Trends

df_total <-nordic%>% 
  mutate(date = as.Date(date)) %>% 
  mutate(ym = format(date, '%y-%m')) %>%
  group_by(ym) %>%
  summarize(ym_cases = sum(new_cases),
            ym_deaths=sum(new_deaths))


head(df_total,14)

## # A tibble: 14 x 3
##    ym    ym_cases ym_deaths
##    <chr>    <int>     <int>
##  1 20-02    12270       765
##  2 20-03    15031       703
##  3 20-04    30420      2936
##  4 20-05    22148      2066
##  5 20-06    31174       991
##  6 20-07    10852       426
##  7 20-08    13103       103
##  8 20-09    25325       116
##  9 20-10    64438       140
## 10 20-11   178058       964
## 11 20-12   302338      2776
## 12 21-01   187396      3930
## 13 21-02   123600      1600
## 14 21-03   160415       676

df_total<-as.data.frame(df_total)
str(df_total)#chek date format

## 'data.frame':    14 obs. of  3 variables:
##  $ ym       : chr  "20-02" "20-03" "20-04" "20-05" ...
##  $ ym_cases : int  12270 15031 30420 22148 31174 10852 13103 25325 64438 178058 ...
##  $ ym_deaths: int  765 703 2936 2066 991 426 103 116 140 964 ...

df_total %>%
  gt()

ym	ym_cases	ym_deaths
20-02	12270	765
20-03	15031	703
20-04	30420	2936
20-05	22148	2066
20-06	31174	991
20-07	10852	426
20-08	13103	103
20-09	25325	116
20-10	64438	140
20-11	178058	964
20-12	302338	2776
21-01	187396	3930
21-02	123600	1600
21-03	160415	676

df_total %>%
  gt(rownames_to_stub = )

ym	ym_cases	ym_deaths
20-02	12270	765
20-03	15031	703
20-04	30420	2936
20-05	22148	2066
20-06	31174	991
20-07	10852	426
20-08	13103	103
20-09	25325	116
20-10	64438	140
20-11	178058	964
20-12	302338	2776
21-01	187396	3930
21-02	123600	1600
21-03	160415	676

#Grouped by  months first
df1 <-nordic%>% 
  mutate(date = as.Date(date)) %>% 
  mutate(ym = format(date, '%y-%m')) %>% 
  group_by(ym,location) %>% 
  summarize(ym_cases = sum(new_cases),
            ym_deaths=sum(new_deaths))
head(df1,14) 

## # A tibble: 14 x 4
## # Groups:   ym [3]
##    ym    location ym_cases ym_deaths
##    <chr> <chr>       <int>     <int>
##  1 20-02 Denmark     10435       382
##  2 20-02 Finland         2        50
##  3 20-02 Iceland       453        29
##  4 20-02 Norway       1366       188
##  5 20-02 Sweden         14       116
##  6 20-03 Denmark      3036       138
##  7 20-03 Finland      1415        40
##  8 20-03 Iceland      1134        71
##  9 20-03 Norway       4626        57
## 10 20-03 Sweden       4820       397
## 11 20-04 Denmark      6317       362
## 12 20-04 Finland      3577       194
## 13 20-04 Iceland       662         8
## 14 20-04 Norway       3097       171

df1<-as.data.frame(df1)

#ym(df$ym )

#Grouping by country first

df2 <-nordic%>% 
  mutate(date = as.Date(date)) %>% 
  mutate(ym = format(date, '%Y-%m')) %>% 
  group_by(location,ym) %>% 
  summarize(ym_cases = sum(new_cases),
            ym_deaths=sum(new_deaths),
            rate=round(sum(new_deaths)/sum(new_cases),digits=2))
head(df2)

## # A tibble: 6 x 5
## # Groups:   location [1]
##   location ym      ym_cases ym_deaths  rate
##   <chr>    <chr>      <int>     <int> <dbl>
## 1 Denmark  2020-02    10435       382  0.04
## 2 Denmark  2020-03     3036       138  0.05
## 3 Denmark  2020-04     6317       362  0.06
## 4 Denmark  2020-05     2513       122  0.05
## 5 Denmark  2020-06     1099        31  0.03
## 6 Denmark  2020-07     1060        10  0.01

df2=as.data.frame(df2)
str(df2) #To check to ym is in character format

## 'data.frame':    70 obs. of  5 variables:
##  $ location : chr  "Denmark" "Denmark" "Denmark" "Denmark" ...
##  $ ym       : chr  "2020-02" "2020-03" "2020-04" "2020-05" ...
##  $ ym_cases : int  10435 3036 6317 2513 1099 1060 3382 11069 18384 34139 ...
##  $ ym_deaths: int  382 138 362 122 31 10 9 26 71 116 ...
##  $ rate     : num  0.04 0.05 0.06 0.05 0.03 0.01 0 0 0 0 ...

