6일차 코로나 데이터 분석


# 그래프에 한글 출력하기 위한 코드
from matplotlib import font_manager, rc

font_name = font_manager.FontProperties(
    fname = 'c:/Windows/Fonts/malgun.ttf').get_name()
rc('font', family=font_name)

# import matplotlib.pyplot as plt
# plt.rc('font', family='AppleGothic') # mac
# plt.rc('font', family='Malgun Gothic') # window

1. 성별, 나이별


import numpy as np
import pandas as pd

# 출처 : 질병관리본부
confirmed = pd.read_csv('./data/daily_Confirmed.csv', index_col = ['Date'])


#pd.read_csv('./data.csv', encoding='utf-8') # Default(기본)
#pd.read_csv('./data.csv', encoding='cp949') # 11172자
#pd.read_csv('./data.csv', encoding='euc-kr') # 2350자


confirmed.info() # confirmed의 정보 확인


<class 'pandas.core.frame.DataFrame'>
Index: 32 entries, 2020-03-01 to 2020-04-01
Data columns (total 11 columns):
Female    32 non-null int64
Male      32 non-null int64
0-9       32 non-null int64
10-       32 non-null int64
20-29     32 non-null int64
30-39     32 non-null int64
40-49     32 non-null int64
50-59     32 non-null int64
60-69     32 non-null int64
70-79     32 non-null int64
80-       32 non-null int64
dtypes: int64(11)
memory usage: 3.0+ KB


confirmed.head() # defult 값은 5


Out[-]
						Female	Male	0-9	 10- 20-29	30-39	40-49	50-59	60-69	70-79	80-
			Date																				
2020-03-01	  2197	1329	27	137	  1054	 426	 521	 687	 453	 158	63
2020-03-02	  2621	1591	32	169	  1235	 506	 633	 834	 530	 192	81
2020-03-03	  3002	1810	34	204	  1417	 578	 713	 952	 597	 224	93
2020-03-04	  3332	1996	34	233	  1575	 631	 790	1051	 646	 260	108
2020-03-05	  3617	2149	38	257	  1727	6 59	 847	1127	 699	 288	124


confirmed.tail()


Out[-]
						Female	Male	0-9	 10- 20-29	30-39	40-49	50-59	60-69	70-79	80-
			Date											
2020-03-28	  5742	3736	109	 501	2567	 978	1278	1780	1201	 632	432
2020-03-29	  5784	3799	111	 508	2602	 991	1292	1798	1210	 635	434
2020-03-30	  5827	3836	112	 513	2630	1002	1297	1812	1218	 640	437
2020-03-31	  5881	3905	112	 515	2656	1012	1312	1851	1235	 651	442
2020-04-01	  5941	3946	116	 519	2682	1027	1323	1865	1245	 658	452


confirmed.isnull().sum()  # 결측치 개수 구하기


Out[-]
Female    0
Male      0
0-9       0
10-       0
20-29     0
30-39     0
40-49     0
50-59     0
60-69     0
70-79     0
80-       0
dtype: int64


# 혹시 결측치가 있다면!
# pd.to_numeric(df['컬럼이름'], errors='coerce') -> nan


confirmed['Female'].describe()


Out[-]
count      32.000000
mean     4882.531250
std       999.970515
min      2197.000000
25%      4547.250000
50%      5146.500000
75%      5601.000000
max      5986.000000
Name: Female, dtype: float64

시각화

plt.pie

rcParams : 차트 크기, 선의 색, 두께 등 설정
explode : Pie 차트 조각 추출되는 크기
autopct : Pie 차트 조각의 전체 대비 백분율


# 마지막 날인 2020년 4월 1일 데이터
# 성별 데이터 가져오기
sex = confirmed.iloc[-1, :2]
sex


Out[-]
Female    5941
Male      3946
Name: 2020-04-01, dtype: int64


# 성별에 따른 확진자 수 pie 그래프
import matplotlib.pyplot as plt

plt.rcParams['figure.figsize'] = 12,8
group_explodes = (0.05, 0)

plt.pie(sex, labels=['female', 'male'],
       explode = group_explodes,
       shadow = True,
       startangle=90,
       colors = ['lightcoral', 'lightskyblue'],
       autopct='%1.2f%%')

plt.title('Confirmed(sex)', size=15)
plt.axis('equal')
plt.show()

Out[-]


# 2020년 3월 1일 ~ 4월 1일 시계열 데이터
sex = confirmed.iloc[:, :2]
sex


Out[-]
					Female	Male
		 Date		
2020-03-01	2197	1329
2020-03-02	2621	1591
2020-03-03	3002	1810
2020-03-04	3332	1996
2020-03-05	3617	2149
2020-03-06	3939	2345
2020-03-07	4245	2522
2020-03-08	4440	2694
2020-03-09	4583	2799
2020-03-10	4661	2852
2020-03-11	4808	2947
2020-03-12	4875	2994
2020-03-13	4936	3043
2020-03-14	5986	3100 
2020-03-15	5026	3136
2020-03-16	5067	3169
2020-03-17	5120	3200
2020-03-18	5173	3240
2020-03-19	5269	3296
2020-03-20	5322	3330
2020-03-21	5412	3387
2020-03-22	5467	3430
2020-03-23	5504	3457
2020-03-24	5540	3497
2020-03-25	5587	3550
2020-03-26	5643	3598
2020-03-27	5694	3638
2020-03-28	5742	3736
2020-03-29	5784	3799
2020-03-30	5827	3836
2020-03-31	5881	3905
2020-04-01	5941	3946


plt.xticks(rotation=70) # x 축 방향 기울이기(기울이지 않으면 겹침)

plt.bar(sex.index, 
				sex.loc[:,'Female'], 
				color='lightcoral', label='Female')

plt.bar(sex.index, 
				sex.loc[:,'Male'], 
				color='lightskyblue', label='Male')

plt.show()
# 3월 14일의 데이터의 확인이 필요

Out[-]


confirmed['Female']['2020-03-14'] = 5000


# 2020년 3월 1일 ~ 4월 1일 시계열 데이터(수정)
sex = confirmed.iloc[:, :2]
sex


Out[-]
					Female	Male
     Date		
2020-03-01	2197	1329
2020-03-02	2621	1591
2020-03-03	3002	1810
2020-03-04	3332	1996
2020-03-05	3617	2149
2020-03-06	3939	2345
2020-03-07	4245	2522
2020-03-08	4440	2694
2020-03-09	4583	2799
2020-03-10	4661	2852
2020-03-11	4808	2947
2020-03-12	4875	2994
2020-03-13	4936	3043
2020-03-14	5000	3100 # 변경 후 (5986 -> 5000)
2020-03-15	5026	3136
2020-03-16	5067	3169
2020-03-17	5120	3200
2020-03-18	5173	3240
2020-03-19	5269	3296
2020-03-20	5322	3330
2020-03-21	5412	3387
2020-03-22	5467	3430
2020-03-23	5504	3457
2020-03-24	5540	3497
2020-03-25	5587	3550
2020-03-26	5643	3598
2020-03-27	5694	3638
2020-03-28	5742	3736
2020-03-29	5784	3799
2020-03-30	5827	3836
2020-03-31	5881	3905
2020-04-01	5941	3946


plt.xticks(rotation=70)

plt.bar(sex.index, 
				sex.loc[:,'Female'], 
				color='lightcoral', label='Female')

plt.bar(sex.index, 
        sex.loc[:,'Male'], 
        color='lightskyblue', 
        label='Male',
        bottom = sex.loc[:,'Female'],
        alpha = 0.5)

plt.xlabel('Date')
plt.ylabel('Number')
plt.title('Confirmed(sex)', size=15)
plt.legend()

plt.show()

Out[-]

Plotly


sex = confirmed.iloc[-1, :2]
print(sex)
print(type(sex))


Out[-]
Female    5941
Male      3946
Name: 2020-04-01, dtype: int64
<class 'pandas.core.series.Series'>


import plotly.graph_objects as go

labels = sex.index
values = sex.values

fig = go.Figure(data=[go.Pie(labels=labels, 
														 values=values)])

fig.show()

Out[-]


