R - 结转值

Question

这是我的起始数据集：

> data
  ID Record Value
   A      1   100
   A      3   200
   A      4   300
   B      1   800

对于每个ID，我想要每个数字1到4的记录。如果记录不可用，请使用最新记录创建它。

最终数据集应如下所示：

> newdata
     ID Updt_Record Value
      A           1   100
      A           2   100
      A           3   200
      A           4   300
      B           1   800
      B           2   800
      B           3   800
      B           4   800

要执行此操作，我目前正在使用dplyr：

library(dplyr)

data1 <- data %>% group_by(ID) %>% filter(Record <= 1) %>% filter(Record == max(Record)) %>% mutate(Updt_Record = 1)
data2 <- data %>% group_by(ID) %>% filter(Record <= 2) %>% filter(Record == max(Record)) %>% mutate(Updt_Record = 2)
data3 <- data %>% group_by(ID) %>% filter(Record <= 3) %>% filter(Record == max(Record)) %>% mutate(Updt_Record = 3)
data4 <- data %>% group_by(ID) %>% filter(Record <= 4) %>% filter(Record == max(Record)) %>% mutate(Updt_Record = 4)

newdata <- data1 %>%
  bind_rows(data2) %>% bind_rows(data3) %>% bind_rows(data4) %>%
  arrange(ID, Record) %>%
  select(ID, Updt_Record, Value)

有更有效的方法吗？谢谢！

Answer 1

library(tidyr)
library(dplyr)
data %>%
  mutate(Record=factor(Record, 1:4)) %>%
  complete(ID, Record) %>%
  fill(Value) %>%
  mutate(Record=as.character(as.numeric(Record)))

# # A tibble: 8 x 3
#       ID Record Value
#   <fctr>  <dbl> <int>
# 1      A      1   100
# 2      A      2   100
# 3      A      3   200
# 4      A      4   300
# 5      B      1   800
# 6      B      2   800
# 7      B      3   800
# 8      B      4   800

数据

data <- structure(list(ID = structure(c(1L, 1L, 1L, 2L), .Label = c("A", 
"B"), class = "factor"), Record = c(1L, 3L, 4L, 1L), Value = c(100L, 
200L, 300L, 800L)), .Names = c("ID", "Record", "Value"), class = "data.frame", row.names = c(NA, 
-4L))