covid analysis
2025-10-16
R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.1 ✔ stringr 1.5.2
## ✔ ggplot2 4.0.0 ✔ tibble 3.3.0
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.1.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(dplyr)
library(ggplot2)
canada_covid19_dataset <- read.csv("D:/2024-2025/georgebrown/2025-fall/Health Information and Data Analysis (4033)/Assign/Group 4/Oct 18/canada_covid19_dataset.csv", stringsAsFactors = FALSE)
Covid19_db <- canada_covid19_dataset
variable.names(Covid19_db)## [1] "pruid" "prname" "prnameFR"
## [4] "date" "reporting_week" "reporting_year"
## [7] "update" "totalcases" "numtotal_last7"
## [10] "ratecases_total" "numdeaths" "numdeaths_last7"
## [13] "ratedeaths" "ratecases_last7" "ratedeaths_last7"
## [16] "numtotal_last14" "numdeaths_last14" "ratetotal_last14"
## [19] "ratedeaths_last14" "avgcases_last7" "avgincidence_last7"
## [22] "avgdeaths_last7" "avgratedeaths_last7"head(Covid19_db, 15)## pruid prname prnameFR date
## 1 59 British Columbia Colombie-Britannique 08-02-2020
## 2 48 Alberta Alberta 08-02-2020
## 3 47 Saskatchewan Saskatchewan 08-02-2020
## 4 46 Manitoba Manitoba 08-02-2020
## 5 35 Ontario Ontario 08-02-2020
## 6 24 Quebec Québec 08-02-2020
## 7 10 Newfoundland and Labrador Terre-Neuve-et-Labrador 08-02-2020
## 8 13 New Brunswick Nouveau-Brunswick 08-02-2020
## 9 12 Nova Scotia Nouvelle-Écosse 08-02-2020
## 10 11 Prince Edward Island Île-du-Prince-Édouard 08-02-2020
## 11 60 Yukon Yukon 08-02-2020
## 12 61 Northwest Territories Territoires du Nord-Ouest 08-02-2020
## 13 62 Nunavut Nunavut 08-02-2020
## 14 99 Repatriated travellers Voyageurs rapatriés 08-02-2020
## 15 1 Canada Canada 08-02-2020
## reporting_week reporting_year update totalcases numtotal_last7
## 1 6 2020 1 4 3
## 2 6 2020 1 0 0
## 3 6 2020 1 0 0
## 4 6 2020 1 0 0
## 5 6 2020 1 4 1
## 6 6 2020 1 0 0
## 7 6 2020 1 0 0
## 8 6 2020 1 0 0
## 9 6 2020 1 0 0
## 10 6 2020 1 0 0
## 11 6 2020 1 0 0
## 12 6 2020 1 0 0
## 13 6 2020 1 0 0
## 14 6 2020 NA 0 0
## 15 6 2020 NA 8 4
## ratecases_total numdeaths numdeaths_last7 ratedeaths ratecases_last7
## 1 0.07 0 0 0 0.05
## 2 0 0 0 0 0
## 3 0 0 0 0 0
## 4 0 0 0 0 0
## 5 0.03 0 0 0 0.01
## 6 0 0 0 0 0
## 7 0 0 0 0 0
## 8 0 0 0 0 0
## 9 0 0 0 0 0
## 10 0 0 0 0 0
## 11 0 0 0 0 0
## 12 0 0 0 0 0
## 13 0 0 0 0 0
## 14 0 0 NA
## 15 0.02 0 0 0 0.01
## ratedeaths_last7 numtotal_last14 numdeaths_last14 ratetotal_last14
## 1 0 4 0 0.07
## 2 0 0 0 0
## 3 0 0 0 0
## 4 0 0 0 0
## 5 0 1 0 0.01
## 6 0 0 0 0
## 7 0 0 0 0
## 8 0 0 0 0
## 9 0 0 0 0
## 10 0 0 0 0
## 11 0 0 0 0
## 12 0 0 0 0
## 13 0 0 0 0
## 14 NA 0 0
## 15 0 5 0 0.01
## ratedeaths_last14 avgcases_last7 avgincidence_last7 avgdeaths_last7
## 1 0 0.43 0.01 0
## 2 0 0 0 0
## 3 0 0 0 0
## 4 0 0 0 0
## 5 0 0.14 0 0
## 6 0 0 0 0
## 7 0 0 0 0
## 8 0 0 0 0
## 9 0 0 0 0
## 10 0 0 0 0
## 11 0 0 0 0
## 12 0 0 0 0
## 13 0 0 0 0
## 14 NA 0 0
## 15 0 0.57 0 0
## avgratedeaths_last7
## 1 0
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0
## 7 0
## 8 0
## 9 0
## 10 0
## 11 0
## 12 0
## 13 0
## 14 NA
## 15 0Covid19_db <- Covid19_db %>%
mutate(across(5:23, as.numeric))## Warning: There were 8 warnings in `mutate()`.
