基于原始列和第二个dataFrame

Question

    df1 <- data.frame(Date = as.Date(c("2024-01-01", "2024-02-01", "2024-03-01",     "2024-04-01", "2024-05-01", "2024-06-01", "2024-07-01")),
                  RT = c("150.5-40", "150.5-40", "150.5-40", "150.5-40", "150.5-140",     "150.5-80", "150.5-80"),
                  RTa = c("150.5-40a", "150.5-40a", "150.5-40a", "150.5-40a", "150.5-    140a", "150.5-80a", "150.5-80a"))

df1

DATERT RTA 2024-01-01 150.5-40150.5-40A

2024-02-01 150.5-40150.5-40A

2024-03-01 150.5-40150.5-40A

2024-04-01 150.5-40150.5-40A

2024-05-01 150.5-140150.5-140A

2024-06-01 150.5-80150.5-80A
2024-07-01 150.5-80150.5-80A

    df2 <- data.frame(Date = as.Date(c("2024-03-01", "2024-04-01")),
                  RT = c("150.5-40", "150.5-10"),
                  MRT = c("150.5-140", "150.5-110"))

df2

DATERT MRT 2024-03-01 150.5-40150.5-140

2024-04-01 150.5-10150.5-110

既定的结果：

DATERT RT RTA RT_F 2024-01-01 150.5-40 150.5-40A150.5-40
2024-02-01 150.5-40 150.5-40A150.5-40

2024-03-01 150.5-40 150.5-40A150.5-40A

2024-04-01 150.5-40 150.5-40A150.5-40A

2024-05-01 150.5-140 150.5-140A150.5-140A

2024-06-01 150.5-80 150.5-80A150.5-80
2024-07-01 150.5-80 150.5-80A150.5-80
我尝试使用dplyr ::突变如下：

df1 %>% 
  dplyr::mutate(RT_F = if_else(RT == df2$RT | RT == df2$MRT & Date >= df2$Date, RTa, RT))

产生以下不准确的结果：

DATERT RT RTA RT_F 2024-01-01 150.5-40 150.5-40A150.5-40A

2024-02-01 150.5-40 150.5-40A150.5-40

2024-03-01 150.5-40 150.5-40A150.5-40A

2024-04-01 150.5-40 150.5-40A150.5-40

2024-05-01 150.5-140 150.5-140A150.5-140A

2024-06-01 150.5-80 150.5-80A150.5-80

2024-07-01 150.5-80 150.5-80A150.5-80
我也尝试了：

for (i in 1:nrow(df1)) { # For every row in df1
  
  # # Select if df1 RT = df2 RT
  if (df1[i, "RT"] %in% df2$"RT") { # If RT is in df2
    df[i, "RTF"] <- df2$RTa # Add RTa to the RTF column
    }
  }

产生以下错误：

在df [i，“ rtf”]

中 也没有成功尝试以下内容

df1 %>% 
  dplyr::mutate(RTF = case_when(
    RT == df2$RT | RT == df2$MRT & Date >= df2$Date ~ RT, 
    TRUE ~ RTa
  ))

基于您的logic在

dplyr<- df2$RTa : object of type 'closure' is not subsettable

代码中，实现所需输出的一种方法是使用

dplyr::left_join()

结合DF1和DF2，然后应用日期条件。

实现此目标的一种方法是将您的DF2对象转换为加入之前使用

tidyr::pivot_longer()

Answer 1

首先，负载所需的软件包和数据（示例数据中存在错误，修改了）：

library(dplyr)
library(tidyr)

df1 <- data.frame(
  Date = as.Date(c("2024-01-01", "2024-02-01", "2024-03-01", 
                   "2024-04-01", "2024-05-01", "2024-06-01", "2024-07-01")),
  RT = c("150.5-40", "150.5-40", "150.5-40",
         "150.5-40", "150.5-140", "150.5-80", "150.5-80"),
  RTa = c("150.5-40a", "150.5-40a", "150.5-40a",
          "150.5-40a", "150.5-140a", "150.5-80a", "150.5-80a")
  )

df2 <- data.frame(
  Date = as.Date(c("2024-03-01", "2024-04-01")),
  RT = c("150.5-40", "150.5-10"),
  MRT = c("150.5-140", "150.5-110")
  )

然后枢轴df2到长形式：

df3 <- df2 |>
  pivot_longer(-Date,
               names_to = "Type",
               values_to = "Code")

df3
# # A tibble: 4 × 3
#   Date       Type  Code     
#   <date>     <chr> <chr>    
# 1 2024-03-01 RT    150.5-40 
# 2 2024-03-01 MRT   150.5-140
# 3 2024-04-01 RT    150.5-10 
# 4 2024-04-01 MRT   150.5-110

最后，加入DF1和DF3并创建一个新列，其中应用日期条件：

df4 <- df1 |>
  left_join(df3, by = join_by(RT == Code)) |>
  mutate(RTF = if_else(Date.x >= Date.y, RTa, RT)) |>
  select(Date = Date.x, RT, RTa, RTF)

df4
#         Date        RT        RTa        RTF
# 1 2024-01-01  150.5-40  150.5-40a   150.5-40
# 2 2024-02-01  150.5-40  150.5-40a   150.5-40
# 3 2024-03-01  150.5-40  150.5-40a  150.5-40a
# 4 2024-04-01  150.5-40  150.5-40a  150.5-40a
# 5 2024-05-01 150.5-140 150.5-140a 150.5-140a
# 6 2024-06-01  150.5-80  150.5-80a       <NA>
# 7 2024-07-01  150.5-80  150.5-80a       <NA>

注意，RTF列中的NA值与您的示例所需输出有所不同，因为您的示例DF2。