#note that with as.Date requires a day, so, I'll set them to the first day of the year for this purpose
df2$ym<-as.Date(paste(df2$ym,"-01",sep=""))
df2

##    location         ym ym_cases ym_deaths  rate
## 1   Denmark 2020-02-01    10435       382  0.04
## 2   Denmark 2020-03-01     3036       138  0.05
## 3   Denmark 2020-04-01     6317       362  0.06
## 4   Denmark 2020-05-01     2513       122  0.05
## 5   Denmark 2020-06-01     1099        31  0.03
## 6   Denmark 2020-07-01     1060        10  0.01
## 7   Denmark 2020-08-01     3382         9  0.00
## 8   Denmark 2020-09-01    11069        26  0.00
## 9   Denmark 2020-10-01    18384        71  0.00
## 10  Denmark 2020-11-01    34139       116  0.00
## 11  Denmark 2020-12-01    83114       461  0.01
## 12  Denmark 2021-01-01    35040       828  0.02
## 13  Denmark 2021-02-01    12727       236  0.02
## 14  Denmark 2021-03-01    16703        44  0.00
## 15  Finland 2020-02-01        2        50 25.00
## 16  Finland 2020-03-01     1415        40  0.03
## 17  Finland 2020-04-01     3577       194  0.05
## 18  Finland 2020-05-01     1864       109  0.06
## 19  Finland 2020-06-01      355         8  0.02
## 20  Finland 2020-07-01      218         1  0.00
## 21  Finland 2020-08-01      654         7  0.01
## 22  Finland 2020-09-01     1906         8  0.00
## 23  Finland 2020-10-01     6121        14  0.00
## 24  Finland 2020-11-01     8799        41  0.00
## 25  Finland 2020-12-01    11195       162  0.01
## 26  Finland 2021-01-01     9131       110  0.01
## 27  Finland 2021-02-01    12434        71  0.01
## 28  Finland 2021-03-01    15844        67  0.00
## 29  Iceland 2020-02-01      453        29  0.06
## 30  Iceland 2020-03-01     1134        71  0.06
## 31  Iceland 2020-04-01      662         8  0.01
## 32  Iceland 2020-05-01        9         0  0.00
## 33  Iceland 2020-06-01       18         0  0.00
## 34  Iceland 2020-07-01       61         0  0.00
## 35  Iceland 2020-08-01      222         0  0.00
## 36  Iceland 2020-09-01      621         0  0.00
## 37  Iceland 2020-10-01     2137         2  0.00
## 38  Iceland 2020-11-01      527        14  0.03
## 39  Iceland 2020-12-01      362         3  0.01
## 40  Iceland 2021-01-01      248         0  0.00
## 41  Iceland 2021-02-01       47         0  0.00
## 42  Iceland 2021-03-01       95         0  0.00
## 43   Norway 2020-02-01     1366       188  0.14
## 44   Norway 2020-03-01     4626        57  0.01
## 45   Norway 2020-04-01     3097       171  0.06
## 46   Norway 2020-05-01      702        26  0.04
## 47   Norway 2020-06-01      439        14  0.03
## 48   Norway 2020-07-01      361         5  0.01
## 49   Norway 2020-08-01     1542         9  0.01
## 50   Norway 2020-09-01     3245        10  0.00
## 51   Norway 2020-10-01     6304         8  0.00
## 52   Norway 2020-11-01    15819        50  0.00
## 53   Norway 2020-12-01    13417       104  0.01
## 54   Norway 2021-01-01    13399       128  0.01
## 55   Norway 2021-02-01     8040        58  0.01
## 56   Norway 2021-03-01    19098        34  0.00
## 57   Sweden 2020-02-01       14       116  8.29
## 58   Sweden 2020-03-01     4820       397  0.08
## 59   Sweden 2020-04-01    16767      2201  0.13
## 60   Sweden 2020-05-01    17060      1809  0.11
## 61   Sweden 2020-06-01    29263       938  0.03
## 62   Sweden 2020-07-01     9152       410  0.04
## 63   Sweden 2020-08-01     7303        78  0.01
## 64   Sweden 2020-09-01     8484        72  0.01
## 65   Sweden 2020-10-01    31492        45  0.00
## 66   Sweden 2020-11-01   118774       743  0.01
## 67   Sweden 2020-12-01   194250      2046  0.01
## 68   Sweden 2021-01-01   129578      2864  0.02
## 69   Sweden 2021-02-01    90352      1235  0.01
## 70   Sweden 2021-03-01   108675       531  0.00