## The first warning was:
## ℹ In argument: `across(5:23, as.numeric)`.
## Caused by warning:
## ! 강제형변환에 의해 생성된 NA 입니다
## ℹ Run `dplyr::last_dplyr_warnings()` to see the 7 remaining warnings.str(Covid19_db)## 'data.frame': 3630 obs. of 23 variables:
## $ pruid : int 59 48 47 46 35 24 10 13 12 11 ...
## $ prname : chr "British Columbia" "Alberta" "Saskatchewan" "Manitoba" ...
## $ prnameFR : chr "Colombie-Britannique" "Alberta" "Saskatchewan" "Manitoba" ...
## $ date : chr "08-02-2020" "08-02-2020" "08-02-2020" "08-02-2020" ...
## $ reporting_week : num 6 6 6 6 6 6 6 6 6 6 ...
## $ reporting_year : num 2020 2020 2020 2020 2020 2020 2020 2020 2020 2020 ...
## $ update : num 1 1 1 1 1 1 1 1 1 1 ...
## $ totalcases : num 4 0 0 0 4 0 0 0 0 0 ...
## $ numtotal_last7 : num 3 0 0 0 1 0 0 0 0 0 ...
## $ ratecases_total : num 0.07 0 0 0 0.03 0 0 0 0 0 ...
## $ numdeaths : num 0 0 0 0 0 0 0 0 0 0 ...
## $ numdeaths_last7 : num 0 0 0 0 0 0 0 0 0 0 ...
## $ ratedeaths : num 0 0 0 0 0 0 0 0 0 0 ...
## $ ratecases_last7 : num 0.05 0 0 0 0.01 0 0 0 0 0 ...
## $ ratedeaths_last7 : num 0 0 0 0 0 0 0 0 0 0 ...
## $ numtotal_last14 : num 4 0 0 0 1 0 0 0 0 0 ...
## $ numdeaths_last14 : num 0 0 0 0 0 0 0 0 0 0 ...
## $ ratetotal_last14 : num 0.07 0 0 0 0.01 0 0 0 0 0 ...
## $ ratedeaths_last14 : num 0 0 0 0 0 0 0 0 0 0 ...
## $ avgcases_last7 : num 0.43 0 0 0 0.14 0 0 0 0 0 ...
## $ avgincidence_last7 : num 0.01 0 0 0 0 0 0 0 0 0 ...
## $ avgdeaths_last7 : num 0 0 0 0 0 0 0 0 0 0 ...
## $ avgratedeaths_last7: num 0 0 0 0 0 0 0 0 0 0 ...Covid19_db$date <- as.Date(Covid19_db$date, format = "%d-%m-%Y")
str(Covid19_db)## 'data.frame': 3630 obs. of 23 variables:
