根据R中的ID列选择最早日期和最晚日期

install.packages("dplyr") # 如果你还没有安装dplyr包
library(dplyr)

# 示例数据
df <- data.frame(
  ID = c(1, 1, 2, 2, 3),
  Date = as.Date(c("2020-01-01", "2020-02-01", "2020-01-15", "2020-02-15", "2020-03-01"))
)

# 使用dplyr找到每个ID的最早和最晚日期
result <- df %>%
  group_by(ID) %>%
  summarise(
    EarliestDate = min(Date),
    LatestDate = max(Date)
  )

print(result)

# A tibble: 3 × 3
     ID EarliestDate LatestDate 
  <dbl> <date>       <date>    
1     1 2020-01-01   2020-02-01
2     2 2020-01-15   2020-02-15
3     3 2020-03-01   2020-03-01