
           ... 
1246555    2003
1246556    2003
1246557    1995
Name: release_year, Length: 1246558, dtype: int64

netflix["release_year"] // 10  # NumPy array에 대한 나눗셈(몫) 연산

0          200
1          200
2          200
          ... 
1246555    200
1246556    200
1246557    199
Name: release_year, Length: 1246558, dtype: int64

netflix.assign(
    decade=netflix["release_year"] // 10 * 10, # 10년 단위
)

	viewer_id	rating	watch_date	release_year	title	record_id	media_type	director	cast	country	date_added	MPAA_rating	duration	genre	description	runtime	num_episodes	decade
0	2191540	4	2004-06-23	2004	50 First Dates	s6019	Movie	Peter Segal	Adam Sandler, Drew Barrymore, Rob Schneider, S...	United States	December 1, 2020	PG-13	99 min	[Comedies, Romantic Movies]	After falling for a pretty art teacher who has...	99	<NA>	2000
1	998702	2	2005-08-26	2002	Men in Black II	s7444	Movie	Barry Sonnenfeld	Tommy Lee Jones, Will Smith, Rip Torn, Lara Fl...	United States	October 1, 2019	PG-13	88 min	[Action & Adventure, Comedies, Sci-Fi & Fantasy]	Will Smith and Tommy Lee Jones reprise their r...	88	<NA>	2000
2	1914163	4	2005-03-21	2004	50 First Dates	s6019	Movie	Peter Segal	Adam Sandler, Drew Barrymore, Rob Schneider, S...	United States	December 1, 2020	PG-13	99 min	[Comedies, Romantic Movies]	After falling for a pretty art teacher who has...	99	<NA>	2000
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1246555	1991791	3	2004-01-06	2003	Bad Boys II	s6213	Movie	Michael Bay	Will Smith, Martin Lawrence, Jordi Mollà, Gabr...	United States	October 1, 2019	R	147 min	[Action & Adventure, Comedies]	In this hyperkinetic sequel, a pair of Miami n...	147	<NA>	2000
1246556	925565	4	2005-11-20	2003	Something's Gotta Give	s8056	Movie	Nancy Meyers	Jack Nicholson, Diane Keaton, Keanu Reeves, Fr...	United States	August 1, 2019	PG-13	128 min	[Comedies, Romantic Movies]	Still sexy at 60, Harry Sanborn wines and dine...	128	<NA>	2000
1246557	811068	5	2004-08-26	1995	The American President	s8188	Movie	Rob Reiner	Michael Douglas, Annette Bening, Martin Sheen,...	United States	January 1, 2021	PG-13	113 min	[Comedies, Dramas, Romantic Movies]	The widowed president strikes up a romance wit...	113	<NA>	1990

1246558 rows × 18 columns

# lambda를 이용한 값 생성
netflix.assign(
    decade=lambda x: x["release_year"] // 10 * 10, # 10년 단위
    weekday=lambda x: x["watch_date"].dt.day_name().str[:3] # 요일
)

	viewer_id	rating	watch_date	release_year	title	record_id	media_type	director	cast	country	date_added	MPAA_rating	duration	genre	description	runtime	num_episodes	decade	weekday
0	2191540	4	2004-06-23	2004	50 First Dates	s6019	Movie	Peter Segal	Adam Sandler, Drew Barrymore, Rob Schneider, S...	United States	December 1, 2020	PG-13	99 min	[Comedies, Romantic Movies]	After falling for a pretty art teacher who has...	99	<NA>	2000	Wed
1	998702	2	2005-08-26	2002	Men in Black II	s7444	Movie	Barry Sonnenfeld	Tommy Lee Jones, Will Smith, Rip Torn, Lara Fl...	United States	October 1, 2019	PG-13	88 min	[Action & Adventure, Comedies, Sci-Fi & Fantasy]	Will Smith and Tommy Lee Jones reprise their r...	88	<NA>	2000	Fri
2	1914163	4	2005-03-21	2004	50 First Dates	s6019	Movie	Peter Segal	Adam Sandler, Drew Barrymore, Rob Schneider, S...	United States	December 1, 2020	PG-13	99 min	[Comedies, Romantic Movies]	After falling for a pretty art teacher who has...	99	<NA>	2000	Mon
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1246555	1991791	3	2004-01-06	2003	Bad Boys II	s6213	Movie	Michael Bay	Will Smith, Martin Lawrence, Jordi Mollà, Gabr...	United States	October 1, 2019	R	147 min	[Action & Adventure, Comedies]	In this hyperkinetic sequel, a pair of Miami n...	147	<NA>	2000	Tue
1246556	925565	4	2005-11-20	2003	Something's Gotta Give	s8056	Movie	Nancy Meyers	Jack Nicholson, Diane Keaton, Keanu Reeves, Fr...	United States	August 1, 2019	PG-13	128 min	[Comedies, Romantic Movies]	Still sexy at 60, Harry Sanborn wines and dine...	128	<NA>	2000	Sun
1246557	811068	5	2004-08-26	1995	The American President	s8188	Movie	Rob Reiner	Michael Douglas, Annette Bening, Martin Sheen,...	United States	January 1, 2021	PG-13	113 min	[Comedies, Dramas, Romantic Movies]	The widowed president strikes up a romance wit...	113	<NA>	1990	Thu