## $ pruid : int 59 48 47 46 35 24 10 13 12 11 ...
## $ prname : chr "British Columbia" "Alberta" "Saskatchewan" "Manitoba" ...
## $ prnameFR : chr "Colombie-Britannique" "Alberta" "Saskatchewan" "Manitoba" ...
## $ date : Date, format: "2020-02-08" "2020-02-08" ...
## $ reporting_week : num 6 6 6 6 6 6 6 6 6 6 ...
## $ reporting_year : num 2020 2020 2020 2020 2020 2020 2020 2020 2020 2020 ...
## $ update : num 1 1 1 1 1 1 1 1 1 1 ...
## $ totalcases : num 4 0 0 0 4 0 0 0 0 0 ...
## $ numtotal_last7 : num 3 0 0 0 1 0 0 0 0 0 ...
## $ ratecases_total : num 0.07 0 0 0 0.03 0 0 0 0 0 ...
## $ numdeaths : num 0 0 0 0 0 0 0 0 0 0 ...
## $ numdeaths_last7 : num 0 0 0 0 0 0 0 0 0 0 ...
## $ ratedeaths : num 0 0 0 0 0 0 0 0 0 0 ...
## $ ratecases_last7 : num 0.05 0 0 0 0.01 0 0 0 0 0 ...
## $ ratedeaths_last7 : num 0 0 0 0 0 0 0 0 0 0 ...
## $ numtotal_last14 : num 4 0 0 0 1 0 0 0 0 0 ...
## $ numdeaths_last14 : num 0 0 0 0 0 0 0 0 0 0 ...
## $ ratetotal_last14 : num 0.07 0 0 0 0.01 0 0 0 0 0 ...
## $ ratedeaths_last14 : num 0 0 0 0 0 0 0 0 0 0 ...
## $ avgcases_last7 : num 0.43 0 0 0 0.14 0 0 0 0 0 ...
## $ avgincidence_last7 : num 0.01 0 0 0 0 0 0 0 0 0 ...
## $ avgdeaths_last7 : num 0 0 0 0 0 0 0 0 0 0 ...
## $ avgratedeaths_last7: num 0 0 0 0 0 0 0 0 0 0 ...avg_total_cases <- function(data, province_name, year) {
data %>%
filter(prname == province_name, format(date, "%Y") == year) %>%
summarise(average_cases = mean(totalcases, na.rm = TRUE))
}
avg_total_cases(Covid19_db, "Ontario", "2021")## average_cases
## 1 486343.9filtered_data <- Covid19_db %>%
filter(prname == "Quebec" & totalcases > 100000)
head(filtered_data)## pruid prname prnameFR date reporting_week reporting_year update
## 1 24 Quebec Québec 2020-11-07 45 2020 1
## 2 24 Quebec Québec 2020-11-14 46 2020 1
## 3 24 Quebec Québec 2020-11-21 47 2020 1
## 4 24 Quebec Québec 2020-11-28 48 2020 1
## 5 24 Quebec Québec 2020-12-05 49 2020 1
## 6 24 Quebec Québec 2020-12-12 50 2020 1
## totalcases numtotal_last7 ratecases_total numdeaths numdeaths_last7
## 1 107784 7824 1214.51 6077 131
## 2 116779 8995 1315.87 6272 195
## 3 124854 8075 1406.86 6453 181
## 4 133886 9032 1508.63 6638 185
## 5 144747 10861 1631.01 6864 226
## 6 156984 12237 1768.90 7100 236
## ratedeaths ratecases_last7 ratedeaths_last7 numtotal_last14 numdeaths_last14
## 1 68.48 88.16 1.48 14497 270
## 2 70.67 101.36 2.20 16819 326
## 3 72.71 90.99 2.04 17070 376
## 4 74.80 101.77 2.08 17107 366
## 5 77.34 122.38 2.55 19893 411
## 6 80.00 137.89 2.66 23098 462
## ratetotal_last14 ratedeaths_last14 avgcases_last7 avgincidence_last7
## 1 163.35 3.04 1117.71 12.59
## 2 189.52 3.67 1285.00 14.48
## 3 192.34 4.24 1153.57 13.00
## 4 192.76 4.12 1290.29 14.54
## 5 224.15 4.63 1551.57 17.48
## 6 260.27 5.21 1748.14 19.70
## avgdeaths_last7 avgratedeaths_last7
## 1 18.71 0.21
## 2 27.86 0.31
## 3 25.86 0.29
## 4 26.43 0.30
## 5 32.29 0.36
## 6 33.71 0.38reshaped_df <- Covid19_db %>%
group_by(Totalcases= totalcases) %>%
reframe(Provinces = prname,
Date = date,
Deaths = sum(numdeaths, na.rm=TRUE))
print(reshaped_df)## # A tibble: 3,630 × 4
## Totalcases Provinces Date Deaths
## <dbl> <chr> <date> <dbl>
## 1 0 Alberta 2020-02-08 0
## 2 0 Saskatchewan 2020-02-08 0
## 3 0 Manitoba 2020-02-08 0
## 4 0 Quebec 2020-02-08 0
## 5 0 Newfoundland and Labrador 2020-02-08 0
## 6 0 New Brunswick 2020-02-08 0
## 7 0 Nova Scotia 2020-02-08 0
## 8 0 Prince Edward Island 2020-02-08 0
## 9 0 Yukon 2020-02-08 0
## 10 0 Northwest Territories 2020-02-08 0
## # ℹ 3,620 more rowsCovid19_db<- na.omit(Covid19_db)
str(Covid19_db)## 'data.frame': 2482 obs. of 23 variables:
## $ pruid : int 59 48 47 46 35 24 10 13 12 11 ...
## $ prname : chr "British Columbia" "Alberta" "Saskatchewan" "Manitoba" ...
## $ prnameFR : chr "Colombie-Britannique" "Alberta" "Saskatchewan" "Manitoba" ...
## $ date : Date, format: "2020-02-08" "2020-02-08" ...
## $ reporting_week : num 6 6 6 6 6 6 6 6 6 6 ...
## $ reporting_year : num 2020 2020 2020 2020 2020 2020 2020 2020 2020 2020 ...
## $ update : num 1 1 1 1 1 1 1 1 1 1 ...
## $ totalcases : num 4 0 0 0 4 0 0 0 0 0 ...
## $ numtotal_last7 : num 3 0 0 0 1 0 0 0 0 0 ...
## $ ratecases_total : num 0.07 0 0 0 0.03 0 0 0 0 0 ...
## $ numdeaths : num 0 0 0 0 0 0 0 0 0 0 ...
## $ numdeaths_last7 : num 0 0 0 0 0 0 0 0 0 0 ...
## $ ratedeaths : num 0 0 0 0 0 0 0 0 0 0 ...
## $ ratecases_last7 : num 0.05 0 0 0 0.01 0 0 0 0 0 ...
## $ ratedeaths_last7 : num 0 0 0 0 0 0 0 0 0 0 ...
## $ numtotal_last14 : num 4 0 0 0 1 0 0 0 0 0 ...
## $ numdeaths_last14 : num 0 0 0 0 0 0 0 0 0 0 ...
## $ ratetotal_last14 : num 0.07 0 0 0 0.01 0 0 0 0 0 ...
## $ ratedeaths_last14 : num 0 0 0 0 0 0 0 0 0 0 ...
## $ avgcases_last7 : num 0.43 0 0 0 0.14 0 0 0 0 0 ...
## $ avgincidence_last7 : num 0.01 0 0 0 0 0 0 0 0 0 ...
## $ avgdeaths_last7 : num 0 0 0 0 0 0 0 0 0 0 ...
## $ avgratedeaths_last7: num 0 0 0 0 0 0 0 0 0 0 ...
## - attr(*, "na.action")= 'omit' Named int [1:1148] 14 15 29 30 44 45 59 60 74 75 ...
## ..- attr(*, "names")= chr [1:1148] "14" "15" "29" "30" ...sum(duplicated(Covid19_db))## [1] 0duplicated(Covid19_db)## [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [13] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [25] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [37] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [49] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [61] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [73] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [85] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [97] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [109] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [121] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [133] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [145] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [157] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [169] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [181] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [193] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [205] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [217] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [229] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [241] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [253] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [265] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [277] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [289] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [301] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [313] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [325] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [337] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [349] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [361] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [373] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [385] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [397] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [409] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [421] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [433] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [445] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [457] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [469] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [481] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [493] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [505] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [517] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [529] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [541] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [553] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [565] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [577] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [589] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [601] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [613] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [625] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [637] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [649] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [661] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [673] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [685] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [697] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [709] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [721] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [733] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [745] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [757] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [769] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [781] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [793] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [805] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [817] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [829] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [841] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [853] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [865] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [877] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [889] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [901] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [913] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [925] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [937] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [949] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [961] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [973] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [985] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [997] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1009] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1021] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1033] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1045] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1057] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1069] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1081] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1093] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1105] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1117] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1129] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1141] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1153] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1165] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1177] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1189] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1201] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1213] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1225] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1237] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1249] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1261] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1273] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