# 공식홈페이지 튜토리얼, 보통은 df으로 그립니다.
import plotly.express as px
# tips데이터는 244 x 7 로 이루어져 있고 day는 4개의 고유값이 있다.
df = px.data.tips()

fig = px.pie(df, 
						 values='tip', names='day')

fig.show()

Out[-]


sex = confirmed.iloc[:, :2]
sex


Out[-]
					Female	Male
     Date		
2020-03-01	2197	1329
2020-03-02	2621	1591
2020-03-03	3002	1810
2020-03-04	3332	1996
2020-03-05	3617	2149
2020-03-06	3939	2345
2020-03-07	4245	2522
2020-03-08	4440	2694
2020-03-09	4583	2799
2020-03-10	4661	2852
2020-03-11	4808	2947
2020-03-12	4875	2994
2020-03-13	4936	3043
2020-03-14	5000	3100
2020-03-15	5026	3136
2020-03-16	5067	3169
2020-03-17	5120	3200
2020-03-18	5173	3240
2020-03-19	5269	3296
2020-03-20	5322	3330
2020-03-21	5412	3387
2020-03-22	5467	3430
2020-03-23	5504	3457
2020-03-24	5540	3497
2020-03-25	5587	3550
2020-03-26	5643	3598
2020-03-27	5694	3638
2020-03-28	5742	3736
2020-03-29	5784	3799
2020-03-30	5827	3836
2020-03-31	5881	3905
2020-04-01	5941	3946


female = go.Bar(x=sex.index,
							  y=sex.iloc[:,0], name='Female')

male = go.Bar(x=sex.index, 
							y=sex.iloc[:,1], name='Male')

data = female, male
# data
layout = go.Layout(title='Confirmed(sex)', barmode='stack')
fig = go.Figure(data=data, layout=layout)

fig.show()

Out[-]


age = confirmed.iloc[-1, 2:]
age


Out[-]
0-9       116
10-       519
20-29    2682
30-39    1027
40-49    1323
50-59    1865
60-69    1245
70-79     658
80-       452
Name: 2020-04-01, dtype: int64


# 4월 1일 나이별 확진자
# bar 그래프

data = [go.Bar(x=age.index, y=age.values)]
layout = go.Layout(title='Confirmed(age)')
fig = go.Figure(data=data, layout=layout)

fig.show()

Out[-]


# 4월 1일 나이별 확진자
# bar 그래프

data = [go.Pie(labels=age.index, values=age.values)]
layout = go.Layout(title='Confirmed(age)')
fig = go.Figure(data=data, layout=layout)

fig.show()

Out[-]


# 치명률
# 4월 1일 기준
# 치명률 = 사망자수/확진자수 * 100


death = pd.read_csv('./data/daily_Deceased.csv', index_col = ['Date']) # 사망자
death.tail()


Out[-]
						Female	Male	0-9	10-	20-29	30-39	40-49	50-59	60-69	70-79	80-
      Date											
2020-03-28	    67	  77	  0	  0	   0	   1	   1	  10	  21	  41	70
2020-03-29	    74	  78	  0	  0	   0	   1	   1	  10	  21	  43	76
2020-03-30	    78	  80	  0	  0	   0	   1	   1	  10	  21	  45	80
2020-03-31	    80	  82	  0	  0	   0	   1	   1	  10	  22	  46	82
2020-04-01	    81	  84	  0	  0	   0	   1	   1	  10	  23	  46	84


confirmed_temp = confirmed.iloc[-1, :]
death_temp = death.iloc[-1, :]


confirmed_temp


Out[-]
Female    5941
Male      3946
0-9        116
10-        519
20-29     2682
30-39     1027
40-49     1323
50-59     1865
60-69     1245
70-79      658
80-        452
Name: 2020-04-01, dtype: int64


death_temp


Out[-]
Female    81
Male      84
0-9        0
10-        0
20-29      0
30-39      1
40-49      1
50-59     10
60-69     23
70-79     46
80-       84
Name: 2020-04-01, dtype: int64


death_rate = round((death_temp/confirmed_temp)*100, 2) # round 소수점 2번째자리까지 반올림
death_rate


Out[-]
Female     1.36
Male       2.13
0-9        0.00
10-        0.00
20-29      0.00
30-39      0.10
40-49      0.08
50-59      0.54
60-69      1.85
70-79      6.99
80-       18.58
Name: 2020-04-01, dtype: float64


sex = confirmed_temp[:2]
sex


Out[-]
Female    5941
Male      3946
Name: 2020-04-01, dtype: int64


sex_death = death_temp[:2]
sex_death


Out[-]
Female    81
Male      84
Name: 2020-04-01, dtype: int64


from plotly.subplots import make_subplots

fig = make_subplots(rows=1,cols=2,specs=[[{'type':'domain'}, {'type':'domain'}]])

labels = sex.index
values = sex.values
labels2 = sex_death.index
values2 = sex_death.values

fig.add_trace(go.Pie(labels=labels, 
										 values=values), row=1, col=1)

fig.add_trace(go.Pie(labels=labels2, 
                     values=values2), row=1, col=2)
fig.update_layout(title='confiremd - death_rate')

fig.show()

Out[-]


age_confirmed = confirmed.iloc[-1, 2:]
age_confirmed


Out[-]
0-9       116
10-       519
20-29    2682
30-39    1027
40-49    1323
50-59    1865
60-69    1245
70-79     658
80-       452
Name: 2020-04-01, dtype: int64


age_death = death_rate.iloc[2:]
age_death


Out[-]
0-9       0.00
10-       0.00
20-29     0.00
30-39     0.10
40-49     0.08
50-59     0.54
60-69     1.85
70-79     6.99
80-      18.58
Name: 2020-04-01, dtype: float64


fig = make_subplots(rows=1,cols=2,specs=[[{'type':'bar'}, {'type':'bar'}]])

labels = age_confirmed.index
values = age_confirmed.values
labels2 = age_death.index
values2 = age_death.values

fig.add_trace(go.Bar(x=labels,
									   y=values, name='confirmed_age'), row=1, col=1)

fig.add_trace(go.Bar(x=labels2, 
										 y=values2, name='death_rate'), row=1, col=2)

fig.update_layout(title='confiremd - death_rate(age)')

fig.show()

Out[-]

2. 코로나 지역별 분석


# 데이터 불러오기(출처 : 질병관리본부)

import pandas as pd
from matplotlib import pyplot as plt

region = pd.read_csv("./data/region.csv", index_col=['day'])


region.head()


Out[-]
						서울	부산	대구	인천	광주	대전	울산	세종	경기	강원	충북	충남	전북	전남	경북	경남	제주	검역	총확진자수
       day																			
2020-03-01	 82	   81	  2569	  6	    9	   13	   17	   1	   84	    7	   11	   60	    5	    3	   514	 62	    2	    0	     3526
2020-03-02	 91	   88	  3081	  7	    9	   14	   20	   1	   92	   19	   11	   78	    6	    5	   624	 64	    2	    0	     4212
2020-03-03	 98	   90	  3601	  7	   11	   14	   20	   1	   94	   20	   11	   81	    7	    5	   685   64	    3	    0	     4812
2020-03-04	 99	   93	  4006	  9	   13	   15	   23	   1	  101	   21	   11	   82	    7	    5	   774	 65	    3	    0	     5328
2020-03-05	103	   92	  4326	  9	   14	   16	   23	   1	  110	   23	   12	   86	    7	    5	   861	 74	    4	    0	     5766


region.tail()


Out[-]
						서울	부산	대구	인천	광주	대전	울산	세종	경기	강원	충북	충남	전북	전남	경북	경남	제주	검역	총확진자수
       day																			
2020-03-28	390	  114	  6587	 51	   20	   31	   39	   44	  433	   32	   41	  126	   10	    8	  1285	 91	    8	  168   	9478
2020-03-29	410	  117	  6610	 58	   20	   34	   39	   46	  448	   34	   41	  127	   12	    9	  1287	 94   	8	  189	    9583
2020-03-30	426	  118	  6624	 58	   20	   34	   39	   46	  463	   36	   44	  127	   13	    9	  1298	 95	    9	  202	    9661
2020-03-31	450	  119	  6684	 64	   20	   36	   39	   46	  476	   36    44	  128	   13	    9	  1300	 96	    9	  217	    9786
2020-04-01	474	  122	  6704	 69	   24	   36	   39	   46	  499	   38	   44	  131	   14	   12	  1302	100	    9	  224	    9887


region.info()


