如何在R语言中识别采样日期是否处于风暴事件±3天范围内

我有两个数据框，一个包含采样日期，另一个包含风暴（AR）事件日期，需要识别每个采样日期是否处于任意风暴事件的±3天范围内。以下是示例数据：

采样数据框 #

structure(list(Date = structure(c(7319, 7378, 7439, 7500, 7531, 7562,
7592, 7623, 7653, 7684), class = "Date"), NO3 = c(2.37, 3.42, 3.13,
2.24, 1.97, 2.22, 2.58, 2.15, 2.05, 3.09), cumP = c(122.8, 104, 19.9, 20.4, 0, 8.8, 134.3, 232.8, 168.3, 171.3), Season = c("R", "R", "F", "I", "H", "R", "R", "R", "R", "R")), row.names = c(NA,
10L), class = "data.frame")

风暴事件数据框 #

structure(list(Date = structure(c(7311, 7313, 7316, 7329, 7338, 7345,
7355, 7451, 7458, 7474, 7580, 7581, 7586, 7598, 7601, 7602, 7615,
7617, 7618, 7619, 7620, 7621, 7630, 7631, 7632, 7637, 7641, 7642,
7646, 7647, 7655), class = "Date")), row.names = c(NA, -31L), class =
"data.frame")

方法一：使用dplyr + lubridate包 #

这种方法代码简洁易读，适合处理数据框操作：

# 加载依赖包
library(dplyr)
library(lubridate)

# 读取示例数据（数据已加载可跳过此步）
sampling_df <- structure(list(Date = structure(c(7319, 7378, 7439, 7500, 7531, 7562,
7592, 7623, 7653, 7684), class = "Date"), NO3 = c(2.37, 3.42, 3.13,
2.24, 1.97, 2.22, 2.58, 2.15, 2.05, 3.09), cumP = c(122.8, 104, 19.9, 20.4, 0, 8.8, 134.3, 232.8, 168.3, 171.3), Season = c("R", "R", "F", "I", "H", "R", "R", "R", "R", "R")), row.names = c(NA,
10L), class = "data.frame")

ar_events_df <- structure(list(Date = structure(c(7311, 7313, 7316, 7329, 7338, 7345,
7355, 7451, 7458, 7474, 7580, 7581, 7586, 7598, 7601, 7602, 7615,
7617, 7618, 7619, 7620, 7621, 7630, 7631, 7632, 7637, 7641, 7642,
7646, 7647, 7655), class = "Date")), row.names = c(NA, -31L), class =
"data.frame")

# 生成所有风暴事件±3天的日期集合，去重避免重复判断
ar_date_range <- ar_events_df %>%
  rowwise() %>%
  mutate(date_range = list(seq(Date - days(3), Date + days(3), by = "day"))) %>%
  pull(date_range) %>%
  unlist() %>%
  unique() %>%
  as.Date(origin = "1970-01-01")

# 为采样数据框添加标记列，判断是否在风暴影响范围内
sampling_df <- sampling_df %>%
  mutate(near_AR = Date %in% ar_date_range)

# 查看最终结果
print(sampling_df)

方法二：基础R实现 #

如果不想加载额外包，可使用基础R代码完成：

# 读取示例数据（数据已加载可跳过此步）
sampling_df <- structure(list(Date = structure(c(7319, 7378, 7439, 7500, 7531, 7562,
7592, 7623, 7653, 7684), class = "Date"), NO3 = c(2.37, 3.42, 3.13,
2.24, 1.97, 2.22, 2.58, 2.15, 2.05, 3.09), cumP = c(122.8, 104, 19.9, 20.4, 0, 8.8, 134.3, 232.8, 168.3, 171.3), Season = c("R", "R", "F", "I", "H", "R", "R", "R", "R", "R")), row.names = c(NA,
10L), class = "data.frame")

ar_events_df <- structure(list(Date = structure(c(7311, 7313, 7316, 7329, 7338, 7345,
7355, 7451, 7458, 7474, 7580, 7581, 7586, 7598, 7601, 7602, 7615,
7617, 7618, 7619, 7620, 7621, 7630, 7631, 7632, 7637, 7641, 7642,
7646, 7647, 7655), class = "Date")), row.names = c(NA, -31L), class =
"data.frame")

# 生成所有风暴事件±3天的日期序列，去重
ar_dates <- ar_events_df$Date
ar_range <- unlist(lapply(ar_dates, function(x) seq(x - 3, x + 3, by = "day")))
ar_range <- unique(ar_range)

# 标记采样日期是否在风暴影响范围内
sampling_df$near_AR <- sampling_df$Date %in% ar_range

# 查看最终结果
print(sampling_df)

结果说明 #

运行代码后，采样数据框会新增一列near_AR：

• TRUE表示该采样日期处于任意风暴事件的±3天范围内
• FALSE表示该采样日期不在任何风暴事件的±3天范围内

内容的提问来源于stack exchange，提问作者arcticmermaid