R 提取和使用数据集中的当前数据 df

R 提取和使用数据集中的当前数据 df,r,R,按照您的要求,此输出为10行(每个区域2行),但要认识到,例如,美国报告的死亡人数和恢复人数都是美洲地区最多的。这意味着它出现了两次。伊朗和澳大利亚也是如此,因此只有7个独特的行 df <- read.csv ('https://raw.githubusercontent.com/ulklc/covid19- timeseries/master/countryReport/raw/rawReport.csv', stringsAsFactors = FALS

按照您的要求,此输出为10行(每个区域2行),但要认识到,例如,美国报告的死亡人数和恢复人数都是美洲地区最多的。这意味着它出现了两次。伊朗和澳大利亚也是如此,因此只有7个独特的行

 df <- read.csv ('https://raw.githubusercontent.com/ulklc/covid19- 
  timeseries/master/countryReport/raw/rawReport.csv',
            stringsAsFactors = FALSE)

  yesterday <- function() Sys.Date() - 1L
  yesterday()
 # [1] "if it doesn't work yesterday()-1  do it"
库(tidyverse)
死亡百分比
筛选器(截止日期(天)=昨天())%>%
按地区划分的组别%>%
过滤器(死亡==最大(死亡))%>%
选择(日期=天,
国名,
区域
死
已恢复)
回收量(单位:df%)
筛选器(截止日期(天)=昨天())%>%
按地区划分的组别%>%
过滤器(已恢复==最大值(已恢复))%>%
选择(日期=天,
国名,
区域
死
已恢复)
全方位
library(tidyverse)
death_df <- df %>%
  filter(as.Date(day) == yesterday()) %>%
  group_by(region) %>%
  filter(death == max(death)) %>%
  select(Date = day,
         countryName,
         region,
         death,
         recovered)

recovered_df <- df %>%
  filter(as.Date(day) == yesterday()) %>%
  group_by(region) %>%
  filter(recovered == max(recovered)) %>%
  select(Date = day,
         countryName,
         region,
         death,
         recovered)

full_df <- bind_rows(death_df, recovered_df)
full_df
# A tibble: 10 x 5
# Groups:   region [5]
   Date       countryName    region   death recovered
   <chr>      <chr>          <chr>    <int>     <int>
 1 2020/05/05 Australia      Oceania     96      5889
 2 2020/05/05 Algeria        Africa     470      2067
 3 2020/05/05 United Kingdom Europe   29427         0
 4 2020/05/05 Iran           Asia      6340     80475
 5 2020/05/05 United States  Americas 72241    199684
 6 2020/05/05 Australia      Oceania     96      5889
 7 2020/05/05 Spain          Europe   25613    154718
 8 2020/05/05 Iran           Asia      6340     80475
 9 2020/05/05 United States  Americas 72241    199684
10 2020/05/05 South Africa   Africa     148      2746