Out[-]
<class 'pandas.core.frame.DataFrame'>
Index: 32 entries, 2020-03-01 to 2020-04-01
Data columns (total 19 columns):
 #   Column  Non-Null Count  Dtype
---  ------  --------------  -----
 0   서울      32 non-null     int64
 1   부산      32 non-null     int64
 2   대구      32 non-null     int64
 3   인천      32 non-null     int64
 4   광주      32 non-null     int64
 5   대전      32 non-null     int64
 6   울산      32 non-null     int64
 7   세종      32 non-null     int64
 8   경기      32 non-null     int64
 9   강원      32 non-null     int64
 10  충북      32 non-null     int64
 11  충남      32 non-null     int64
 12  전북      32 non-null     int64
 13  전남      32 non-null     int64
 14  경북      32 non-null     int64
 15  경남      32 non-null     int64
 16  제주      32 non-null     int64
 17  검역      32 non-null     int64
 18  총확진자수   32 non-null     int64
dtypes: int64(19)
memory usage: 5.0+ KB


region.isnull().sum()


Out[-]
서울       0
부산       0
대구       0
인천       0
광주       0
대전       0
울산       0
세종       0
경기       0
강원       0
충북       0
충남       0
전북       0
전남       0
경북       0
경남       0
제주       0
검역       0
총확진자수    0
dtype: int64


pd.options.display.max_rows = 1000
pd.options.display.max_columns = 100


region.tail()


Out[-]
						서울	부산	대구	인천	광주	대전	울산	세종	경기	강원	충북	충남	전북	전남	경북	경남	제주	검역	총확진자수
       day																			
2020-03-28	390	  114	  6587	 51	   20	   31	   39	   44	  433	   32	   41	  126	   10	    8	  1285	 91	    8	  168   	9478
2020-03-29	410	  117	  6610	 58	   20	   34	   39	   46	  448	   34	   41	  127	   12	    9	  1287	 94   	8	  189	    9583
2020-03-30	426	  118	  6624	 58	   20	   34	   39	   46	  463	   36	   44	  127	   13	    9	  1298	 95	    9	  202	    9661
2020-03-31	450	  119	  6684	 64	   20	   36	   39	   46	  476	   36    44	  128	   13	    9	  1300	 96	    9	  217	    9786
2020-04-01	474	  122	  6704	 69	   24	   36	   39	   46	  499	   38	   44	  131	   14	   12	  1302	100	    9	  224	    9887


last = region.iloc[-1,:]
last


Out[-]
서울        474
부산        122
대구       6704
인천         69
광주         24
대전         36
울산         39
세종         46
경기        499
강원         38
충북         44
충남        131
전북         14
전남         12
경북       1302
경남        100
제주          9
검역        224
총확진자수    9887
Name: 2020-04-01, dtype: int64


last = region.iloc[-1,:-2]
last


Out[-]
서울     474
부산     122
대구    6704
인천      69
광주      24
대전      36
울산      39
세종      46
경기     499
강원      38
충북      44
충남     131
전북      14
전남      12
경북    1302
경남     100
제주       9
Name: 2020-04-01, dtype: int64


location_data = go.Bar(x=last.index, y=last.values)
layout = go.Layout(title='전국 확진자수', xaxis_title='지역', yaxis_title='확진자수')
fig = go.Figure(data=location_data, layout=layout)
fig.show()

Out[-]


last = last.sort_values(ascending=True)

# ascending 오름차순 
# 낮은 것부터 차례로 배열

# descending 내림차순
# 높은 것부터 차례로 배열

location_data = go.Bar(x=last.index, y=last.values)
layout = go.Layout(title='전국 확진자수', xaxis_title='지역', yaxis_title='확진자수')
fig = go.Figure(data=location_data, layout=layout)
fig.show()

Out[-]


region.index


Out[-]
Index(['2020-03-01', '2020-03-02', '2020-03-03', '2020-03-04', '2020-03-05',
       '2020-03-06', '2020-03-07', '2020-03-08', '2020-03-09', '2020-03-10',
       '2020-03-11', '2020-03-12', '2020-03-13', '2020-03-14', '2020-03-15',
       '2020-03-16', '2020-03-17', '2020-03-18', '2020-03-19', '2020-03-20',
       '2020-03-21', '2020-03-22', '2020-03-23', '2020-03-24', '2020-03-25',
       '2020-03-26', '2020-03-27', '2020-03-28', '2020-03-29', '2020-03-30',
       '2020-03-31', '2020-04-01'],
      dtype='object', name='day')


region.iloc[:,2]


Out[-]
day
2020-03-01    2569
2020-03-02    3081
2020-03-03    3601
2020-03-04    4006
2020-03-05    4326
2020-03-06    4693
2020-03-07    5084
2020-03-08    5381
2020-03-09    5571
2020-03-10    5663
2020-03-11    5794
2020-03-12    5867
2020-03-13    5928
2020-03-14    5990
2020-03-15    6031
2020-03-16    6066
2020-03-17    6098
2020-03-18    6144
2020-03-19    6241
2020-03-20    6275
2020-03-21    6344
2020-03-22    6387
2020-03-23    6411
2020-03-24    6442
2020-03-25    6456
2020-03-26    6482
2020-03-27    6516
2020-03-28    6587
2020-03-29    6610
2020-03-30    6624
2020-03-31    6684
2020-04-01    6704
Name: 대구, dtype: int64


# 전체 지역 그래프 그리기
import plotly.graph_objects as go
fig = go.Figure()
for i in range(len(last)) :
    fig.add_trace(go.Scatter(x=region.index, y=region.iloc[:,i], mode='lines+markers', name = region.columns[i]))
fig.update_layout(title='코나확진자수', xaxis_title='Day', yaxis_title='확진자수')
fig.show()

Out[-]


last = region.iloc[-1, :18]
last


Out[-]
서울     474
부산     122
대구    6704
인천      69
광주      24
대전      36
울산      39
세종      46
경기     499
강원      38
충북      44
충남     131
전북      14
전남      12
경북    1302
경남     100
제주       9
검역     224
Name: 2020-04-01, dtype: int64


last.index


Out[-]
Index(['서울', '부산', '대구', '인천', '광주', '대전', '울산', '세종', '경기', '강원', '충북', '충남',
       '전북', '전남', '경북', '경남', '제주', '검역'],
      dtype='object')


last.values


Out[-]
array([ 474,  122, 6704,   69,   24,   36,   39,   46,  499,   38,   44,
        131,   14,   12, 1302,  100,    9,  224], dtype=int64)


labels = last.index
values = last.values

fig = go.Figure(data=[go.Pie(labels=labels, values=values)])
fig.update_layout(title="지역별 확진자 비율")

fig.show()

Out[-]


region.iloc[:, 16]


Out[-]
day
2020-03-01    2
2020-03-02    2
2020-03-03    3
2020-03-04    3
2020-03-05    4
2020-03-06    4
2020-03-07    4
2020-03-08    4
2020-03-09    4
2020-03-10    4
2020-03-11    4
2020-03-12    4
2020-03-13    4
2020-03-14    4
2020-03-15    4
2020-03-16    4
2020-03-17    4
2020-03-18    4
2020-03-19    4
2020-03-20    4
2020-03-21    4
2020-03-22    4
2020-03-23    4
2020-03-24    4
2020-03-25    6
2020-03-26    6
2020-03-27    7
2020-03-28    8
2020-03-29    8
2020-03-30    9
2020-03-31    9
2020-04-01    9
Name: 제주, dtype: int64


