Covid19_Project

R Markdown

First Data analysis project in R.

Which countries have had the highest number of positive cases against the number of tests?

library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6      ✔ purrr   0.3.5 
## ✔ tibble  3.1.8      ✔ dplyr   1.0.10
## ✔ tidyr   1.2.1      ✔ stringr 1.4.1 
## ✔ readr   2.1.3      ✔ forcats 0.5.2 
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

covid19 <- read.csv('covid19.csv')
covid19_all <- filter(covid19,Province_State == 'All States')
highest_case_positive_rate <- covid19_all %>%
                group_by(Country_Region) %>% 
                summarize(sum_positive = sum(daily_positive),
                          sum_test= sum(daily_tested),
                          rate = sum_positive/sum_test
                          )
sorted <- arrange (highest_case_positive_rate,-rate)
top3 <- head(sorted, 3)
question <- "Which countries have had the highest number of positive cases against the number of tests?"
answer <- top3 %>% pull(Country_Region)
#top3_name <- top3 %>% pull(Country_Region)
#answer <- c("Positive against tested Top3" = top3_name)
covid_analysis_list <- list(question, answer, highest_case_positive_rate)
covid_analysis_list[2]

## [[1]]
## [1] "Ecuador" "Mexico"  "Sweden"

Positive top rate