
#한글 폰트 설정
!sudo apt-get install -y fonts-nanum
!sudo fc-cache -fv
!rm ~/.cache/matplotlib -rf

Reading package lists... Done
Building dependency tree       
Reading state information... Done
The following package was automatically installed and is no longer required:
  libnvidia-common-460
Use 'sudo apt autoremove' to remove it.
The following NEW packages will be installed:
  fonts-nanum
0 upgraded, 1 newly installed, 0 to remove and 20 not upgraded.
Need to get 9,604 kB of archives.
After this operation, 29.5 MB of additional disk space will be used.
Get:1 http://archive.ubuntu.com/ubuntu bionic/universe amd64 fonts-nanum all 20170925-1 [9,604 kB]
Fetched 9,604 kB in 2s (5,526 kB/s)
debconf: unable to initialize frontend: Dialog
debconf: (No usable dialog-like program is installed, so the dialog based frontend cannot be used. at /usr/share/perl5/Debconf/FrontEnd/Dialog.pm line 76, <> line 1.)
debconf: falling back to frontend: Readline
debconf: unable to initialize frontend: Readline
debconf: (This frontend requires a controlling tty.)
debconf: falling back to frontend: Teletype
dpkg-preconfigure: unable to re-open stdin: 
Selecting previously unselected package fonts-nanum.
(Reading database ... 124016 files and directories currently installed.)
Preparing to unpack .../fonts-nanum_20170925-1_all.deb ...
Unpacking fonts-nanum (20170925-1) ...
Setting up fonts-nanum (20170925-1) ...
Processing triggers for fontconfig (2.12.6-0ubuntu2) ...
/usr/share/fonts: caching, new cache contents: 0 fonts, 1 dirs
/usr/share/fonts/truetype: caching, new cache contents: 0 fonts, 3 dirs
/usr/share/fonts/truetype/humor-sans: caching, new cache contents: 1 fonts, 0 dirs
/usr/share/fonts/truetype/liberation: caching, new cache contents: 16 fonts, 0 dirs
/usr/share/fonts/truetype/nanum: caching, new cache contents: 10 fonts, 0 dirs
/usr/local/share/fonts: caching, new cache contents: 0 fonts, 0 dirs
/root/.local/share/fonts: skipping, no such directory
/root/.fonts: skipping, no such directory
/var/cache/fontconfig: cleaning cache directory
/root/.cache/fontconfig: not cleaning non-existent cache directory
/root/.fontconfig: not cleaning non-existent cache directory
fc-cache: succeeded


#기본 패키지
import math
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
plt.rc('font', family='NanumBarunGothic') #한글 폰트 가져오기

plt.style.use('seaborn') #그래프 기본 설정
sns.set(font_scale=1)

import warnings 
warnings.simplefilter(action='ignore', category=FutureWarning)


#구글 드라이브 마운트
from google.colab import drive 
drive.mount('/content/drive')

Mounted at /content/drive


from google.colab import drive
drive.mount('/content/drive')

Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount("/content/drive", force_remount=True).


#데이터 불러오기
#csv 데이터 파일
sw = pd.read_csv('/content/drive/MyDrive/Colab Notebooks/데이터 분석 실습/Starwars/Starwars.csv')


#데이터 내용 요약
print("총 데이터 개수: ", sw.shape[0]*sw.shape[1])
print("총 결측치 수: {} = 전체 데이터의 {:.2f}% ".format(sw.isnull().sum().sum(), (sw.isnull().sum().sum()*100)/(sw.shape[0]*sw.shape[1])))
print("스타워즈에 등장하는 등장인물 수: ", sw['name'].nunique())
print("스타워즈에 등장하는 종족 수: ", sw['species'].nunique())

총 데이터 개수:  957
총 결측치 수: 105 = 전체 데이터의 10.97% 
스타워즈에 등장하는 등장인물 수:  87
스타워즈에 등장하는 종족 수:  37


#NULL이 존재하는 컬럼 확인하기
sw.isnull().any(axis=0)
#height, mass, type, x, y 컬럼에 NaN 존재함

name          False
height         True
mass           True
hair_color     True
skin_color    False
eye_color     False
birth_year     True
sex            True
gender         True
homeworld      True
species        True
dtype: bool


#컬럼별로 NULL 개수 확인
sw.isnull().sum()

name           0
height         6
mass          28
hair_color     5
skin_color     0
eye_color      0
birth_year    44
sex            4
gender         4
homeworld     10
species        4
dtype: int64


#결측치 처리
#hair color, sex, gender, homeworld, species의 경우 개인 특성이므로 다른 값을 넣어주는 것이 의미가 없다
#height, mass에서는 결측치를 0으로 처리
sw['height'].fillna(0, inplace=True)
sw['mass'].fillna(0, inplace=True)
sw.head()