# region.index
index = region.columns
list(index).index('제주')


Out[-]
16


jeju = region.iloc[:, 16]
jeju


Out[-]
day
2020-03-01    2
2020-03-02    2
2020-03-03    3
2020-03-04    3
2020-03-05    4
2020-03-06    4
2020-03-07    4
2020-03-08    4
2020-03-09    4
2020-03-10    4
2020-03-11    4
2020-03-12    4
2020-03-13    4
2020-03-14    4
2020-03-15    4
2020-03-16    4
2020-03-17    4
2020-03-18    4
2020-03-19    4
2020-03-20    4
2020-03-21    4
2020-03-22    4
2020-03-23    4
2020-03-24    4
2020-03-25    6
2020-03-26    6
2020-03-27    7
2020-03-28    8
2020-03-29    8
2020-03-30    9
2020-03-31    9
2020-04-01    9
Name: 제주, dtype: int64


# plotly
data = go.Bar(x=jeju.index, y=jeju.values,)
layout = go.Layout(title='제주도 확진자수',xaxis_title='Day', yaxis_title='확진자수')
fig = go.Figure(data=data, layout=layout)
fig.show()

Out[-]


# plotly semi log 그래프
data = go.Line(x=jeju.index, y=jeju.values,)

layout = go.Layout(title='제주도 확진자수',
                   xaxis_title='Day',
                   yaxis_title='확진자수',
                   yaxis_type='log',
                  )

fig = go.Figure(data=data, layout=layout)
fig.show()

Out[-]

Map


import pandas as pd

data = pd.read_csv("./data/region.csv", index_col=['day'])
data.tail()


Out[-]
						서울	부산	대구	인천	광주	대전	울산	세종	경기	강원	충북	충남	전북	전남	경북	경남	제주	검역	총확진자수
       day																			
2020-03-28	390	  114	  6587	 51	   20	   31	   39	   44	  433	   32	   41	  126	   10	    8	  1285	 91	    8	  168   	9478
2020-03-29	410	  117	  6610	 58	   20	   34	   39	   46	  448	   34	   41	  127	   12	    9	  1287	 94   	8	  189	    9583
2020-03-30	426	  118	  6624	 58	   20	   34	   39	   46	  463	   36	   44	  127	   13	    9	  1298	 95	    9	  202	    9661
2020-03-31	450	  119	  6684	 64	   20	   36	   39	   46	  476	   36    44	  128	   13	    9	  1300	 96	    9	  217	    9786
2020-04-01	474	  122	  6704	 69	   24	   36	   39	   46	  499	   38	   44	  131	   14	   12	  1302	100	    9	  224	    9887


map_data = data.iloc[-1, :17]
map_data = pd.DataFrame(map_data)
map_data


Out[-]
   2020-04-01
서울	   474
부산	   122
대구	  6704
인천	    69
광주	    24
대전	    36
울산	    39
세종	    46
경기	   499
강원	    38
충북	    44
충남	   131
전북	    14
전남	    12
경북	  1302
경남	   100
제주	     9


loc = {
  '서울' : [37.566418, 126.977950],#서울시청
  '부산' : [35.180152, 129.074980],#부산시청
  '대구' : [35.871468, 128.601757],#대구시청
  '인천' : [37.456445, 126.705873],#인천시청
  '광주' : [35.160068, 126.851426],#광주광역시청
  '대전' : [36.350664, 127.384819],#대전시청
  '울산' : [35.539772, 129.311486],#울산시청
  '세종' : [36.480838, 127.289181],#세종시청
  '경기' : [37.275221, 127.009382],#경기도청
  '강원' : [37.885300, 127.729835],#강원(강원도청)
  '충북' : [36.635947, 127.491345],#충북도청
  '충남' : [36.658826, 126.672849],#충남도청
  '전북' : [35.820599, 127.108759],#전북도청
  '전남' : [34.816351, 126.462924],#전남도청
  '경북' : [36.574108, 128.509303],#경북도청
  '경남' : [35.238398, 128.692371],#경남도청
  '제주' : [33.3617007, 126.511657]#제주
    }
type(loc)


Out[-]
dict


# 위도(latitude)와 경도(longitude)

loc = pd.DataFrame(loc).T
loc.columns = ['lat', 'lon']
loc


Out[-]
						lat	      lon
서울	37.566418	126.977950
부산	35.180152	129.074980
대구	35.871468	128.601757
인천	37.456445	126.705873
광주	35.160068	126.851426
대전	36.350664	127.384819
울산	35.539772	129.311486
세종	36.480838	127.289181
경기	37.275221	127.009382
강원	37.885300	127.729835
충북	36.635947	127.491345
충남	36.658826	126.672849
전북	35.820599	127.108759
전남	34.816351	126.462924
경북	36.574108	128.509303
경남	35.238398	128.692371
제주	33.361701	126.511657


!pip install folium


Out[-]
Collecting folium
  Downloading folium-0.10.1-py2.py3-none-any.whl (91 kB)
Requirement already satisfied: numpy in c:\programdata\anaconda3\lib\site-packages (from folium) (1.16.4)
Collecting branca>=0.3.0
  Downloading branca-0.4.0-py3-none-any.whl (25 kB)
Requirement already satisfied: requests in c:\programdata\anaconda3\lib\site-packages (from folium) (2.22.0)
Requirement already satisfied: jinja2>=2.9 in c:\programdata\anaconda3\lib\site-packages (from folium) (2.10.1)
Requirement already satisfied: six in c:\programdata\anaconda3\lib\site-packages (from branca>=0.3.0->folium) (1.12.0)
Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in c:\programdata\anaconda3\lib\site-packages (from requests->folium) (1.24.2)
Requirement already satisfied: idna<2.9,>=2.5 in c:\programdata\anaconda3\lib\site-packages (from requests->folium) (2.8)
Requirement already satisfied: chardet<3.1.0,>=3.0.2 in c:\programdata\anaconda3\lib\site-packages (from requests->folium) (3.0.4)
Requirement already satisfied: certifi>=2017.4.17 in c:\programdata\anaconda3\lib\site-packages (from requests->folium) (2019.6.16)
Requirement already satisfied: MarkupSafe>=0.23 in c:\programdata\anaconda3\lib\site-packages (from jinja2>=2.9->folium) (1.1.1)
Installing collected packages: branca, folium
Successfully installed branca-0.4.0 folium-0.10.1


import matplotlib.pyplot as plt
import folium

map_osm = folium.Map(location=[35.824,127.147], zoom_start=7)
map_osm

Out[-]


from folium.plugins import MarkerCluster
marker_cluster = MarkerCluster().add_to(map_osm)

for i in range(17):
    folium.Marker(
        [loc.iloc[i:i+1,0], loc.iloc[i:i+1,1]],
        popup = map_data[i:i+1],
        icon=folium.Icon(color='red',icon='star'),
    ).add_to(marker_cluster)
map_osm.save("map.html") # jupyter notebook에 한글 깨져서 html로 저장
map_osm

Out[-]


map_data.iloc[1]


Out[-]
2020-04-01    122
Name: 부산, dtype: int64


from folium.plugins import MarkerCluster

map_osm = folium.Map(location=[35.824,127.147], zoom_start=7)
marker_cluster = MarkerCluster().add_to(map_osm)

for i in range(17):
    folium.Circle(
        [loc.iloc[i:i+1,0], loc.iloc[i:i+1,1]],
        tooltip = map_data[i:i+1],
        radius = int(map_data.iloc[i])*10, ## 확진자 수 * 20배
        fill_color='red',
        color='red'
    ).add_to(marker_cluster)
map_osm.save("map.html")
map_osm

Out[-]

옵션값

공식홈페이지(https://python-visualization.github.io/folium/)

stroke (Bool, True) : Whether to draw stroke along the path. Set it to false to disable borders on polygons or circles.

color (str, '#3388ff') : Stroke color.

weight (int, 3) : Stroke width in pixels.

opacity (float, 1.0) : Stroke opacity.

line_cap (str, 'round' (lineCap)) : A string that defines shape to be used at the end of the stroke.

line_join (str, 'round' (lineJoin)) : A string that defines shape to be used at the corners of the stroke.

dash_array (str, None (dashArray)) : A string that defines the stroke dash pattern. Doesn’t work on Canvas-powered layers in some old browsers.

dash_offset (str, None (dashOffset)) : A string that defines the distance into the dash pattern to start the dash. Doesn’t work on Canvas-powered layers in some old browsers.

fill (Bool, False) : Whether to fill the path with color. Set it to false to disable filling on polygons or circles.

fill_color (str, default to color (fillColor)) : Fill color. Defaults to the value of the color option.

fill_opacity (float, 0.2 (fillOpacity)) : Fill opacity.

fill_rule (str, 'evenodd' (fillRule)) : A string that defines how the inside of a shape is determined.

bubbling_mouse_events (Bool, True (bubblingMouseEvents)) : When true a mouse event on this path will trigger the same event on the map (unless L.DomEvent.stopPropagation is used).

