cococo

코로나 지역별 신규 발생 2020.04.02 ~ 2021.01.27 통계청 자료. 검역은 뺌

a<-read.csv("C:\\rpub\\heat\\co.csv")
a<-a[,2:18]

coco<-cor(a)
coco

##           Seoul        BS        DG      Inch       GWJ        DJ       ULS
## Seoul 1.0000000 0.7960487 0.7472052 0.8906271 0.5178533 0.3824312 0.5791741
## BS    0.7960487 1.0000000 0.6983604 0.7720481 0.4574868 0.3334023 0.6208996
## DG    0.7472052 0.6983604 1.0000000 0.7371724 0.4434784 0.3438807 0.5087012
## Inch  0.8906271 0.7720481 0.7371724 1.0000000 0.5512272 0.3069536 0.5793571
## GWJ   0.5178533 0.4574868 0.4434784 0.5512272 1.0000000 0.2345512 0.2595327
## DJ    0.3824312 0.3334023 0.3438807 0.3069536 0.2345512 1.0000000 0.2679006
## ULS   0.5791741 0.6208996 0.5087012 0.5793571 0.2595327 0.2679006 1.0000000
## SJ    0.4146734 0.3909250 0.2661356 0.3203350 0.3389115 0.2003882 0.1335423
## GYG   0.9431533 0.8328604 0.7723399 0.8993667 0.5528212 0.3772806 0.6326615
## GW    0.7503262 0.6510492 0.6303435 0.7278381 0.4944036 0.2191222 0.4186639
## ChB   0.7918480 0.6764465 0.6617674 0.7392188 0.4396772 0.3236343 0.4726405
## ChN   0.7864302 0.5642072 0.5661150 0.6851659 0.4571165 0.3106908 0.3989441
## JB    0.7226090 0.6330660 0.4936999 0.6713901 0.3342799 0.2486805 0.4130702
## JN    0.4557202 0.3884574 0.2991888 0.4646428 0.4089800 0.1424819 0.2373417
## GB    0.8116617 0.6766275 0.7384251 0.7561137 0.4852427 0.3117651 0.4151834
## GN    0.8022931 0.7582571 0.6744334 0.7656647 0.4853507 0.2691174 0.4874501
## jeju  0.7567685 0.5441710 0.6135068 0.7251055 0.3821465 0.2582764 0.4249709
##              SJ       GYG        GW       ChB       ChN        JB        JN
## Seoul 0.4146734 0.9431533 0.7503262 0.7918480 0.7864302 0.7226090 0.4557202
## BS    0.3909250 0.8328604 0.6510492 0.6764465 0.5642072 0.6330660 0.3884574
## DG    0.2661356 0.7723399 0.6303435 0.6617674 0.5661150 0.4936999 0.2991888
## Inch  0.3203350 0.8993667 0.7278381 0.7392188 0.6851659 0.6713901 0.4646428
## GWJ   0.3389115 0.5528212 0.4944036 0.4396772 0.4571165 0.3342799 0.4089800
## DJ    0.2003882 0.3772806 0.2191222 0.3236343 0.3106908 0.2486805 0.1424819
## ULS   0.1335423 0.6326615 0.4186639 0.4726405 0.3989441 0.4130702 0.2373417
## SJ    1.0000000 0.4039115 0.3672751 0.3242053 0.3523200 0.3087416 0.2771968
## GYG   0.4039115 1.0000000 0.7326641 0.7863971 0.7368146 0.7022246 0.4575498
## GW    0.3672751 0.7326641 1.0000000 0.6094031 0.5798420 0.5158390 0.5850332
## ChB   0.3242053 0.7863971 0.6094031 1.0000000 0.6407485 0.5977440 0.3144791
## ChN   0.3523200 0.7368146 0.5798420 0.6407485 1.0000000 0.5940414 0.3769634
## JB    0.3087416 0.7022246 0.5158390 0.5977440 0.5940414 1.0000000 0.3306591
## JN    0.2771968 0.4575498 0.5850332 0.3144791 0.3769634 0.3306591 1.0000000
## GB    0.3279464 0.8010414 0.6656533 0.7501415 0.7323718 0.5302089 0.3540361
## GN    0.4115537 0.8353018 0.6862454 0.6894104 0.6336291 0.6384182 0.4886497
## jeju  0.1716687 0.7281924 0.5679915 0.7987780 0.6225161 0.5860106 0.2488999
##              GB        GN      jeju
## Seoul 0.8116617 0.8022931 0.7567685
## BS    0.6766275 0.7582571 0.5441710
## DG    0.7384251 0.6744334 0.6135068
## Inch  0.7561137 0.7656647 0.7251055
## GWJ   0.4852427 0.4853507 0.3821465
## DJ    0.3117651 0.2691174 0.2582764
## ULS   0.4151834 0.4874501 0.4249709
## SJ    0.3279464 0.4115537 0.1716687
## GYG   0.8010414 0.8353018 0.7281924
## GW    0.6656533 0.6862454 0.5679915
## ChB   0.7501415 0.6894104 0.7987780
## ChN   0.7323718 0.6336291 0.6225161
## JB    0.5302089 0.6384182 0.5860106
## JN    0.3540361 0.4886497 0.2488999
## GB    1.0000000 0.6756613 0.7733962
## GN    0.6756613 1.0000000 0.6095569
## jeju  0.7733962 0.6095569 1.0000000

상관계수에 따른 시각화 반올림을 안하면 너무 지저분하니 둘째자리까지만 표기

히트맵을 만들기 위해 행렬데이터 만듬

library(reshape2)
melt_coco<-melt(coco)
melt_coco$value<-round(melt_coco$value, digits = 2)

library(ggplot2)

coheat<-ggplot(data = melt_coco, aes(x=Var1, y=Var2, fill=value)) + 
  geom_tile()+
  scale_fill_gradient2(low = "blue", high = "red", mid = "white", midpoint = 0.5, limit = c(0,1), 
                       name="피어슨/상관")
coheat

상관계수를 써 보았다. 전남(JN)은 대전(DJ)하고 별로 안친한가? ㅠㅠ 바로 옆인 광주(GWJ)랑도 .46정도라 좀 놀람 경기(GYG)는 서울하고 .94로 그냥 같다고 볼정도내….

coheat<-ggplot(data = melt_coco, aes(x=Var1, y=Var2, fill=value)) + 
  geom_tile()+
  scale_fill_gradient2(low = "blue", high = "red", mid = "white", midpoint = 0.5, limit = c(0,1), 
                       name="피어슨/상관")+
  ggtitle("지역별 코로나 신규확진자 상관표")+
  theme(plot.title = element_text(face = "bold", size = 25, color = 1))
 
  
  
coheat+
  geom_text(aes(Var2, Var1, label = value), color = "black", size = 3)

cococo

LHJ

2021 1 29