df.2 <-nordic%>% 
  mutate(date = as.Date(date)) %>% 
  mutate(ym = format(date, '%Y-%m')) %>% 
  group_by(location,ym) %>% 
  summarize(ym_cases = sum(new_cases),
            ym_deaths=sum(new_deaths),
            rate=round(sum(new_deaths)/sum(new_cases),digits=2),
            survival=round((1-rate),digits=2))
head(df.2)

## # A tibble: 6 x 6
## # Groups:   location [1]
##   location ym      ym_cases ym_deaths  rate survival
##   <chr>    <chr>      <int>     <int> <dbl>    <dbl>
## 1 Denmark  2020-02    10435       382  0.04     0.96
## 2 Denmark  2020-03     3036       138  0.05     0.95
## 3 Denmark  2020-04     6317       362  0.06     0.94
## 4 Denmark  2020-05     2513       122  0.05     0.95
## 5 Denmark  2020-06     1099        31  0.03     0.97
## 6 Denmark  2020-07     1060        10  0.01     0.99

 #survival=round((1-(sum(new_deaths)/sum(new_cases))),digits=2))

df.2=as.data.frame(df.2)
str(df.2) #To check to ym is in character format

## 'data.frame':    70 obs. of  6 variables:
##  $ location : chr  "Denmark" "Denmark" "Denmark" "Denmark" ...
##  $ ym       : chr  "2020-02" "2020-03" "2020-04" "2020-05" ...
##  $ ym_cases : int  10435 3036 6317 2513 1099 1060 3382 11069 18384 34139 ...
##  $ ym_deaths: int  382 138 362 122 31 10 9 26 71 116 ...
##  $ rate     : num  0.04 0.05 0.06 0.05 0.03 0.01 0 0 0 0 ...
##  $ survival : num  0.96 0.95 0.94 0.95 0.97 0.99 1 1 1 1 ...

#note that with as.Date requires a day, so, I'll set them to the first day of the year for this purpose
df.2$ym<-as.Date(paste(df.2$ym,"-01",sep=""))

#https://gt.rstudio.com/articles/gt-datasets.html    

# Create a gt table based on a preprocessed `yearmonth from tdyr
#df3

df_wider1<-df2 %>%
  pivot_wider(
    names_from = ym, values_from = c(ym_cases, ym_deaths))
colnames(df_wider1)

##  [1] "location"             "rate"                 "ym_cases_2020-02-01" 
##  [4] "ym_cases_2020-03-01"  "ym_cases_2020-04-01"  "ym_cases_2020-05-01" 
##  [7] "ym_cases_2020-06-01"  "ym_cases_2020-07-01"  "ym_cases_2020-08-01" 
## [10] "ym_cases_2020-09-01"  "ym_cases_2020-10-01"  "ym_cases_2020-11-01" 
## [13] "ym_cases_2020-12-01"  "ym_cases_2021-01-01"  "ym_cases_2021-02-01" 
## [16] "ym_cases_2021-03-01"  "ym_deaths_2020-02-01" "ym_deaths_2020-03-01"
## [19] "ym_deaths_2020-04-01" "ym_deaths_2020-05-01" "ym_deaths_2020-06-01"
## [22] "ym_deaths_2020-07-01" "ym_deaths_2020-08-01" "ym_deaths_2020-09-01"
## [25] "ym_deaths_2020-10-01" "ym_deaths_2020-11-01" "ym_deaths_2020-12-01"
## [28] "ym_deaths_2021-01-01" "ym_deaths_2021-02-01" "ym_deaths_2021-03-01"