3. 코로나19 한국 데이터 분석


# 현재 코로나 검사 현황 데이터(출처 : 질병관리본부)
import pandas as pd
df = pd.read_csv("./data/total.csv", index_col = ["date"])
df.head()


Out[-]
							총계	확진자	격리해제	격리중	사망	검사중	결과 음성
			date
2020-03-01	 96985	 3526	      30	   3479	   17	  32422	     61037
2020-03-02	109591	 4212	      31	   4159  	 22	  33799	     71580
2020-03-03	125851	 4812	      34	   4750	   28	  35555	     85484
2020-03-04	136707	 5328	      41	   5255	   32	  28414	    102965
2020-03-05	146541	 5766	      88	   5643	   35	  21810	    118965


df.tail()


Out[-]
							총계	확진자	격리해제	격리중	사망	검사중	결과 음성
			date							
2020-03-28	387925	 9478	    4811	   4523	   144	16564	    361883
2020-03-29	394141	 9583	    5033	   4398  	 152	15028	    369530
2020-03-30	395194 	 9661	    5228	   4275	   158	13531	    372002
2020-03-31	410564	 9786	    5408	   4216	   162	16892	    383886
2020-04-01	421547	 9887	    5567	   4155	   165	16585	    395075


df.info()


Out[-]
<class 'pandas.core.frame.DataFrame'>
Index: 32 entries, 2020-03-01 to 2020-04-01
Data columns (total 7 columns):
 #   Column  Non-Null Count  Dtype
---  ------  --------------  -----
 0   총계      32 non-null     int64
 1   확진자     32 non-null     int64
 2   격리해제    32 non-null     int64
 3   격리중     32 non-null     int64
 4   사망      32 non-null     int64
 5   검사중     32 non-null     int64
 6   결과 음성   32 non-null     int64
dtypes: int64(7)
memory usage: 2.0+ KB


df.isnull().sum()


Out[-]
총계       0
확진자      0
격리해제     0
격리중      0
사망       0
검사중      0
결과 음성    0
dtype: int64


df.index


Out[-]
Index(['2020-03-01', '2020-03-02', '2020-03-03', '2020-03-04', '2020-03-05',
       '2020-03-06', '2020-03-07', '2020-03-08', '2020-03-09', '2020-03-10',
       '2020-03-11', '2020-03-12', '2020-03-13', '2020-03-14', '2020-03-15',
       '2020-03-16', '2020-03-17', '2020-03-18', '2020-03-19', '2020-03-20',
       '2020-03-21', '2020-03-22', '2020-03-23', '2020-03-24', '2020-03-25',
       '2020-03-26', '2020-03-27', '2020-03-28', '2020-03-29', '2020-03-30',
       '2020-03-31', '2020-04-01'],
      dtype='object', name='date')


df.iloc[:,6]


Out[-]
date
2020-03-01     61037
2020-03-02     71580
2020-03-03     85484
2020-03-04    102965
2020-03-05    118965
2020-03-06    136624
2020-03-07    151802
2020-03-08    162008
2020-03-09    171778
2020-03-10    184179
2020-03-11    196100
2020-03-12    209402
2020-03-13    222728
2020-03-14    235615
2020-03-15    243778
2020-03-16    251297
2020-03-17    261105
2020-03-18    270888
2020-03-19    282555
2020-03-20    292487
2020-03-21    303006
2020-03-22    308343
2020-03-23    315447
2020-03-24    324105
2020-03-25    334481
2020-03-26    341332
2020-03-27    352410
2020-03-28    361883
2020-03-29    369530
2020-03-30    372002
2020-03-31    383886
2020-04-01    395075
Name: 결과 음성, dtype: int64


df.columns[6]


Out[-]
'결과 음성'


df.columns[1]


Out[-]
'확진자'


# 코로나 확진자-음성 그래프
import plotly.graph_objects as go
fig = go.Figure()

fig.add_trace(go.Scatter(x=df.index, 
                         y=df.iloc[:,6], 
                         mode = 'lines+markers', 
                         name='결과 음성'))
fig.add_trace(go.Scatter(x=df.index, 
                         y=df.
                         iloc[:,1], 
                         mode = 'lines+markers', 
                         name='확진자'))

fig.update_layout(title='코로나 양성, 음성', xaxis_title='Day', yaxis_title='count')
fig.show()

Out[-]


# 코로나 확진자-음성 그래프(semi-log)
import plotly.graph_objects as go
fig = go.Figure()

fig.add_trace(go.Scatter(x=df.index, 
                         y=df.iloc[:,6], 
                         mode = 'lines+markers', 
                         name='결과 음성'))
fig.add_trace(go.Scatter(x=df.index, 
                         y=df.
                         iloc[:,1], 
                         mode = 'lines+markers', 
                         name='확진자'))

fig.update_layout(title='코로나 양성, 음성', 
                  xaxis_title='Day', 
                  yaxis_title='count',
                  yaxis_type='log'
                 )
fig.show()

Out[-]


d = df.copy()
d.tail()


Out[-]
							총계	확진자	격리해제	격리중	사망	검사중	결과 음성
			date							
2020-03-28	387925	 9478	    4811	   4523	   144	16564	    361883
2020-03-29	394141	 9583	    5033	   4398  	 152	15028	    369530
2020-03-30	395194 	 9661	    5228	   4275	   158	13531	    372002
2020-03-31	410564	 9786	    5408	   4216	   162	16892	    383886
2020-04-01	421547	 9887	    5567	   4155	   165	16585	    395075


# 치명률 = 사망자수/확진자수 *100
# 완치율 = 격리해제/확진자수 *100
d['치명률'] = round(d.iloc[:,4]/d.iloc[:,1]*100, 2)
d['완치율'] = round(d.iloc[:,2]/d.iloc[:,1]*100, 2)
d.tail()


Out[-]
							총계	확진자	격리해제	격리중	사망	검사중	결과 음성  치명률  완치율
			date							
2020-03-28	387925	 9478	    4811	   4523	   144	16564	    361883    1.52   50.76
2020-03-29	394141	 9583	    5033	   4398  	 152	15028	    369530    1.59   52.52
2020-03-30	395194 	 9661	    5228	   4275	   158	13531	    372002    1.64   54.11
2020-03-31	410564	 9786	    5408	   4216	   162	16892	    383886    1.66   55.26
2020-04-01	421547	 9887	    5567	   4155	   165	16585	    395075    1.67   56.31


d.index


Out[-]
Index(['2020-03-01', '2020-03-02', '2020-03-03', '2020-03-04', '2020-03-05',
       '2020-03-06', '2020-03-07', '2020-03-08', '2020-03-09', '2020-03-10',
       '2020-03-11', '2020-03-12', '2020-03-13', '2020-03-14', '2020-03-15',
       '2020-03-16', '2020-03-17', '2020-03-18', '2020-03-19', '2020-03-20',
       '2020-03-21', '2020-03-22', '2020-03-23', '2020-03-24', '2020-03-25',
       '2020-03-26', '2020-03-27', '2020-03-28', '2020-03-29', '2020-03-30',
       '2020-03-31', '2020-04-01'],
      dtype='object', name='date')


d.iloc[:,7]