1246558 rows × 19 columns

`groupby()`, `agg()`, `apply()`

카테고리별로 나뉘어진 데이터에 대한 통계치를 생성

groupby()는 데이터를 의미있는 그룹으로 나누어 분석할 수 있도록 해줌
.count(), .sum(), .mean(), .min(), .max()과 같은 통계치를 구하는 methods와 함께 효과적으로 자주 활용됨

아래 표는 groupby()와 함께 자주 쓰이는 효율적인 methods

Source: Ch.10 in Python for Data Analysis (3e) by Wes McKinney

netflix.columns

Index(['viewer_id', 'rating', 'watch_date', 'release_year', 'title',
       'record_id', 'media_type', 'director', 'cast', 'country', 'date_added',
       'MPAA_rating', 'duration', 'genre', 'description', 'runtime',
       'num_episodes'],
      dtype='str')

netflix.groupby("title")["rating"].mean()

title
50 First Dates                 3.752
A Cinderella Story             3.625
About a Boy                    3.589
                                ... 
Training Day                   3.571
Tremors 4: The Legend Begins   3.043
Under Siege                    3.313
Name: rating, Length: 94, dtype: Float64

netflix.groupby("viewer_id")["rating"].agg(["mean", "std"])

	mean	std
viewer_id
6	3.250	1.035
7	4.071	1.141
8	4.000	<NA>
...	...	...
2649409	4.000	<NA>
2649426	4.000	0.000
2649429	4.833	0.408

316804 rows × 2 columns

def min_max(x):
    return pd.Series([x.min(), x.max()], index=["min", "max"])  # Series를 반환

netflix.groupby("title")["rating"].apply(min_max)

title                            
50 First Dates                min    1
                              max    5
A Cinderella Story            min    1
                                    ..
Tremors 4: The Legend Begins  max    5
Under Siege                   min    1
                              max    5
Name: rating, Length: 188, dtype: int8

def standardize_by_user(x):
    return (x - x.mean()) / x.std()

(
    netflix
    .groupby("viewer_id")["rating"]
    .apply(standardize_by_user)
    .reset_index(level=0)
)

	viewer_id	rating
422187	6	0.725
723559	6	-0.242
726864	6	0.725
...	...	...
1009754	2649429	0.408
1132274	2649429	0.408
1228870	2649429	0.408

1246558 rows × 2 columns

Exploratory Data Analysis (EDA)

평점 분포

mean_ratings = (
    netflix
    .groupby("title")["rating"]
    .agg(["mean", "std", "count"])
    .reset_index()
)
mean_ratings

	title	mean	std	count
0	50 First Dates	3.752	1.002	72913
1	A Cinderella Story	3.625	1.036	17594
2	About a Boy	3.589	0.952	36596
...	...	...	...	...
91	Training Day	3.571	0.989	36707
92	Tremors 4: The Legend Begins	3.043	1.194	947
93	Under Siege	3.313	1.019	14769

94 rows × 4 columns

mean_ratings.sort_values("mean", ascending=False)

	title	mean	std	count
43	Kabhi Khushi Kabhie Gham	4.237	1.008	97
86	The Pianist	4.116	0.901	30497
18	Coach Carter	4.071	0.891	30022
...	...	...	...	...
80	The Flintstones	2.441	1.045	5203
40	Jeans	2.269	1.023	93
14	Boom	1.882	1.107	51