#sex -> (none, NaN) 
print(sw[sw['sex'] == 'none'])
print(sw[sw['sex'].isnull()])

      name  height   mass hair_color   skin_color  eye_color  birth_year  \
1    C-3PO   167.0   75.0        NaN         gold     yellow       112.0   
2    R2-D2    96.0   32.0        NaN  white, blue        red        33.0   
7    R5-D4    97.0   32.0        NaN   white, red        red         NaN   
21   IG-88   200.0  140.0       none        metal        red        15.0   
72  R4-P17    96.0    0.0       none  silver, red  red, blue         NaN   
84     BB8     0.0    0.0       none         none      black         NaN   

     sex     gender homeworld species  
1   none  masculine  Tatooine   Droid  
2   none  masculine     Naboo   Droid  
7   none  masculine  Tatooine   Droid  
21  none  masculine       NaN   Droid  
72  none   feminine       NaN   Droid  
84  none  masculine       NaN   Droid  
              name  height  mass hair_color skin_color eye_color  birth_year  \
36        Ric Oli?   183.0   0.0      brown       fair      blue         NaN   
39   Quarsh Panaka   183.0   0.0      black       dark     brown        62.0   
79       Sly Moore   178.0  48.0       none       pale     white         NaN   
85  Captain Phasma     0.0   0.0    unknown    unknown   unknown         NaN   

    sex gender homeworld species  
36  NaN    NaN     Naboo     NaN  
39  NaN    NaN     Naboo     NaN  
79  NaN    NaN    Umbara     NaN  
85  NaN    NaN       NaN     NaN


#if sex = none, then species = Droid
sw['sex'][(sw['sex'] == 'none')] = 'robot'
print('Sex: ', sw['sex'].unique())

Sex:  ['male' 'robot' 'female' 'hermaphroditic' nan]

<ipython-input-23-aedb8c37b719>:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  sw['sex'][(sw['sex'] == 'none')] = 'robot'


#스타워즈 캐릭터의 성비(sex, gender)
print(sw['sex'].value_counts())
print(sw['gender'].value_counts())

male              60
female            16
robot              6
hermaphroditic     1
Name: sex, dtype: int64
masculine    66
feminine     17
Name: gender, dtype: int64


f, ax = plt.subplots(1, 2, figsize=(18, 8))

sw['gender'].value_counts().plot.pie(ax=ax[0], autopct='%1.0f%%', shadow=True) 
ax[0].set_title('Starwars: Gender', size=18) #그래프 제목
ax[0].set_ylabel('') #unnecessary y_label

sns.countplot(x='sex', data=sw, ax=ax[1])
ax[1].set_title('Starwars: Sex', size=18) #그래프 제목

plt.show()


#스타워즈 캐릭터의 신장
sw['height'].describe()


#skewness and kurtosis 구하기
#Skewness(왜도): 데이터가 정규분포에서 한 쪽으로 치우쳐있는가?
#                -3 < skewness < 3 사이의 값이면 기준에 부합한다
#Kurtosis(첨도): 얼마나 뾰족한가(데이터가 얼마나 평균 근처에 몰려있는가)?
#               : 정규분포의 kurtosis = 0
print("Skewness: %f" % sw['height'].skew())
print("Kurtosis: %f" % sw['height'].kurt())

Skewness: -1.760878
Kurtosis: 2.927697


#자웅동체(hermaphroditic) 캐릭터(Jabba Desilijic Tiure) - 1 instance
sw[sw['sex'] == 'hermaphroditic'].head()


#성별에 따른 스타워즈 캐릭터의 신장 분포 그래프
#자웅동체 캐릭터(Jabba Desilijic Tiure)의 확률 분포 그래프는 존재하지 않음

fig, ax = plt.subplots(1, 2, figsize=(16, 5))

#sns.distplot
sns.distplot(sw[sw['sex'] == 'male']['height'], ax=ax[0])
sns.distplot(sw[sw['sex'] == 'female']['height'], ax=ax[0])
sns.distplot(sw[sw['sex'] == 'robot']['height'], ax=ax[0])
ax[0].legend(['male','female','robot'])

#sns.kdeplot
sns.kdeplot(sw[sw['gender'] == 'masculine']['height'], ax=ax[1])
sns.kdeplot(sw[sw['gender'] == 'feminine']['height'], ax=ax[1])
ax[1].legend(['masculine','feminine'])

plt.show()


#몸무게가 가장 가벼운 캐릭터
notz = sw[sw['mass'] != 0]  #몸무게가 0인 것은 제외
min(notz['mass'])

15.0


#데이터 내용 정리해서 출력
print("{}의 몸무게가 {} (으)로 가장 가볍다 ".format(notz[notz['mass'] == min(notz['mass'])]['name'].values, min(notz['mass'])))
print("{}의 몸무게가 {} (으)로 가장 무겁다 ".format(notz[notz['mass'] == max(notz['mass'])]['name'].values, max(notz['mass'])))