Out[-]
date
2020-03-01    0.48
2020-03-02    0.52
2020-03-03    0.58
2020-03-04    0.60
2020-03-05    0.61
2020-03-06    0.67
2020-03-07    0.65
2020-03-08    0.70
2020-03-09    0.69
2020-03-10    0.72
2020-03-11    0.77
2020-03-12    0.84
2020-03-13    0.84
2020-03-14    0.89
2020-03-15    0.92
2020-03-16    0.91
2020-03-17    0.97
2020-03-18    1.00
2020-03-19    1.06
2020-03-20    1.09
2020-03-21    1.16
2020-03-22    1.17
2020-03-23    1.24
2020-03-24    1.33
2020-03-25    1.38
2020-03-26    1.42
2020-03-27    1.49
2020-03-28    1.52
2020-03-29    1.59
2020-03-30    1.64
2020-03-31    1.66
2020-04-01    1.67
Name: 치명률, dtype: float64


d_g = go.Bar(x=d.index, y=d.iloc[:,7])
layout = go.Layout(title='치명율(사망/확진자수)')
fig = go.Figure(data=d_g, layout=layout)
fig.show()

Out[-]


death = go.Bar(x=d.index, y=d.iloc[:,7], name = "치명율")
cure = go.Bar(x=d.index, y=d.iloc[:,8], name = "완치율")
data = cure, death
layout = go.Layout(title="치명율-완치율그래프", barmode='stack')
fig = go.Figure(data=data, layout = layout)
fig.show()

Out[-]


fig = go.Figure()

fig.add_trace(go.Scatter(x=d.index, 
                         y=d.iloc[:,7], 
                         mode = 'lines+markers',
                         name='치명율'))
fig.add_trace(go.Scatter(x=d.index, 
                         y=d.iloc[:,8],
                         mode = 'lines+markers',
                         name='완치율'))

fig.update_layout(title='치명율-완치율 그래프', 
                  xaxis_title='Day', 
                  yaxis_title='count')
fig.show()

Out[-]


today = df.copy()
today.tail()


Out[-]
							총계	확진자	격리해제	격리중	사망	검사중	결과 음성
			date							
2020-03-28	387925	 9478	    4811	   4523	   144	16564	    361883
2020-03-29	394141	 9583	    5033	   4398  	 152	15028	    369530
2020-03-30	395194 	 9661	    5228	   4275	   158	13531	    372002
2020-03-31	410564	 9786	    5408	   4216	   162	16892	    383886
2020-04-01	421547	 9887	    5567	   4155	   165	16585	    395075


print(today.columns[1])
print(today.columns[2])
print(today.columns[4])


Out[-]
확진자
격리해제
사망


일일확진자 = []
일일격리해제 = []
일일사망자 = []


일일확진자.append(595)
일일격리해제.append(3)
일일사망자.append(1)

for i in range(len(today)-1):
    일일확진자.append(today.iloc[:, 1][i+1]-today.iloc[:, 1][i])
    일일격리해제.append(today.iloc[:, 2][i+1]-today.iloc[:, 2][i])
    일일사망자.append(today.iloc[:, 4][i+1]-today.iloc[:, 4][i])
    
일일확진자 = pd.DataFrame(일일확진자, index=today.index)
일일격리해제 = pd.DataFrame(일일격리해제, index=today.index)
일일사망자 = pd.DataFrame(일일사망자, index=today.index)

일일확진자 = 일일확진자.rename(columns={0:'일일확진자'})
일일격리해제 = 일일격리해제.rename(columns={0:'일일격리해제'})
일일사망자 = 일일사망자.rename(columns={0:'일일사망자'})

today = pd.concat([today, 일일확진자, 일일격리해제, 일일사망자], axis=1)
today


Out[-]
							총계	확진자	격리해제	격리중	사망	검사중	결과 음성  일일확진자  일일격리해제  일일사망자
			date							
2020-03-28	387925	 9478	    4811	   4523	   144	16564	    361883         146           283          5
2020-03-29	394141	 9583	    5033	   4398  	 152	15028	    369530         105           222          8
2020-03-30	395194 	 9661	    5228	   4275	   158	13531	    372002          78           195          6
2020-03-31	410564	 9786	    5408	   4216	   162	16892	    383886         125           180          4
2020-04-01	421547	 9887	    5567	   4155	   165	16585	    395075         101           159          3


# 일일확진자-격리해제 그래프
fig=go.Figure()

fig.add_trace(go.Scatter(x=today.index, 
                         y=today.iloc[:,7], 
                         mode = 'lines+markers', 
                         name='일일확진자'))

fig.add_trace(go.Scatter(x=today.index, 
                         y=today.iloc[:,8], 
                         mode = 'lines+markers', 
                         name='일일격리해제'))

fig.update_layout(title='일일확진자-격리해제 그래프', 
                  xaxis_title='Day', 
                  yaxis_title='count')
fig.show()

Out[-]


fig=go.Figure()

t1 = go.Bar(x=today.index, 
            y=today.iloc[:,7], 
            name='일일확진자')

t2 = go.Bar(x=today.index, 
            y=today.iloc[:,8], 
            name='일일격리해제')

data = t2, t1
layout = go.Layout(title='일일확진자-격리해제 그래프', barmode='stack')
fig = go.Figure(data=data, layout=layout)
fig.show()

Out[-]


일일사망자 = today.iloc[:,-1] # 일일사망자
치명률 = d.iloc[ : , -2] # 치명률
치명률


Out[-]
date
2020-03-01    0.48
2020-03-02    0.52
2020-03-03    0.58
2020-03-04    0.60
2020-03-05    0.61
2020-03-06    0.67
2020-03-07    0.65
2020-03-08    0.70
2020-03-09    0.69
2020-03-10    0.72
2020-03-11    0.77
2020-03-12    0.84
2020-03-13    0.84
2020-03-14    0.89
2020-03-15    0.92
2020-03-16    0.91
2020-03-17    0.97
2020-03-18    1.00
2020-03-19    1.06
2020-03-20    1.09
2020-03-21    1.16
2020-03-22    1.17
2020-03-23    1.24
2020-03-24    1.33
2020-03-25    1.38
2020-03-26    1.42
2020-03-27    1.49
2020-03-28    1.52
2020-03-29    1.59
2020-03-30    1.64
2020-03-31    1.66
2020-04-01    1.67
Name: 치명률, dtype: float64


import matplotlib.pyplot as plt

plt.rcParams['figure.figsize']=15,8 # 그래프 크기 
fig , ax = plt.subplots()
plt.xticks(rotation=90)

# ax 막대그래프
ax.bar(death_1.index ,death_1.values, 
         color = 'gray')


ax.set_xlabel("년/월/일")
ax.set_ylabel('사망자(수)')

ax.set_ylim(0 ,10)
# ax1 선그래프
ax1 = ax.twinx() 

ax1.plot(death , 
         color = 'r',
         label = '치명율')

ax1.set_ylim(0.0 , 2)
ax1.set_ylabel('치명율')

plt.title('일일 사망자 현황')

plt.grid(True)  

plt.show()

Out[-]

4. 세계 코로나 현황

자료 출처 : kaggle - https://www.kaggle.com/sudalairajkumar/novel-corona-virus-2019-dataset#time_series_covid_19_confirmed.csv

참고자료 : https://github.com/CSSEGISandData/COVID-19


import pandas as pd

confirmed = pd.read_csv('./data/time_series_covid_19_confirmed.csv')
deaths = pd.read_csv('./data/time_series_covid_19_deaths.csv')
recovered = pd.read_csv('./data/time_series_covid_19_recovered.csv')


confirmed.info()