94 rows × 4 columns

(
    so.Plot(mean_ratings, x="mean", y="std")
    .add(so.Dots(alpha=.5), pointsize="count")
    .add(so.Line(), so.PolyFit(5))
    .scale(pointsize=(3, 20))
    .layout(size=(8, 7))
)

netflix2 = (
    netflix
    .assign(
        decade=lambda x: x["release_year"] // 10 * 10,  # 10년 단위
        weekday=lambda x: x["watch_date"].dt.day_name().str[:3],
        weekend=lambda x: x["weekday"].isin(["Sat", "Sun"]),
        title_length=lambda x: x["title"].str.len()
    )
)

netflix2["weekday"] = netflix2["weekday"].astype("category").cat.set_categories(["Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"])

netflix2.head()

	viewer_id	rating	watch_date	release_year	title	record_id	media_type	director	cast	country	...	MPAA_rating	duration	genre	description	runtime	num_episodes	decade	weekday	weekend	title_length
0	2191540	4	2004-06-23	2004	50 First Dates	s6019	Movie	Peter Segal	Adam Sandler, Drew Barrymore, Rob Schneider, S...	United States	...	PG-13	99 min	[Comedies, Romantic Movies]	After falling for a pretty art teacher who has...	99	<NA>	2000	Wed	False	14
1	998702	2	2005-08-26	2002	Men in Black II	s7444	Movie	Barry Sonnenfeld	Tommy Lee Jones, Will Smith, Rip Torn, Lara Fl...	United States	...	PG-13	88 min	[Action & Adventure, Comedies, Sci-Fi & Fantasy]	Will Smith and Tommy Lee Jones reprise their r...	88	<NA>	2000	Fri	False	15
2	1914163	4	2005-03-21	2004	50 First Dates	s6019	Movie	Peter Segal	Adam Sandler, Drew Barrymore, Rob Schneider, S...	United States	...	PG-13	99 min	[Comedies, Romantic Movies]	After falling for a pretty art teacher who has...	99	<NA>	2000	Mon	False	14
3	2041113	3	2003-12-30	1995	Bad Boys	s6212	Movie	Michael Bay	Will Smith, Martin Lawrence, Téa Leoni, Tchéky...	United States	...	R	119 min	[Action & Adventure, Comedies]	In this fast-paced actioner, two Miami narcoti...	119	<NA>	1990	Tue	False	8
4	948394	4	2005-04-01	1996	Dragonheart	s6642	Movie	Rob Cohen	Sean Connery, Dennis Quaid, David Thewlis, Pet...	United States	...	PG-13	103 min	[Action & Adventure, Sci-Fi & Fantasy]	In ancient times when majestic fire-breathers ...	103	<NA>	1990	Fri	False	11

5 rows × 21 columns

mean_ratings_by_wday = (
    netflix2
    .groupby(["weekday"])["rating"]
    .agg(["mean", "std", "count"])
    .reset_index()
)
mean_ratings_by_wday

	weekday	mean	std	count
0	Mon	3.587	1.060	214181
1	Tue	3.581	1.060	221189
2	Wed	3.593	1.061	206516
...	...	...	...	...
4	Fri	3.581	1.070	167458
5	Sat	3.586	1.075	123017
6	Sun	3.590	1.072	133268

7 rows × 4 columns

요일별 평점

(
    so.Plot(mean_ratings_by_wday, x="weekday", y="mean")
    .add(so.Dot(), pointsize="count")
)

제목의 길이?

(
    so.Plot(netflix2, x="title_length", y="rating")
    .add(so.Dot(), so.Agg("mean"))
)

시청자별 분석

viewing_count = netflix.groupby("viewer_id")["rating"].size()
viewing_count

viewer_id
6           8
7          14
8           1
           ..
2649409     1
2649426     4
2649429     6
Name: rating, Length: 316804, dtype: Int64

# pandas의 method를 사용한 시각화
viewing_count.hist(bins=100);

viewing_count_df = viewing_count.reset_index(name="count")
(
    so.Plot(viewing_count_df, x="count")
    .add(so.Bars(), so.Hist(bins=50))
    .limit(y=(0, 100))
)

user_stats = (
    netflix
    .groupby("viewer_id")["rating"]
    .agg(["mean", "std", "count"])
)
user_stats

	mean	std	count
viewer_id
6	3.250	1.035	8
7	4.071	1.141	14
8	4.000	<NA>	1
...	...	...	...
2649409	4.000	<NA>	1
2649426	4.000	0.000	4
2649429	4.833	0.408	6

316804 rows × 3 columns

user_stat_30 = user_stats.query("count >= 30")
user_stat_30

	mean	std	count
viewer_id
57633	2.176	1.314	34
110938	3.781	0.941	32
147386	3.667	0.711	30
...	...	...	...
2606799	3.237	1.515	38
2625420	2.419	0.923	31
2626336	2.516	1.235	31

