Problems


  1. Use read.csv to import the Covid19 data from WHO: link
WHOdf <- read.csv("WHO-COVID-19-global-data.csv", header = TRUE)
  1. How many columns and rows the data have? How many categorical variables the data have?
str(WHOdf)
## 'data.frame':    39001 obs. of  8 variables:
##  $ ï..Date_reported : chr  "2/24/2020" "2/25/2020" "2/26/2020" "2/27/2020" ...
##  $ Country_code     : chr  "AF" "AF" "AF" "AF" ...
##  $ Country          : chr  "Afghanistan" "Afghanistan" "Afghanistan" "Afghanistan" ...
##  $ WHO_region       : chr  "EMRO" "EMRO" "EMRO" "EMRO" ...
##  $ New_cases        : int  5 0 0 0 0 0 0 0 0 0 ...
##  $ Cumulative_cases : int  5 5 5 5 5 5 5 5 5 5 ...
##  $ New_deaths       : int  0 0 0 0 0 0 0 0 0 0 ...
##  $ Cumulative_deaths: int  0 0 0 0 0 0 0 0 0 0 ...
dim(WHOdf)
## [1] 39001     8
  1. How many missing values are there? Show the missing values by columns. What variable has the most number of missing values?
sum(is.na(WHOdf))
## [1] 173
colSums(is.na(WHOdf))
##  ï..Date_reported      Country_code           Country        WHO_region 
##                 0               173                 0                 0 
##         New_cases  Cumulative_cases        New_deaths Cumulative_deaths 
##                 0                 0                 0                 0
  1. Correct the types of the variables that are mismatched type.
class(WHOdf$ï..Date_reported)
## [1] "character"
library(lubridate)
## 
## Attaching package: 'lubridate'
## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union
WHOdf$ï..Date_reported <- mdy(WHOdf$ï..Date_reported)
class(WHOdf$ï..Date_reported)
## [1] "Date"
  1. Find the daily average number of cases globally.
daily_new_cases <- mean(WHOdf$New_cases)
daily_new_cases
## [1] 656.4618
daily_cumulative_cases <- mean(WHOdf$Cumulative_cases)
daily_cumulative_cases
## [1] 40414.05
  1. Find the maximum cases a day.
max_cases <- max(WHOdf$New_cases)
max_cases
## [1] 78761
  1. Which country at which date has the maximum number of cases a day? Hint: use the which.max function to find the index of the row that contains the maximum number of cases. Then from the row index, find that country and the date. 
which_max <- which.max(WHOdf$New_cases)
which_max
## [1] 16888
WHOdf[16888,1:3]
##       ï..Date_reported Country_code Country
## 16888       2020-08-30           IN   India
  1. How many WHO’s region there are in the data?
table(WHOdf$WHO_region)
## 
##  AFRO  AMRO  EMRO  EURO Other SEARO  WPRO 
##  8219  9425  4056 11397   211  1950  3743
# There are 7 regions
  1. Find the daily average cases in EUROPE. Find the daily average cases by regions.
WHOdf_Europe <- WHOdf[WHOdf$WHO_region == 'EURO',]
average_Europe <- mean(WHOdf_Europe$New_cases)
average_Europe
## [1] 378.2812
by(WHOdf$New_cases, WHOdf$WHO_region, mean)
## WHOdf$WHO_region: AFRO
## [1] 129.1473
## ------------------------------------------------------------ 
## WHOdf$WHO_region: AMRO
## [1] 1429.151
## ------------------------------------------------------------ 
## WHOdf$WHO_region: EMRO
## [1] 478.1075
## ------------------------------------------------------------ 
## WHOdf$WHO_region: EURO
## [1] 378.2812
## ------------------------------------------------------------ 
## WHOdf$WHO_region: Other
## [1] 3.511848
## ------------------------------------------------------------ 
## WHOdf$WHO_region: SEARO
## [1] 2214.503
## ------------------------------------------------------------ 
## WHOdf$WHO_region: WPRO
## [1] 134.1061
  1. Find the daily average number of cases in the US in the last 5 days.
WHOdf_US <- WHOdf[(WHOdf$Country=='United States of America')&(Sys.Date()-WHOdf$ï..Date_reported<10),]
mean(WHOdf_US$New_cases)
## [1] 40611
# Changed the number from 5 to 10 to account for the five days in between the system date and the last reported date, so we are actually going back 10 days to get the last five rows of dates
  1. Which day of the week has the most number of cases in South East Asia (SEARO region)?
WHOdf$weekday <- wday(WHOdf$ï..Date_reported)
WHOdf_SEARO <- WHOdf[(WHOdf$WHO_region=='SEARO'),]
by(WHOdf_SEARO$New_cases,WHOdf_SEARO$weekday,sum)
## WHOdf_SEARO$weekday: 1
## [1] 635936
## ------------------------------------------------------------ 
## WHOdf_SEARO$weekday: 2
## [1] 617453
## ------------------------------------------------------------ 
## WHOdf_SEARO$weekday: 3
## [1] 587327
## ------------------------------------------------------------ 
## WHOdf_SEARO$weekday: 4
## [1] 633744
## ------------------------------------------------------------ 
## WHOdf_SEARO$weekday: 5
## [1] 597792
## ------------------------------------------------------------ 
## WHOdf_SEARO$weekday: 6
## [1] 620520
## ------------------------------------------------------------ 
## WHOdf_SEARO$weekday: 7
## [1] 625509
# Day 1, or Monday has the most number of cases in the SEARO region