Out[-]
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 258 entries, 0 to 257
Data columns (total 76 columns):
 #   Column          Non-Null Count  Dtype  
---  ------          --------------  -----  
 0   Province/State  80 non-null     object 
 1   Country/Region  258 non-null    object 
 2   Lat             258 non-null    float64
 3   Long            258 non-null    float64
 4   1/22/20         258 non-null    int64  
 5   1/23/20         258 non-null    int64  
 6   1/24/20         258 non-null    int64  
 7   1/25/20         258 non-null    int64  
 8   1/26/20         258 non-null    int64  
 9   1/27/20         258 non-null    int64  
 10  1/28/20         258 non-null    int64  
 11  1/29/20         258 non-null    int64  
 12  1/30/20         258 non-null    int64  
 13  1/31/20         258 non-null    int64  
 14  2/1/20          258 non-null    int64  
 15  2/2/20          258 non-null    int64  
 16  2/3/20          258 non-null    int64  
 17  2/4/20          258 non-null    int64  
 18  2/5/20          258 non-null    int64  
 19  2/6/20          258 non-null    int64  
 20  2/7/20          258 non-null    int64  
 21  2/8/20          258 non-null    int64  
 22  2/9/20          258 non-null    int64  
 23  2/10/20         258 non-null    int64  
 24  2/11/20         258 non-null    int64  
 25  2/12/20         258 non-null    int64  
 26  2/13/20         258 non-null    int64  
 27  2/14/20         258 non-null    int64  
 28  2/15/20         258 non-null    int64  
 29  2/16/20         258 non-null    int64  
 30  2/17/20         258 non-null    int64  
 31  2/18/20         258 non-null    int64  
 32  2/19/20         258 non-null    int64  
 33  2/20/20         258 non-null    int64  
 34  2/21/20         258 non-null    int64  
 35  2/22/20         258 non-null    int64  
 36  2/23/20         258 non-null    int64  
 37  2/24/20         258 non-null    int64  
 38  2/25/20         258 non-null    int64  
 39  2/26/20         258 non-null    int64  
 40  2/27/20         258 non-null    int64  
 41  2/28/20         258 non-null    int64  
 42  2/29/20         258 non-null    int64  
 43  3/1/20          258 non-null    int64  
 44  3/2/20          258 non-null    int64  
 45  3/3/20          258 non-null    int64  
 46  3/4/20          258 non-null    int64  
 47  3/5/20          258 non-null    int64  
 48  3/6/20          258 non-null    int64  
 49  3/7/20          258 non-null    int64  
 50  3/8/20          258 non-null    int64  
 51  3/9/20          258 non-null    int64  
 52  3/10/20         258 non-null    int64  
 53  3/11/20         258 non-null    int64  
 54  3/12/20         258 non-null    int64  
 55  3/13/20         258 non-null    int64  
 56  3/14/20         258 non-null    int64  
 57  3/15/20         258 non-null    int64  
 58  3/16/20         258 non-null    int64  
 59  3/17/20         258 non-null    int64  
 60  3/18/20         258 non-null    int64  
 61  3/19/20         258 non-null    int64  
 62  3/20/20         258 non-null    int64  
 63  3/21/20         258 non-null    int64  
 64  3/22/20         258 non-null    int64  
 65  3/23/20         258 non-null    int64  
 66  3/24/20         258 non-null    int64  
 67  3/25/20         258 non-null    int64  
 68  3/26/20         258 non-null    int64  
 69  3/27/20         258 non-null    int64  
 70  3/28/20         258 non-null    int64  
 71  3/29/20         258 non-null    int64  
 72  3/30/20         258 non-null    int64  
 73  3/31/20         258 non-null    int64  
 74  4/1/20          258 non-null    int64  
 75  4/2/20          258 non-null    int64  
dtypes: float64(2), int64(72), object(2)
memory usage: 153.3+ KB


confirmed.head()


Out[-]
	Province/State	Country/Region	    Lat	     Long	1/22/20	1/23/20	1/24/20	1/25/20	1/26/20	1/27/20	...	3/28/20	3/29/20	3/30/20	3/31/20	4/1/20	4/2/20
0	          NaN	     Afghanistan	 33.0000	65.0000	      0	      0	      0	      0	      0	      0	...	    110	    120	    170	    174	   237	   273
1	          NaN	         Albania	 41.1533	20.1683	      0	      0	      0	      0	      0	      0	...	    197	    212	    223	    243	   259	   277
2	          NaN	         Algeria	 28.0339	 1.6596	      0	      0	      0	      0	      0	      0	...	    454	    511	    584	    716	   847	   986
3	          NaN	         Andorra	 42.5063	 1.5218	      0	      0	      0	      0	      0	      0	...	    308	    334	    370	    376	   390	   428
4	          NaN	          Angola	-11.2027	17.8739	      0	      0	      0	      0	      0	      0	...	      5	      7	      7	      7	     8	     8

5 rows × 76 columns


confirmed.tail()


Out[-]
		Province/State	Country/Region	       Lat	      Long	1/22/20	1/23/20	1/24/20	1/25/20	1/26/20	1/27/20	...	3/28/20	3/29/20	3/30/20	3/31/20	4/1/20	4/2/20
253	           NaN	      Botswana	-22.328500	 24.684900	      0	      0	      0	      0	      0	      0	...	      0	      0	      3	      4	     4	     4
254	           NaN	       Burundi	 -3.373100	 29.918900	      0	      0	      0	      0	      0	      0	...	      0	      0	      0	      2	     2	     3
255	           NaN	  Sierra Leone	  8.460555	-11.779889	      0	      0	      0	      0	      0	      0	...	      0	      0	      0	      1	     2	     2
   	 Bonaire, Sint 
256  Eustatius and     Netherlands	 12.178400	-68.238500	      0	      0	      0	      0	      0	      0	...	      0	      0	      0	      0	     0	     2
						  Saba	
257	
               NaN	        Malawi	-13.254308	 34.301525	      0	      0	      0	      0	      0	      0	...	      0	      0	      0	      0	     0	     3
5 rows × 76 columns

데이터 전처리


# 데이터 전처리 (Province/State) 제거
confirmed_1 = confirmed.drop(['Province/State'], axis = 1)
deaths_1 = deaths.drop(['Province/State'], axis = 1)
recovered_1 = recovered.drop(['Province/State'], axis = 1)


confirmed_1.head()


Out[-]
	Country/Region	1/22/20	1/23/20	1/24/20	1/25/20	1/26/20	1/27/20	...	3/28/20	3/29/20	3/30/20	3/31/20	4/1/20	4/2/20
0	   Afghanistan	      0	      0	      0	      0	      0	      0	...	    110	    120	    170	    174	   237	   273
1        Albania	      0	      0	      0	      0	      0	      0	...	    197	    212	    223	    243	   259	   277
2	       Algeria	      0	      0	      0	      0	      0	      0	...	    454	    511	    584	    716	   847	   986
3        Andorra	      0	      0	      0	      0	      0	      0	...	    308	    334	    370	    376	   390	   428
4	        Angola	      0	      0	      0	      0	      0	      0	...	      5	      7	      7	      7	     8	     8

5 rows × 75 columns

중복된 Country를 찾고 그룹화 하기


# 중복된 나라 찾기
country = confirmed_2.iloc[:,0]
df = country.value_counts()
df.index[1]
df[0]
# 중복된 나라 1개 초과일 경우
for i in range(len(df)):
    temp = df[i]
    if temp > 1:
        print(df.index[i])


Out[-]
China
Canada
France
United Kingdom
Australia
Netherlands
Denmark


# 중복된 나라 출력하기
confirmed_2.iloc[:,0]
confirmed_2.iloc[:,0].value_counts()


Out[-]
China                  33
Canada                 15
France                 10
United Kingdom         10
Australia               8
                       ..
Congo (Brazzaville)     1
Holy See                1
Armenia                 1
Sweden                  1
Malawi                  1
Name: Country/Region, Length: 181, dtype: int64

중복된 나라 : China, Canada, United Kingdom, France, Australia, Netherlands, Denmark


# 중복된 나라 그룹화 해서 값을 합함
confirmed_3 = confirmed_2.groupby('Country/Region').sum()
deaths_3= deaths_2.groupby('Country/Region').sum()
recovered_3= recovered_2.groupby('Country/Region').sum()


confirmed_3.loc[['China']].T
confirmed_3.loc[['United Kingdom']].T


Out[-]
Country/Region	United Kingdom
			 1/22/20	             0
       1/23/20	             0
       1/24/20	             0
       1/25/20	             0
       1/26/20	             0
           ...	           ...
			 3/28/20	         17312
			 3/29/20	         19780
			 3/30/20	         22453
			 3/31/20	         25481
				4/1/20	         29865
				4/2/20	         34173
72 rows × 1 columns

시각화


confirmed_3.iloc[:, -1]
confirmed_3.iloc[:, -1]['China']