library(data.table)
df_wider<-setnames(df_wider1, old = c(
"ym_cases_2020-02-01", "ym_cases_2020-03-01", "ym_cases_2020-04-01",
"ym_cases_2020-05-01", "ym_cases_2020-06-01", "ym_cases_2020-07-01", "ym_cases_2020-08-01", 
"ym_cases_2020-09-01", "ym_cases_2020-10-01", "ym_cases_2020-11-01", "ym_cases_2020-12-01",
"ym_cases_2021-01-01", "ym_cases_2021-02-01", "ym_cases_2021-03-01", "ym_deaths_2020-02-01",
"ym_deaths_2020-03-01", "ym_deaths_2020-04-01", "ym_deaths_2020-05-01", "ym_deaths_2020-06-01",
"ym_deaths_2020-07-01", "ym_deaths_2020-08-01", "ym_deaths_2020-09-01", "ym_deaths_2020-10-01",
"ym_deaths_2020-11-01", "ym_deaths_2020-12-01", "ym_deaths_2021-01-01", "ym_deaths_2021-02-01",
"ym_deaths_2021-03-01"),
new = c(
  "Feb, 2020",
"Mar, 2020",
"Apr, 2020",
"May, 2020",
"Jun, 2020",
"Jul, 2020",
"Aug, 2020",
"Sep, 2020",
"Oct, 2020",
"Nov, 2020",
"Dec, 2020",
"Jan, 2021",
"Feb, 2021",
"Mar, 2021",
"Feb, 2020",
"Mar, 2020",
"Apr, 2020",
"May, 2020",
"Jun, 2020",
"Jul, 2020",
"Aug, 2020",
"Sep, 2020",
"Oct, 2020",
"Nov, 2020",
"Dec, 2020",
"Jan, 2021",
"Feb, 2021",
"Mar, 2021"))
#(df_wider)

DF=df2
names(DF)[names(DF) == "location"] <- "Country"
names(DF)[names(DF) == "ym"] <- "Date"
names(DF)[names(DF) == "ym_cases"] <- "Cases"
names(DF)[names(DF) == "ym_deaths"] <- "Deaths"




p=ggplot(data = DF, aes(x = Date, y = Cases, group=Country, colour=Country))+
  geom_vline(xintercept=as.numeric(DF$Date[yday(DF$Date)==1]), colour="grey80") +
  geom_line(size = 1.2, show.legend = T)+ scale_x_date(date_labels="%b", date_breaks="month", expand=c(0,0)) +
  theme_bw() 
p

p1=p+scale_y_continuous(labels = scales::comma)+theme(axis.text.x=element_text(size=8))+ labs(x = " ", y="", title = "COVID-19 cases in Nordic countries", subtitle = "Monthly amounts from 2020 to 2021",
       caption = "Source: https://ourworldindata.org/, March 2021")+ theme(plot.caption = element_text(color = "gray", face = "italic"))
p1

p1

#unnecesary to set panel.background = element_blank()
p2<-p1+theme(panel.grid = element_blank(), axis.line=element_line(colour="gray"), axis.ticks.y=element_blank(),panel.border = element_blank())
#?element_line
p2

#color

  
p3=p2+scale_color_manual(values = c("#034e7b", "#3690c0", "#74a9cf", "#a6bddb", "#d8d6dd")) +theme(legend.position = "top", legend.direction = "horizontal", legend.title = element_blank())

This plot shows the sum of total cases reported in Nordic countries by month. The date range begins from February 2020 up to March 2021.A vertical line represents the beginning of 2021.

Here is an intercative version of the previous plot.

p=ggplot(data = DF, aes(x = Date, y = Deaths, group=Country, colour=Country))+
  geom_vline(xintercept=as.numeric(DF$Date[yday(DF$Date)==1]), colour="grey80") +
  geom_line(size = 1)+ scale_x_date(date_labels="%b", date_breaks="month", expand=c(0,0)) +
  theme_bw() 
p

p1=p+scale_y_continuous(labels = scales::comma)+theme(axis.text.x=element_text(size=8))+ labs(x = " ", y="", title = "COVID-19 death cases in Nordic countries", subtitle = "Monthly amounts from 2020 to 2021",
       caption = "Source: https://ourworldindata.org/, March 2021")+ theme(plot.caption = element_text(color = "gray", face = "italic"))
p1

p1

#unnecesary to set panel.background = element_blank()
p2<-p1+theme(panel.grid = element_blank(), axis.line=element_line(colour="gray"), axis.ticks.y=element_blank(),panel.border = element_blank())

p2

#color
p3=p2+scale_color_manual(values = c("#034e7b", "#3690c0", "#74a9cf", "#a6bddb", "#d8d6dd")) +theme(legend.position = "top", legend.direction = "horizontal", legend.title = element_blank())