78 rows × 3 columns

(
    so.Plot(user_stat_30, x="mean", y="std")
    .add(so.Dot(alpha=.5))
    .add(so.Line(color=".5"), so.PolyFit(5))
    .layout(size=(8, 7))
)

장르별 분석

netflix["genre"]

0                               [Comedies, Romantic Movies]
1          [Action & Adventure, Comedies, Sci-Fi & Fantasy]
2                               [Comedies, Romantic Movies]
                                 ...                       
1246555                      [Action & Adventure, Comedies]
1246556                         [Comedies, Romantic Movies]
1246557                 [Comedies, Dramas, Romantic Movies]
Name: genre, Length: 1246558, dtype: object

netflix_long = netflix.explode('genre')

netflix_long

	viewer_id	rating	watch_date	release_year	title	record_id	media_type	director	cast	country	date_added	MPAA_rating	duration	genre	description	runtime	num_episodes
0	2191540	4	2004-06-23	2004	50 First Dates	s6019	Movie	Peter Segal	Adam Sandler, Drew Barrymore, Rob Schneider, S...	United States	December 1, 2020	PG-13	99 min	Comedies	After falling for a pretty art teacher who has...	99	<NA>
0	2191540	4	2004-06-23	2004	50 First Dates	s6019	Movie	Peter Segal	Adam Sandler, Drew Barrymore, Rob Schneider, S...	United States	December 1, 2020	PG-13	99 min	Romantic Movies	After falling for a pretty art teacher who has...	99	<NA>
1	998702	2	2005-08-26	2002	Men in Black II	s7444	Movie	Barry Sonnenfeld	Tommy Lee Jones, Will Smith, Rip Torn, Lara Fl...	United States	October 1, 2019	PG-13	88 min	Action & Adventure	Will Smith and Tommy Lee Jones reprise their r...	88	<NA>
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1246557	811068	5	2004-08-26	1995	The American President	s8188	Movie	Rob Reiner	Michael Douglas, Annette Bening, Martin Sheen,...	United States	January 1, 2021	PG-13	113 min	Comedies	The widowed president strikes up a romance wit...	113	<NA>
1246557	811068	5	2004-08-26	1995	The American President	s8188	Movie	Rob Reiner	Michael Douglas, Annette Bening, Martin Sheen,...	United States	January 1, 2021	PG-13	113 min	Dramas	The widowed president strikes up a romance wit...	113	<NA>
1246557	811068	5	2004-08-26	1995	The American President	s8188	Movie	Rob Reiner	Michael Douglas, Annette Bening, Martin Sheen,...	United States	January 1, 2021	PG-13	113 min	Romantic Movies	The widowed president strikes up a romance wit...	113	<NA>

2515217 rows × 17 columns

(
    so.Plot(netflix_long, y="genre")  # y에 genre가 나오도록!
    .add(so.Bar(), so.Hist("proportion"))
)

genre_mean = (
    netflix_long
    .groupby('genre')['rating']
    .agg(['mean', 'std', 'count'])
    .reset_index()
)
genre_mean

	genre	mean	std	count
0	Action & Adventure	3.518	1.074	466348
1	Anime Series	3.627	1.361	126
2	Children & Family Movies	3.319	1.098	106728
...	...	...	...	...
15	Sports Movies	3.819	1.032	49586
16	TV Dramas	3.765	1.167	731
17	Thrillers	3.551	0.998	133365

18 rows × 4 columns

genre_mean.nlargest(3, "mean")

	genre	mean	std	count
9	Independent Movies	3.907	0.993	70433
15	Sports Movies	3.819	1.032	49586
10	International Movies	3.809	0.971	107332

order_by_mean = genre_mean.sort_values("mean", ascending=False)["genre"].values

(
    so.Plot(genre_mean, y="genre", x="mean")
    .add(so.Bar())
    .scale(y=so.Nominal(order=order_by_mean))  # 그래프에 순서 부여
    .limit(x=(3, 4.1))
)

(
    so.Plot(genre_mean, y="genre", x="std")
    .add(so.Bar())
    .scale(y=so.Nominal(order=order_by_mean))  # 그래프에 순서 부여
    .limit(x=(.9, 1.4))
)

netflix_long["weekday"] = netflix_long["watch_date"].dt.day_name().str[:3]
netflix_long["weekday"] = netflix_long["weekday"].astype("category").cat.set_categories(["Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"])

genre_mean_by_weekday = (
    netflix_long
    .groupby(['genre', 'weekday'], observed=True)['rating']
    .agg(['mean', 'std', 'count'])
    .reset_index()
)
genre_mean_by_weekday

	genre	weekday	mean	std	count
0	Action & Adventure	Mon	3.517	1.072	80952
1	Action & Adventure	Tue	3.506	1.067	82126
2	Action & Adventure	Wed	3.527	1.071	76901
...	...	...	...	...	...
123	Thrillers	Fri	3.536	1.008	18130
124	Thrillers	Sat	3.561	1.014	13853
125	Thrillers	Sun	3.559	0.994	14223