1285] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1297] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1309] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1321] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1333] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1345] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1357] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1369] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1381] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1393] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1405] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1417] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1429] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1441] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1453] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1465] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1477] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1489] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1501] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1513] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1525] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1537] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1549] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1561] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1573] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1585] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1597] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1609] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1621] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1633] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1645] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1657] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1669] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1681] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1693] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1705] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1717] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1729] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1741] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1753] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1765] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1777] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1789] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1801] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1813] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1825] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1837] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1849] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1861] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1873] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1885] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1897] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1909] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1921] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1933] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1945] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1957] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1969] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1981] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [1993] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2005] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2017] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2029] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2041] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2053] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2065] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2077] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2089] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2101] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2113] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2125] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2137] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2149] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2161] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2173] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2185] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2197] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2209] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2221] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2233] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2245] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2257] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2269] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2281] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2293] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2305] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2317] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2329] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2341] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2353] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2365] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2377] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2389] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2401] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2413] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2425] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2437] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2449] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2461] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [2473] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSECovid19_db <- Covid19_db %>% arrange(desc(totalcases))
str(Covid19_db)## 'data.frame': 2482 obs. of 23 variables:
## $ pruid : int 35 35 35 35 35 35 35 35 35 35 ...
## $ prname : chr "Ontario" "Ontario" "Ontario" "Ontario" ...
## $ prnameFR : chr "Ontario" "Ontario" "Ontario" "Ontario" ...
## $ date : Date, format: "2024-05-25" "2024-05-18" ...
## $ reporting_week : num 21 20 19 18 17 16 15 14 13 12 ...
## $ reporting_year : num 2024 2024 2024 2024 2024 ...
## $ update : num 1 1 1 1 1 1 1 1 1 1 ...
## $ totalcases : num 1719315 1718344 1717089 1716148 1715259 ...
## $ numtotal_last7 : num 971 1255 941 889 739 ...
## $ ratecases_total : num 11015 11009 11001 10995 10989 ...
## $ numdeaths : num 18683 18665 18653 18642 18637 ...
## $ numdeaths_last7 : num 18 12 11 5 10 14 11 9 7 8 ...
## $ ratedeaths : num 120 120 120 119 119 ...
## $ ratecases_last7 : num 6.22 8.04 6.03 5.7 4.73 4.18 4.56 4.43 3.33 3.88 ...
## $ ratedeaths_last7 : num 0.12 0.08 0.07 0.03 0.06 0.09 0.07 0.06 0.04 0.05 ...
## $ numtotal_last14 : num 2226 2196 1830 1628 1392 ...
## $ numdeaths_last14 : num 30 23 16 15 24 25 20 16 15 19 ...
## $ ratetotal_last14 : num 14.26 14.07 11.72 10.43 8.92 ...
## $ ratedeaths_last14 : num 0.19 0.15 0.1 0.1 0.15 0.16 0.13 0.1 0.1 0.12 ...
## $ avgcases_last7 : num 139 179 134 127 106 ...
## $ avgincidence_last7 : num 0.89 1.15 0.86 0.81 0.68 0.6 0.65 0.63 0.48 0.55 ...
## $ avgdeaths_last7 : num 2.57 1.71 1.57 0.71 1.43 2 1.57 1.29 1 1.14 ...
## $ avgratedeaths_last7: num 0.02 0.01 0.01 0 0.01 0.01 0.01 0.01 0.01 0.01 ...
## - attr(*, "na.action")= 'omit' Named int [1:1148] 14 15 29 30 44 45 59 60 74 75 ...
## ..- attr(*, "names")= chr [1:1148] "14" "15" "29" "30" ...Covid19_db <- Covid19_db %>%
rename(
Province = prname,
Total_Cases = totalcases,
Total_Deaths = numdeaths
)
str(Covid19_db)## 'data.frame': 2482 obs. of 23 variables:
## $ pruid : int 35 35 35 35 35 35 35 35 35 35 ...
## $ Province : chr "Ontario" "Ontario" "Ontario" "Ontario" ...
## $ prnameFR : chr "Ontario" "Ontario" "Ontario" "Ontario" ...
## $ date : Date, format: "2024-05-25" "2024-05-18" ...
## $ reporting_week : num 21 20 19 18 17 16 15 14 13 12 ...
## $ reporting_year : num 2024 2024 2024 2024 2024 ...
## $ update : num 1 1 1 1 1 1 1 1 1 1 ...
## $ Total_Cases : num 1719315 1718344 1717089 1716148 1715259 ...
## $ numtotal_last7 : num 971 1255 941 889 739 ...
## $ ratecases_total : num 11015 11009 11001 10995 10989 ...
## $ Total_Deaths : num 18683 18665 18653 18642 18637 ...
## $ numdeaths_last7 : num 18 12 11 5 10 14 11 9 7 8 ...
## $ ratedeaths : num 120 120 120 119 119 ...
## $ ratecases_last7 : num 6.22 8.04 6.03 5.7 4.73 4.18 4.56 4.43 3.33 3.88 ...
## $ ratedeaths_last7 : num 0.12 0.08 0.07 0.03 0.06 0.09 0.07 0.06 0.04 0.05 ...
## $ numtotal_last14 : num 2226 2196 1830 1628 1392 ...
## $ numdeaths_last14 : num 30 23 16 15 24 25 20 16 15 19 ...
## $ ratetotal_last14 : num 14.26 14.07 11.72 10.43 8.92 ...
## $ ratedeaths_last14 : num 0.19 0.15 0.1 0.1 0.15 0.16 0.13 0.1 0.1 0.12 ...
## $ avgcases_last7 : num 139 179 134 127 106 ...
## $ avgincidence_last7 : num 0.89 1.15 0.86 0.81 0.68 0.6 0.65 0.63 0.48 0.55 ...
## $ avgdeaths_last7 : num 2.57 1.71 1.57 0.71 1.43 2 1.57 1.29 1 1.14 ...
## $ avgratedeaths_last7: num 0.02 0.01 0.01 0 0.01 0.01 0.01 0.01 0.01 0.01 ...
## - attr(*, "na.action")= 'omit' Named int [1:1148] 14 15 29 30 44 45 59 60 74 75 ...
## ..- attr(*, "names")= chr [1:1148] "14" "15" "29" "30" ...Covid19_db <- Covid19_db %>%
mutate(Double_Cases = Total_Cases * 2)
set.seed(111)
train_rows <- sample(1:nrow(Covid19_db), 0.7 * nrow(Covid19_db))
training_set <- Covid19_db[train_rows, ]
summary(Covid19_db)## pruid Province prnameFR date
## Min. :10.00 Length:2482 Length:2482 Min. :2020-02-08
## 1st Qu.:13.00 Class :character Class :character 1st Qu.:2021-01-02
## Median :46.00 Mode :character Mode :character Median :2021-12-04
## Mean :35.92 Mean :2022-01-09
## 3rd Qu.:48.00 3rd Qu.:2022-12-10
## Max. :62.00 Max. :2024-05-25
## reporting_week reporting_year update Total_Cases numtotal_last7
## Min. : 1.00 Min. :2020 Min. :1 Min. : 0 Min. : 0
## 1st Qu.:13.00 1st Qu.:2020 1st Qu.:1 1st Qu.: 1141 1st Qu.: 25
## Median :25.00 Median :2021 Median :1 Median : 56413 Median : 310
## Mean :25.66 Mean :2022 Mean :1 Mean : 246615 Mean : 1994
## 3rd Qu.:39.00 3rd Qu.:2022 3rd Qu.:1 3rd Qu.: 243424 3rd Qu.: 1519
## Max. :53.00 Max. :2024 Max. :1 Max. :1719315 Max. :108671
## ratecases_total Total_Deaths numdeaths_last7 ratedeaths
## Min. : 0.0 Min. : 0.0 Min. : -1.00 Min. : 0.000
## 1st Qu.: 200.3 1st Qu.: 10.0 1st Qu.: 0.00 1st Qu.: 3.397
## Median : 4390.8 Median : 474.5 Median : 4.00 Median : 46.915
## Mean : 6368.4 Mean : 3121.9 Mean : 23.93 Mean : 59.915
## 3rd Qu.:10763.6 3rd Qu.: 3559.0 3rd Qu.: 23.00 