['Ratts Tyerell']의 몸무게가 15.0 (으)로 가장 가볍다 
['Jabba Desilijic Tiure']의 몸무게가 1358.0 (으)로 가장 무겁다


#Groupby로 스타워즈 종족 별 평균 몸무게를 계산해보자
weight = sw[['species', 'mass']].groupby(['species'], as_index=True).mean()
weight


#몸무게 상위 10개 종족
weight['mass'].sort_values(ascending=False).head(10).plot.bar(color='red')
plt.xticks(rotation=45)
plt.show()


#스타워즈 종족별 몸무게 그래프 (sort=desc)
f, ax = plt.subplots(1, 1, figsize=(10, 8))

colors = sns.color_palette('crest',len(weight['mass']))

g = weight['mass'].sort_values(ascending=False).plot.bar(color = colors)
g.set_xticklabels(g.get_xticklabels(),rotation=90) #라벨 중첩 해소

plt.show()


#Hutt - outlier
#몸무게 0 제외
out1 = sw['species'].isin(['Hutt'])
out2 = sw['mass'].isin([0])
sw[~out1][~out2].shape

<ipython-input-55-4e3d60c6794b>:5: UserWarning: Boolean Series key will be reindexed to match DataFrame index.
  sw[~out1][~out2].shape

(58, 11)


#두 데이터 사이의 상관관계

sns.lmplot(data=sw[~out1][~out2], x='height', y='mass', hue='gender')
sns.set_style(style='darkgrid')

plt.show()

<ipython-input-56-5c5f9cc7fe44>:4: UserWarning: Boolean Series key will be reindexed to match DataFrame index.
  sns.lmplot(data=sw[~out1][~out2], x='height', y='mass', hue='gender') # hue=gender로 나타내서도 살펴보기

	mass
species
Aleena	15.000000
Besalisk	102.000000
Cerean	82.000000
Chagrian	0.000000
Clawdite	55.000000
Droid	46.500000
Dug	40.000000
Ewok	20.000000
Geonosian	80.000000
Gungan	49.333333
Human	52.034286
Hutt	1358.000000
Iktotchi	0.000000
Kaleesh	159.000000
Kaminoan	44.000000
Kel Dor	80.000000
Mirialan	53.100000
Mon Calamari	83.000000
Muun	0.000000
Nautolan	87.000000
Neimodian	90.000000
Pau'an	80.000000
Quermian	0.000000
Rodian	74.000000
Skakoan	48.000000
Sullustan	68.000000
Tholothian	50.000000
Togruta	57.000000
Toong	65.000000
Toydarian	0.000000
Trandoshan	113.000000
Twi'lek	27.500000
Vulptereen	45.000000
Wookiee	124.000000
Xexto	0.000000
Yoda's species	17.000000
Zabrak	40.000000

Starwars Data

Purpose & Contents

Data

Starwars Character Report

Starwars Data

Purpose & Contents

Data

Conclusion

Code

2.분석 내용¶

3.데이터 전처리¶

3-1.결측치 처리¶

4.EDA & Visualization¶

4-1. 스타워즈 캐릭터의 성별 비율¶

4-2. 스타워즈 캐릭터의 성별에 따른 신장 분포¶

4-3. 가장 가벼운 캐릭터와 가장 무거운 캐릭터¶

4-4.스타워즈 캐릭터의 종족 간 몸무게 비교¶

4-5. 스타워즈 캐릭터의 무게-키 상관관계¶

5.Review¶

TAEWON KIM

Recent posts

Comments

	name	height	mass	hair_color	skin_color	eye_color	birth_year	sex	gender	homeworld	species
0	Luke Skywalker	172.0	77.0	blond	fair	blue	19.0	male	masculine	Tatooine	Human
1	C-3PO	167.0	75.0	NaN	gold	yellow	112.0	none	masculine	Tatooine	Droid
2	R2-D2	96.0	32.0	NaN	white, blue	red	33.0	none	masculine	Naboo	Droid
3	Darth Vader	202.0	136.0	none	white	yellow	41.9	male	masculine	Tatooine	Human
4	Leia Organa	150.0	49.0	brown	light	brown	19.0	female	feminine	Alderaan	Human

Starwars Data

Purpose & Contents

Data

Starwars Character Report

Starwars Data

Purpose & Contents

Data

Conclusion

Code

2.분석 내용¶

3.데이터 전처리¶

3-1.결측치 처리¶

4.EDA & Visualization¶

4-1. 스타워즈 캐릭터의 성별 비율¶

4-2. 스타워즈 캐릭터의 성별에 따른 신장 분포¶

4-3. 가장 가벼운 캐릭터와 가장 무거운 캐릭터¶

4-4.스타워즈 캐릭터의 종족 간 몸무게 비교¶

4-5. 스타워즈 캐릭터의 무게-키 상관관계¶

5.Review¶

TAEWON KIM

Recent posts

Newsletter

Comments