126 rows × 5 columns

order_by_mean = genre_mean.sort_values("mean", ascending=False)["genre"].values

(
    so.Plot(genre_mean_by_weekday, y="genre", x="mean", color="weekday")
    .add(so.Bar(), so.Dodge())
    .scale(y=so.Nominal(order=order_by_mean))  # 그래프에 순서 부여
    # .facet("weekday")
    .limit(x=(3.3, 4.1))
    .layout(size=(9, 9))
)

mean_ratings_by_genre = (
    netflix_long
    .groupby(["title", "genre"])["rating"]
    .agg(["mean", "std", "count"])
    .reset_index()
)
mean_ratings_by_genre

	title	genre	mean	std	count
0	50 First Dates	Comedies	3.752	1.002	72913
1	50 First Dates	Romantic Movies	3.752	1.002	72913
2	A Cinderella Story	Children & Family Movies	3.625	1.036	17594
...	...	...	...	...	...
206	Tremors 4: The Legend Begins	Horror Movies	3.043	1.194	947
207	Tremors 4: The Legend Begins	Sci-Fi & Fantasy	3.043	1.194	947
208	Under Siege	Action & Adventure	3.313	1.019	14769

209 rows × 5 columns

(
    so.Plot(mean_ratings_by_genre, x="mean", y="std")
    .add(so.Dots(alpha=.5), pointsize="count")
    .add(so.Line(color=".3"), so.PolyFit(1))
    .facet("genre", wrap=4)
    .share(y=False)
    .scale(pointsize=(3, 20))
    .layout(size=(9, 13))
)

출시년도

netflix.head(3)

	viewer_id	rating	watch_date	release_year	title	record_id	media_type	director	cast	country	date_added	MPAA_rating	duration	genre	description	runtime	num_episodes
0	2191540	4	2004-06-23	2004	50 First Dates	s6019	Movie	Peter Segal	Adam Sandler, Drew Barrymore, Rob Schneider, S...	United States	December 1, 2020	PG-13	99 min	[Comedies, Romantic Movies]	After falling for a pretty art teacher who has...	99	<NA>
1	998702	2	2005-08-26	2002	Men in Black II	s7444	Movie	Barry Sonnenfeld	Tommy Lee Jones, Will Smith, Rip Torn, Lara Fl...	United States	October 1, 2019	PG-13	88 min	[Action & Adventure, Comedies, Sci-Fi & Fantasy]	Will Smith and Tommy Lee Jones reprise their r...	88	<NA>
2	1914163	4	2005-03-21	2004	50 First Dates	s6019	Movie	Peter Segal	Adam Sandler, Drew Barrymore, Rob Schneider, S...	United States	December 1, 2020	PG-13	99 min	[Comedies, Romantic Movies]	After falling for a pretty art teacher who has...	99	<NA>

netflix.groupby(["release_year", "title"])["rating"].agg(["mean", "count"])

		mean	count
release_year	title
1965	Doctor Zhivago	3.976	8810
1965	The Cincinnati Kid	3.651	501
1968	Rosemary's Baby	3.608	16421
...	...	...	...
2005	King's Ransom	2.958	4040
	Paheli	3.452	31
	The Amityville Horror	3.484	9896

94 rows × 2 columns

(
    so.Plot(netflix, x="release_year", y="rating")
    .add(so.Line(marker="."), so.Agg("mean"))
)

# 10년 단위로 
netflix["decade"] = netflix["release_year"] // 10 * 10
(
    so.Plot(netflix, x="decade", y="rating")
    .add(so.Line(marker="."), so.Agg("mean"))
)

Project-Native 구현

netflix = pd.read_parquet("data/netflix_ratings_titles.parquet")

기본통계

총 시청 기록 수: 1246558개
총 시청자 수: 316804명
고유 작품 수: 94개
총 시청 시간: 2391943.3시간
전체 평균 평점: 3.59/10

# 총 시청 기록 수
netflix.shape

(1246558, 17)