3rd Qu.:105.085
## Max. :33703.3 Max. :20100.0 Max. :838.00 Max. :226.490
## ratecases_last7 ratedeaths_last7 numtotal_last14 numdeaths_last14
## Min. : 0.00 Min. :-0.0800 Min. : 0 Min. : -1.00
## 1st Qu.: 4.08 1st Qu.: 0.0000 1st Qu.: 54 1st Qu.: 0.00
## Median : 17.60 Median : 0.2500 Median : 618 Median : 9.00
## Mean : 75.46 Mean : 0.5788 Mean : 3986 Mean : 47.79
## 3rd Qu.: 66.64 3rd Qu.: 0.7600 3rd Qu.: 3058 3rd Qu.: 47.00
## Max. :2132.44 Max. :11.2600 Max. :211900 Max. :1587.00
## ratetotal_last14 ratedeaths_last14 avgcases_last7 avgincidence_last7
## Min. : 0.000 Min. :-0.080 Min. : 0.000 Min. : 0.000
## 1st Qu.: 8.715 1st Qu.: 0.000 1st Qu.: 3.575 1st Qu.: 0.580
## Median : 34.550 Median : 0.580 Median : 44.290 Median : 2.515
## Mean : 150.797 Mean : 1.150 Mean : 284.823 Mean : 10.779
## 3rd Qu.: 133.317 3rd Qu.: 1.617 3rd Qu.: 217.015 3rd Qu.: 9.518
## Max. :4142.580 Max. :17.880 Max. :15524.430 Max. :304.540
## avgdeaths_last7 avgratedeaths_last7 Double_Cases
## Min. : -0.140 Min. :-0.01000 Min. : 0
## 1st Qu.: 0.000 1st Qu.: 0.00000 1st Qu.: 2282
## Median : 0.570 Median : 0.04000 Median : 112825
## Mean : 3.419 Mean : 0.08264 Mean : 493230
## 3rd Qu.: 3.290 3rd Qu.: 0.11000 3rd Qu.: 486848
## Max. :119.710 Max. : 1.61000 Max. :3438630mean(Covid19_db$Total_Cases, na.rm = TRUE)## [1] 246615median(Covid19_db$Total_Cases, na.rm = TRUE)## [1] 56412.5Mode <- as.numeric(names(sort(table(Covid19_db$Total_Cases), decreasing = TRUE)[1]))
Range <- range(Covid19_db$Total_Cases, na.rm = TRUE)
cat("Mode:", Mode, "\n")## Mode: 0cat("Range:", Range, "\n")## Range: 0 1719315Including Plots
You can also embed plots, for example:
library(ggpubr)
ggscatter(Covid19_db, x = "Total_Cases", y = "Total_Deaths",
color = "Province",
palette = "jco",
add = "reg.line", conf.int = TRUE,
cor.coef = TRUE, cor.method = "pearson",
xlab = "Total COVID-19 Cases", ylab = "Total Deaths")
# Aggregate total cases by province
Covid19_summary <- Covid19_db %>%
group_by(Province) %>%
summarise(Total_Cases = sum(Total_Cases, na.rm = TRUE))
# Plot
ggbarplot(Covid19_summary, x = "Province", y = "Total_Cases",
fill = "Province",
palette = get_palette("Set3", length(unique(Covid19_summary$Province))),
sort.val = "desc", rotate = TRUE,
xlab = "Province", ylab = "Total Reported Cases (Millions)",
title = "Total COVID-19 Cases by Province",
subtitle = "Cumulative totals (2020–2024)") +
scale_y_continuous(labels = function(x) paste0(x / 1e6, "M")) +
theme_minimal()
# Run the correlation test
cor_result <- cor.test(Covid19_db$Total_Cases, Covid19_db$Total_Deaths, method = "pearson", use = "complete.obs")
# Extract the correlation coefficient
correlation_value <- cor_result$estimate
# Print the result
cat("Pearson Correlation between cases and deaths:", round(correlation_value, 3), "\n")## Pearson Correlation between cases and deaths: 0.96Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.