基于重叠日期的数据框之间的匹配值

Question

我目前正在处理以下数据结构：

属性df：

  ID Begin_A      End_A        Interval                          Value
1  5 1990-03-01   2017-03-10   1990-03-01 UTC--2017-03-10 UTC    Cat1
2 10 1993-12-01   2017-12-02   1993-12-01 UTC--2017-12-02 UTC    Cat2
3  5 1991-03-01   2017-03-03   1991-03-01 UTC--2017-03-03 UTC    Cat3
4 10 1995-12-05   2017-12-10   1995-12-05 UTC--2017-12-10 UTC    Cat4

预订 df：

  ID    Begin_A      End_A                       Interval
1  5 2017-03-03 2017-03-05 2017-03-03 UTC--2017-03-05 UTC
2  6 2017-05-03 2017-05-05 2017-05-03 UTC--2017-05-05 UTC
3  8 2017-03-03 2017-03-05 2017-03-03 UTC--2017-03-05 UTC
4 10 2017-12-05 2017-12-06 2017-12-05 UTC--2017-12-06 UTC

正如在下面的帖子中已经提到的：Matching values conditioned on overlapping Intervals and ID，我打算进行以下数据重组：从预订中获取 ID，过滤属性 ID 与预订 ID 匹配的属性数据框的所有行。检查哪些具有匹配属性 ID 的行也具有重叠的时间间隔（来自 lubridate 的 int_overlaps）。然后从 Value 列中获取相应的值，并将它们中的每一个打印到 Attribute_value 列中。

预期的结果如下所示：

ID  Begin_A      End_A        Interval                        Attribute_value
5   2017-03-03   2017-03-05   2017-03-03 UTC--2017-03-05 UTC  Cat1,Cat3
6   2017-05-03   2017-05-05   2017-05-03 UTC--2017-05-05 UTC  NA
8   2017-03-03   2017-03-05   2017-03-03 UTC--2017-03-05 UTC  NA
10  2017-12-05   2017-12-06   2017-12-05 UTC--2017-12-06 UTC  Cat4

ycw 已经在这里提供了这个问题的部分答案：(https://stackoverflow.com/a/46819541/8259308)。此解决方案不允许属性数据框中的 Begin_A 和 End_A 之间存在很长的句点，因为使用以下命令创建了具有单独日期的向量：

complete(Date = full_seq(Date, period = 1), ID) %>%

由于我的原始数据集在 Attributes 数据框中有大量长时间的观察，因此 R 无法处理这些大量观察。我的想法是修改上述行以将日期的跳跃减少到几个月（这也会降低精度）或尝试一种新方法。 以下代码生成上述数据帧：

library(lubridate)
library(tidyverse)
# Attributes data frame:
date1 <- as.Date(c('1990-3-1','1993-12-1','1991-3-1','1995-12-5'))
date2 <- as.Date(c('2017-3-10','2017-12-2','2017-3-3','2017-12-10'))
attributes <- data.frame(matrix(NA,nrow=4, ncol = 5)) 
names(attributes) <- c("ID","Begin_A", "End_A", "Interval", "Value")
attributes$ID <- as.numeric(c(5,10,5,10))
attributes$Begin_A <-date1
attributes$End_A <-date2
attributes$Interval <-attributes$Begin_A %--% attributes$End_A
attributes$Value<- as.character(c("Cat1","Cat2","Cat3","Cat4"))

### Bookings data frame:

date1 <- as.Date(c('2017-3-3','2017-5-3','2017-3-3','2017-12-5'))
date2 <- as.Date(c('2017-3-5','2017-5-5','2017-3-5','2017-12-6'))
bookings <- data.frame(matrix(NA,nrow=4, ncol = 4)) 
names(bookings) <- c("ID","Begin_A", "End_A", "Interval")
bookings$ID <- as.numeric(c(5,6,8,10))
bookings$Begin_A <-date1
bookings$End_A <-date2
bookings$Interval <-bookings$Begin_A %--% bookings$End_A

这是ycw提供的上一篇帖子的解决方案：

library(tidyverse)

attributes2 <- attributes %>%
  select(-Interval) %>%
  gather(Type, Date, ends_with("_A")) %>%
  select(-Type) %>%
  group_by(Value) %>%
  complete(Date = full_seq(Date, period = 1), ID) %>%
  ungroup()

bookings2 <- bookings %>%
  select(-Interval) %>%
  gather(Type, Date, ends_with("_A")) %>%
  select(-Type) %>%
  group_by(ID) %>%
  complete(Date = full_seq(Date, period = 1)) %>%
  ungroup()

bookings3 <- bookings2 %>%
  left_join(attributes2, by = c("ID", "Date")) %>%
  group_by(ID) %>%
  summarise(Attribute_value = toString(sort(unique(Value)))) %>%
  mutate(Attribute_value = ifelse(Attribute_value %in% "", NA, Attribute_value))

bookings4 <- bookings %>% left_join(bookings3, by = "ID")
bookings4
  ID    Begin_A      End_A                       Interval Attribute_value
1  5 2017-03-03 2017-03-05 2017-03-03 UTC--2017-03-05 UTC      Cat1, Cat3
2  6 2017-05-03 2017-05-05 2017-05-03 UTC--2017-05-05 UTC            <NA>
3  8 2017-03-03 2017-03-05 2017-03-03 UTC--2017-03-05 UTC            <NA>
4 10 2017-12-05 2017-12-06 2017-12-05 UTC--2017-12-06 UTC            Cat4

Answer 1

您可以考虑data.table，它允许“非等连接”，即基于>=、>、<= 和< 的连接。在同一个调用中，可以对 RHS 数据集中 (i) 中的每一行匹配 (by = .EACHI) 的 LHS 数据集中的组执行聚合操作。

d1[d2, on = .(id = id, end >= begin),
         .(i.begin, i.end, val_str = toString(val)), by = .EACHI]

#    id        end    i.begin      i.end    val_str
# 1:  5 2017-03-03 2017-03-03 2017-03-05 Cat3, Cat1
# 2:  6 2017-05-03 2017-05-03 2017-05-05         NA
# 3:  8 2017-03-03 2017-03-03 2017-03-05         NA
# 4: 10 2017-12-05 2017-12-05 2017-12-06       Cat4

---

数据准备：

d1 <- data.frame(id = c(5, 10, 5, 10),
                 begin = as.Date(c('1990-3-1','1993-12-1','1991-3-1','1995-12-5')),
                 end = as.Date(c('2017-3-10','2017-12-2','2017-3-3','2017-12-10')),
                 val = c("Cat1", "Cat2", "Cat3", "Cat4"))

d2 <- data.frame(id = c(5, 6, 8, 10),
                 begin = as.Date(c('2017-3-3','2017-5-3','2017-3-3','2017-12-5')),
                 end = as.Date(c('2017-3-5','2017-5-5','2017-3-5','2017-12-6')))

library(data.table)
setDT(d1)
setDT(d2)