# 총 시청자 수
netflix["viewer_id"].nunique()

# 고유 작품 수
netflix["title"].nunique()

# 총 시청 시간
netflix["runtime"].sum() / 60

2391943.316666667

# 전체 평균 평점: 3.59/10
netflix["rating"].mean()

3.58698833106843

def get_basic_stats(db):
    return {
        "총 시청 기록수": db.shape[0],
        "총 시청자 수": db["viewer_id"].nunique(),
        "고유 작품 수": db["title"].nunique(),
        "총 시청 시간": db["runtime"].sum() / 60,
        "전체 평균 평점": db["rating"].mean()
    }

get_basic_stats(netflix)

{'총 시청 기록수': 1246558,
 '총 시청자 수': 316804,
 '고유 작품 수': 94,
 '총 시청 시간': 2391943.316666667,
 '전체 평균 평점': 3.58698833106843}

NumPy 스칼라값 표현 예전 방식으로 수정

np.set_printoptions(legacy='1.25')

시청자 분석

가장 활발한 시청자 TOP 5

387418: 45회 시청
305344: 43회 시청
1664010: 43회 시청
2439493: 40회 시청
2606799: 38회 시청

# 가장 활발한 시청자 TOP 5
netflix.value_counts("viewer_id")[:5].reset_index(name="count")

	viewer_id	count
0	387418	45
1	305344	43
2	1664010	43
3	2439493	40
4	2606799	38

시청자별 통계

[6] 시청 횟수: 8회 평균 평점: 3.25/10

[7] 시청 횟수: 14회 평균 평점: 4.07/10

[8] 시청 횟수: 1회 평균 평점: 4.00/10

[10] 시청 횟수: 1회 평균 평점: 4.00/10

[59] 시청 횟수: 1회 평균 평점: 4.00/10

# 시청자별 통계
user_stats = netflix.groupby("viewer_id")["rating"].agg(["mean", "std", "count"])
user_stats[:5]  # 처음 5개 레코드만 표시

	mean	std	count
viewer_id
6	3.250	1.035	8
7	4.071	1.141	14
8	4.000	<NA>	1
10	4.000	<NA>	1
59	4.000	<NA>	1

작품별 분석

평균 평점 TOP 10 작품 (최소 3명 이상 평가)

Kabhi Khushi Kabhie Gham
평균 평점: 4.24/10 (97명 평가)
The Pianist
평균 평점: 4.12/10 (30497명 평가)
Coach Carter
평균 평점: 4.07/10 (30022명 평가)
Kuch Kuch Hota Hai
평균 평점: 4.00/10 (271명 평가)
Doctor Zhivago
평균 평점: 3.98/10 (8810명 평가)
Like Water for Chocolate
평균 평점: 3.97/10 (13459명 평가)
American Beauty
평균 평점: 3.96/10 (77407명 평가)
Lock, Stock and Two Smoking Barrels 평균 평점: 3.93/10 (19899명 평가)
Charlotte’s Web
평균 평점: 3.92/10 (13693명 평가)
Jaws
평균 평점: 3.88/10 (40425명 평가)

# 평균 평점 TOP 10 작품 (최소 3명 이상 평가)
def get_top_rated_media(n=10, min_ratings=3):
    return (
        netflix
        .groupby("title")["rating"]
        .agg(["mean", "count"])
        .query("count >= @min_ratings")
        .nlargest(n, "mean")
    )

get_top_rated_media()

	mean	count
title
Kabhi Khushi Kabhie Gham	4.237	97
The Pianist	4.116	30497
Coach Carter	4.071	30022
...	...	...
Lock, Stock and Two Smoking Barrels	3.933	19899
Charlotte's Web	3.917	13693
Jaws	3.880	40425

10 rows × 2 columns

장르 분석

장르별 통계

Comedies: 시청 횟수: 606749회 평균 평점: 3.51/10 시청자 수: 243514명 총 시청 시간: 1083382.5시간

Action & Adventure: 시청 횟수: 466348회 평균 평점: 3.52/10 시청자 수: 217876명 총 시청 시간: 912268.1시간

Dramas: 시청 횟수: 428928회 평균 평점: 3.75/10 시청자 수: 200592명 총 시청 시간: 874892.6시간

…

# 장르별 통계: 시청 횟수, 평균 평점, 시청자 수, 총 시청시간

netflix_long = netflix.explode('genre')

genre_stats = (
    netflix_long.groupby("genre")
    .agg(
        count=("rating", "size"),
        mean_rating=("rating", "mean"),
        total_viewers=("viewer_id", "nunique"),  # nunique(): 고유 값 개수 함수
        total_runtime=("runtime", "sum"),
    )
    .assign(
        total_runtime=lambda x: x["total_runtime"] / 60
    )
    .reset_index()
)
genre_stats

	genre	count	mean_rating	total_viewers	total_runtime
0	Action & Adventure	466348	3.518	217876	912268.133
1	Anime Series	126	3.627	126	0.000
2	Children & Family Movies	106728	3.319	69248	163799.883
...	...	...	...	...	...
15	Sports Movies	49586	3.819	45149	104607.100
16	TV Dramas	731	3.765	731	0.000
17	Thrillers	133365	3.551	89527	271388.767