Out[-]
82432


# 4월 2일 기준으로 누적 확진자 데이터
confirmed_4 = confirmed_3.iloc[:, -1 ]
deaths_4 = deaths_3.iloc[:, -1 ]
recovered_4 = recovered_3.iloc[:, -1 ]


df = confirmed_4.sort_values(ascending=False)
df


Out[-]
Country/Region
US                                  243453
Italy                               115242
Spain                               112065
Germany                              84794
China                                82432
                                     ...  
Burundi                                  3
Sierra Leone                             2
Saint Vincent and the Grenadines         2
Papua New Guinea                         1
Timor-Leste                              1
Name: 4/2/20, Length: 181, dtype: int64


import plotly.graph_objects as go
import plotly.express as px

fig = px.bar(confirmed_4, 
             x = confirmed_4.index, 
             y = confirmed_4.values, 
             height = 600)

fig.update_layout(title_text='Covid19 : Confirmed', 
                  xaxis_title='Country', 
                  yaxis_title='confirmed')

fig.show()

Out[-]


import plotly.graph_objects as go
import plotly.express as px

fig = px.bar(df, 
             x = df.index, 
             y = df.values, 
             height = 600)

fig.update_layout(title_text='Covid19 : Confirmed', 
                  xaxis_title='Country', 
                  yaxis_title='confirmed',
                  yaxis_type='log',
                 )

fig.show()

Out[-]


import plotly.graph_objects as go

df1 = confirmed_4.sort_values(ascending=False)
df2 = deaths_4.sort_values(ascending=False)
df3 = recovered_4.sort_values(ascending=False)


fig = go.Figure(
    data = [go.Bar(name = 'confirmed', 
                   x = df1.index, 
                   y = df1.values),
            go.Bar(name = 'deaths', 
                   x = df2.index, 
                   y = df2.values ),
            go.Bar(name = 'recoverd', 
                   x = df3.index, 
                   y = df3.values)])

fig.update_layout(barmode = 'stack', 
                  title_text = '4월 2일 코로나 확진자, 사망자, 완치자',
                  yaxis_type='log',
                 )
fig.show()

Out[-]

Top 15


# 누적 확진자 기준으로 나라 top15를 구한다
# 사망자 데이터, 완치자 데이터 에서 위에 나라의 변수 값을 추출한다. 
confirmed_5 = confirmed_4.sort_values(ascending = False).head(15)
# confirmed_5
confirmed_list15 = []
for i in confirmed_5.index:
    confirmed_list15.append(i)
confirmed_list15


Out[-]
['US',
 'Italy',
 'Spain',
 'Germany',
 'China',
 'France',
 'Iran',
 'United Kingdom',
 'Switzerland',
 'Turkey',
 'Belgium',
 'Netherlands',
 'Canada',
 'Austria',
 'Korea, South']


confirmed_5


Out[-]
Country/Region
US                243453
Italy             115242
Spain             112065
Germany            84794
China              82432
France             59929
Iran               50468
United Kingdom     34173
Switzerland        18827
Turkey             18135
Belgium            15348
Netherlands        14788
Canada             11284
Austria            11129
Korea, South        9976
Name: 4/2/20, dtype: int64


confirmed_5 = pd.DataFrame(confirmed_5)
confirmed_5


Out[-]
								4/2/20
Country/Region	
						US	243453
				 Italy	115242
				 Spain	112065
			 Germany	 84794
				 China	 82432
				France	 59929
					Iran	 50468
United Kingdom	 34173
	 Switzerland	 18827
				Turkey	 18135
			 Belgium	 15348
	 Netherlands	 14788
				Canada	 11284
			 Austria	 11129
	Korea, South	  9976


confirmed_list15

# top 15 누적사망자
deaths_5 = []
for i in confirmed_list15:
    for index, values in enumerate(deaths_4.index):
        if i == values:
            deaths_5.append(deaths_4[index])
            
deaths_5 = pd.DataFrame(deaths_5, 
                        index=confirmed_5.index, 
                        columns=confirmed_5.columns)
deaths_5


Out[-]
								4/2/20
Country/Region	
						US	 7087
				 Italy	14681
				 Spain	11198
			 Germany	 1275
				 China	 3326
				France	 6520
					Iran	 3294
United Kingdom	 3611
	 Switzerland	  591
				Turkey	  425
			 Belgium	 1143
	 Netherlands	 1490
				Canada	  179
			 Austria	  168
  Korea, South	  174


deaths_4
# deaths_4.index
deaths_4[2]


Out[-]
105


for index, values in enumerate(confirmed_list15):
    print(index, values)


Out[-]
0 US
1 Italy
2 Spain
3 Germany
4 China
5 France
6 Iran
7 United Kingdom
8 Switzerland
9 Turkey
10 Belgium
11 Netherlands
12 Canada
13 Austria
14 Korea, South


# top 15 누적완치자
recovered_5  = []
for i in confirmed_list15:
    for index, values in enumerate(recovered_4.index):
        if i == values :
            recovered_5.append(recovered_4[index])

recovered_5 = pd.DataFrame(recovered_5, 
                           index = confirmed_5.index, 
                           columns = confirmed_5.columns)
recovered_5


Out[-]
								4/2/20     
Country/Region	
						US	 9707
				 Italy	19758
				 Spain	30513
			 Germany	24575
				 China	76760
				France	14135
					Iran	17935
United Kingdom	  208
	 Switzerland	 4846
				Turkey	  484
			 Belgium	 2872
	 Netherlands	  260
				Canada	 2175
			 Austria	 2022
  Korea, South	 6021


import plotly.graph_objects as go

fig = go.Figure(
    
data = [go.Bar(name = 'confiremd', 
               x = confirmed_5.index, 
               y = confirmed_5['4/2/20']),

       go.Bar(name = 'deaths', 
              x = deaths_5.index, 
              y = deaths_5['4/2/20'] ),

       go.Bar(name = 'recovered', 
              x = recovered_5.index, 
              y = recovered_5['4/2/20'])])

fig.update_layout(barmode = 'stack', 
                  title_text = ' top 15 : 4월 2일 코로나 확진자, 사망자, 완치자 (수)')
fig.show()

Out[-]

US covid - 19


confirmed_3.loc["US", ]


Out[-]
1/22/20         1
1/23/20         1
1/24/20         2
1/25/20         2
1/26/20         5
            ...  
3/29/20    140886
3/30/20    161807
3/31/20    188172
4/1/20     213372
4/2/20     243453
Name: US, Length: 72, dtype: int64


# 확진자 , 사망자 , 완치자 시계열 막대그래프 
fig = go.Figure()

fig.add_trace(go.Bar(x = confirmed_3.loc["US",].index,
                     y = confirmed_3.loc["US",], 
                     name = 'confirmed'))

fig.add_trace(go.Bar(x = deaths_3.loc["US",].index,
                     y = deaths_3.loc["US",], 
                     name = 'deaths'))

fig.add_trace(go.Bar(x = recovered_3.loc["US",].index,
                     y = recovered_3.loc["US",], 
                     name = 'recovered_3'))

fig.update_layout(yaxis_type='log')

fig.show()

Out[-]


# 확진자 , 사망자 , 완치자 시계열 선그래프 
fig = go.Figure()

fig.add_trace(go.Scatter(x = confirmed_3.loc["US",].index,
                     y = confirmed_3.loc["US",], 
                     mode = 'lines + markers',
                     name = 'confirmed'))

fig.add_trace(go.Scatter(x = deaths_3.loc["US",].index,
                     y = deaths_3.loc["US",], 
                     mode = 'lines + markers',
                     name = 'deaths'))

fig.add_trace(go.Scatter(x = recovered_3.loc["US",].index,
                     y = recovered_3.loc["US",], 
                     mode = 'lines + markers',
                     name = 'recovered_3'))

fig.update_layout(yaxis_type='log')

fig.show()

Out[-]

6일차 코로나 데이터 분석

목차

1. 성별, 나이별

시각화

Plotly

2. 코로나 지역별 분석

Map

옵션값

3. 코로나19 한국 데이터 분석

4. 세계 코로나 현황

데이터 전처리

중복된 Country를 찾고 그룹화 하기

시각화

Top 15

US covid - 19