Another trend we can look at is the total number of Coronavirus deaths per Nordic country. Also displyed in a monthly basis. An interactive version is right below.

p3

library(plotly)
ggplotly(p3)

DF=df.2
names(DF)[names(DF) == "location"] <- "Country"
names(DF)[names(DF) == "ym"] <- "Date"
names(DF)[names(DF) == "ym_cases"] <- "Cases"
names(DF)[names(DF) == "ym_deaths"] <- "Deaths"
names(DF)[names(DF)=="rate"]<-"Rate"
names(DF)[names(DF)=="survival"]<-"Survival"
#DF$Survival=as.numeric(DF$Survival)



#DF[which(DF$Rate=='8.29'|  DF$Rate=='25'),]
ind<-DF[which(DF$Rate=='8.29'|  DF$Rate=='25'),] #rows: 15, 57
DF2<-DF[-c(15,57),]


p=ggplot(data = DF2, aes(x = Date, y = Survival, group=Country, colour=Country))+
  geom_vline(xintercept=as.numeric(DF2$Date[yday(DF2$Date)==1]), colour="grey80") +
  geom_line(size = 1)+ scale_x_date(date_labels="%b", date_breaks="month", expand=c(0,0)) +
  theme_bw() 
p

p1=p+scale_y_continuous(labels = scales::percent_format(accuracy=1)) +theme(axis.text.x=element_text(size=8))+ labs(x = " ", y="", title = "COVID-19 survival rate in Nordic countries", subtitle = "Monthly rates from 2020 to 2021",
       caption = "Source: https://ourworldindata.org/, March 2021")+ theme(plot.caption = element_text(color = "gray", face = "italic"))
p1

#unnecesary to set panel.background = element_blank()
p2<-p1+theme(panel.grid = element_blank(), axis.line=element_line(colour="gray"), axis.ticks.y=element_blank(),panel.border = element_blank())

p2

#color
p3=p2+scale_color_manual(values = c("#034e7b", "#3690c0", "#74a9cf", "#a6bddb", "#d8d6dd")) +theme(legend.position = "top", legend.direction = "horizontal", legend.title = element_blank())

More over, there is an important relationship to stand out: survival rate. This graph shows the percentage of cases that successfully recover. In Nordic countries, this rate is very high. Overtime, they converge to 100%.

p3

library(plotly)
ggplotly(p3)

The change in the trend mentioned above is displayed considering the rate at the begining of the pandemic vs the most recent data.

library(scales)
newdata <- subset(DF2, Date=="2020-03-01" | Date=='2021-03-01',
select=c(Country,Date,Cases,Deaths, Rate, Survival),)

#newdata
p<-ggplot(data = newdata, aes(x = Date, y = Survival, group = Country)) +
  geom_line(aes(color = Country), size = 1) +
  
  scale_x_date(date_labels="%b,%Y") 
p

p1=p+scale_y_continuous(labels = scales::percent_format(accuracy=1)) +theme(axis.text.x=element_text(size=8))+ labs(x = " ", y="", title = "COVID-19 survival rate in Nordic countries", subtitle = "A year comparison (From March 2020 to March 2021)",
       caption = "Source: https://ourworldindata.org/, March 2021")+ theme(plot.caption = element_text(color = "gray", face = "italic"))
p1

p1

#unnecesary to set panel.background = element_blank()
p2<-p1+theme(panel.grid = element_blank(), axis.line=element_line(colour="gray"), axis.ticks.y=element_blank(),panel.border = element_blank())

p2

#color
p3=p2+scale_color_manual(values = c("#034e7b", "#3690c0", "#74a9cf", "#a6bddb", "#d8d6dd")) +theme(legend.position = "top", legend.direction = "horizontal", legend.title = element_blank())

p3