18 rows × 5 columns

# 장르 분포 시각화: 시청 횟수
order_by_count = genre_stats.sort_values("count", ascending=False)["genre"].values
(
    so.Plot(genre_stats, y="genre", x="count")
    .add(so.Bar())
    .scale(y=so.Nominal(order=order_by_count))
)

시간대 분석

월별 시청 추이

1999-11 1회
1999-12 30회
2000-01 1009회
2000-02 1089회
2000-03 916회

netflix = netflix.assign(
    year_month=lambda x: x["watch_date"].dt.to_period("M")
)

# 월별 시청 추이
netflix.value_counts("year_month").sort_index()

year_month
1999-11        1
1999-12       30
2000-01     1009
           ...  
2005-10    65141
2005-11    38613
2005-12    21827
Freq: M, Name: count, Length: 74, dtype: int64

viewing_by_month = netflix.value_counts("year_month").sort_index().reset_index()

(
    so.Plot(viewing_by_month, x="count", y="year_month")
    .add(so.Bars())
    .layout(size=(6, 10))
)

# 시각화: seaborn에서 직접 계산하여 그리기
(
    so.Plot(netflix, y="year_month")
    .add(so.Bars(), so.Hist())
    .layout(size=(6, 10))
)

# 요일별 시청 패턴
netflix = netflix.assign(
    weekday=lambda x: x["watch_date"].dt.day_name().str[:3] # 요일
)

netflix["weekday"] = netflix["weekday"].astype("category").cat.set_categories(["Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"]) # 요일 순서 지정을 위해 카테고리 변환

netflix.value_counts("weekday").sort_index()

weekday
Mon    214181
Tue    221189
Wed    206516
        ...  
Fri    167458
Sat    123017
Sun    133268
Name: count, Length: 7, dtype: int64

# 요일별 시청 패턴 시각화
(
    so.Plot(netflix, y="weekday")
    .add(so.Bars(), so.Hist())
)

평점 분석

전체 평점 분포

5점: 266619개
4점: 433481개
3점: 365585개
2점: 126742개
1점: 54131개

# 전체 평점 분포
netflix.value_counts("rating").sort_index()

rating
1     54131
2    126742
3    365585
4    433481
5    266619
Name: count, dtype: int64

# 시각화
(
    so.Plot(netflix, y="rating")
    .add(so.Bar(), so.Hist(discrete=True))
)

종합 리포트

시청 기록 종합 리포트

총 시청 기록 수: 1246558개
총 시청자 수: 316804명
고유 작품 수: 94개
총 시청 시간: 2391943.3시간
전체 평균 평점: 3.59/10

가장 인기 있는 장르: Comedies

평균 평점이 가장 높은 TOP 3 작품:

Kabhi Khushi Kabhie Gham (평균: 4.24/10, 97명 평가)
The Pianist (평균: 4.12/10, 30497명 평가)
Coach Carter (평균: 4.07/10, 30022명 평가)

def get_summary_report(db):
    return {
        "총 시청 기록 수": db.shape[0],
        "총 시청자 수": db["viewer_id"].nunique(),
        "고유 작품 수": db["title"].nunique(),
        "총 시청 시간": db["runtime"].sum() / 60,
        "전체 평균 평점": db["rating"].mean(),
        "가장 인기 있는 장르": genre_stats.set_index("genre")["count"].idxmax(),
        "평균 평점이 가장 높은 TOP 3 작품": get_top_rated_media(3, 3).reset_index().to_dict(orient="records")
    }

get_summary_report(netflix)

{'총 시청 기록 수': 1246558,
 '총 시청자 수': 316804,
 '고유 작품 수': 94,
 '총 시청 시간': 2391943.316666667,
 '전체 평균 평점': 3.58698833106843,
 '가장 인기 있는 장르': 'Comedies',
 '평균 평점이 가장 높은 TOP 3 작품': [{'title': 'Kabhi Khushi Kabhie Gham',
   'mean': 4.237113402061856,
   'count': 97},
  {'title': 'The Pianist', 'mean': 4.116142571400466, 'count': 30497},
  {'title': 'Coach Carter', 'mean': 4.070748118046765, 'count': 30022}]}

Module로 변환/활용

반복되는 분석 패턴을 netflix_utils.py 모듈로 분리하면, 코드 재사용성과 가독성이 높아집니다.

import netflix_utils as nu

import netflix_utils as nu

# 데이터 로딩 및 환경 설정
nu.setup_display(max_rows=6)
netflix = nu.load_netflix_data("data/netflix_ratings.parquet")
netflix.head(3)

	movie_id	user_id	rating	date	title	genre	year
0	3282	972104	4	2005-09-16	Sideways	[Comedy, Drama, Romance]	2004
1	143	2297762	5	2004-08-07	The Game	[Drama, Mystery, Thriller]	1997
2	1744	1489846	3	2003-05-22	Beverly Hills Cop	[Action, Comedy, Crime]	1984

# 파생 변수 한 번에 추가 (decade, weekday, title_length)
netflix_enriched = nu.enrich_netflix(netflix)
netflix_enriched.head(3)

	movie_id	user_id	rating	date	title	genre	year	decade	weekday	title_length
0	3282	972104	4	2005-09-16	Sideways	[Comedy, Drama, Romance]	2004	2000	Fri	8
1	143	2297762	5	2004-08-07	The Game	[Drama, Mystery, Thriller]	1997	1990	Sat	8
2	1744	1489846	3	2003-05-22	Beverly Hills Cop	[Action, Comedy, Crime]	1984	1980	Thu	17

# 영화별 통계 (최소 30명 이상 평가한 영화만)
m_stats = nu.movie_stats(netflix, min_count=30)
m_stats.sort_values("mean", ascending=False).head()

	title	mean	std	count
734	The Sixth Sense	4.329	0.793	15166
733	The Silence of the Lambs	4.310	0.815	12940
101	Braveheart	4.289	0.901	13590
72	Batman Begins	4.215	0.860	5529
510	Sense and Sensibility	4.195	0.896	1133

# 사용자별 통계 (최소 30개 이상 평가한 사용자만)
u_stats = nu.user_stats(netflix, min_count=30)
u_stats.head()

	mean	std	count
user_id
1333	2.674	0.778	43
2213	3.871	0.846	31
2455	3.433	0.817	30
2905	3.700	1.418	30
3321	2.977	1.012	43

# 장르별 통계
g_stats = nu.genre_stats(netflix)
g_stats.sort_values("mean", ascending=False)

	genre	mean	std	count
10	Film-Noir	3.965	0.935	9020
20	War	3.908	1.037	32304
3	Biography	3.878	0.995	121688
...	...	...	...	...
4	Comedy	3.528	1.067	770697
12	Horror	3.386	1.065	177556
17	Sci-Fi	3.332	1.090	115480

22 rows × 4 columns

# 범용 집계: 요일별 평점
netflix_enriched = nu.add_ordered_weekday(netflix)
nu.rating_stats_by(netflix_enriched, "weekday")

	weekday	mean	std	count
0	Mon	3.584	1.054	324006
1	Tue	3.582	1.054	331272
2	Wed	3.590	1.055	311012
...	...	...	...	...
4	Fri	3.589	1.061	245186
5	Sat	3.596	1.065	184385
6	Sun	3.596	1.060	199471

7 rows × 4 columns

# 시각화: 평균 vs 표준편차 산점도
nu.plot_mean_vs_std(m_stats, title="Movie: Mean vs Std")

# 시각화: 장르 순위
nu.plot_genre_ranking(g_stats, metric="mean", title="Genre Mean Rating")

# 시각화: 연도별 평점 추세
nu.plot_trend_by_year(netflix, x_col="year", title="Rating Trend by Year")

# 사용자별 평점 표준화 (z-score)
standardized = nu.standardize_rating_by(netflix, group_col="user_id")
standardized.head()

	user_id	rating
117541	6	-0.483
324856	6	1.932
412793	6	-0.483
448624	6	1.932
604841	6	-0.483

Cleaned Data

Data Wrangling

subsetting

query()

sort_values()

assign()

groupby(), agg(), apply()

Exploratory Data Analysis (EDA)

평점 분포

요일별 평점

제목의 길이?

시청자별 분석

장르별 분석

출시년도

Project-Native 구현

기본통계

시청자 분석

가장 활발한 시청자 TOP 5

시청자별 통계

작품별 분석

장르 분석

시간대 분석

평점 분석

종합 리포트

Module로 변환/활용

`query()`

`sort_values()`

`assign()`

`groupby()`, `agg()`, `apply()`