R 按日期列出的唯一值

我想获得一个包含两列的数据帧：1。不同的水果（无重复）2。特定水果（即猕猴桃）首次出现的日期

---

水果我想这就是你想要的

fruits <- c("apples, oranges, pears, bananas",
        "pineapples, mangos, guavas",
        "bananas, apples, kiwis") 

fruits<-as.data.frame(fruits,stringsAsFactors=FALSE) #probably easier for the fruits to be strings rather than factors
fruits$date<-as.Date(c( "12.8.16", "22.4.17", "12.9.16"),format="%d.%m.%y") #and set your dates to be Dates rather than strings (otherwise they will be sorted alphabetically)

fruits[with(fruits, order(date)), ]

#need to convert your df to one-fruit-per-row
fruits2 <- do.call(rbind, #this binds together the data frames created by the lapply loop
               lapply(1:nrow(fruits), #loops through the rows of fruits df to create a list of data frames, each corresponding to one row
                      function(i) data.frame(fruit=trimws(strsplit((fruits$fruits),",")[[i]]), #splits your strings at commas, and trims off the whitespace
                                             date=fruits$date[i],stringsAsFactors = FALSE))) #adds the date corresponding to each row

#finding the first appearance is easily done using dplyr
library(dplyr)
fruits3 <- fruits2 %>% group_by(fruit) %>% summarise(firstdate=min(date))

以下是一些解决方案：

1）strsplit/unest/summary使用dplyr和tidyr。首先将
date
列转换为
“date”
类，并拆分
水果
列，生成一列，其中每个单元格包含一个水果向量<代码>取消测试

并找到最小值：

library(dplyr)
library(tidyr)

fruits %>%
       mutate(date = as.Date(date, "%d.%m.%y"),
              fruits = strsplit(as.character(fruits), ", ")) %>%
       unnest %>%
       group_by(fruits) %>%
       summarize(date = min(date)) %>%
       ungroup

给予：

# A tibble: 8 × 2
      fruits       date
       <chr>     <date>
1     apples 2016-08-12
2    bananas 2016-08-12
3     guavas 2017-04-22
4      kiwis 2016-09-12
5     mangos 2017-04-22
6    oranges 2016-08-12
7      pears 2016-08-12
8 pineapples 2017-04-22

2）strsplit/stack/aggregate这不使用任何包。首先，我们拆分水果列，并用日期将结果列表的组件命名为

L

。然后我们堆叠列表，创建一个数据框并重命名列，同时创建一个真正的

“Date”

类列。最后，我们

聚合
以找到最小值

L <- with(fruits, setNames(strsplit(as.character(fruits), ", "), as.Date(date,"%d.%m.%y")))
stk <- with(stack(L), data.frame(fruits = values, date = as.Date(ind)))
aggregate(date ~ fruits, stk, min)

下面是一个使用splitstackshape包的方法，它使用下面的data.table包。我们可以使用
cSplit（）
在逗号处拆分
水果
列，然后使用data.table语法获取最小的
日期

library(splitstackshape)
## create the long data frame from the split 'fruits' column
DT <- cSplit(fruits, "fruits", sep = ",", direction = "long")
## convert the 'date' column to date class and take the minimum row
DT[, .(date = min(as.IDate(date, "%d.%m.%y"))), by = fruits]
#        fruits       date
# 1:     apples 2016-08-12
# 2:    oranges 2016-08-12
# 3:      pears 2016-08-12
# 4:    bananas 2016-08-12
# 5: pineapples 2017-04-22
# 6:     mangos 2017-04-22
# 7:     guavas 2017-04-22
# 8:      kiwis 2016-09-12

库（splitstackshape）
##从拆分的“水果”列创建长数据帧
DT
fruits %>%
       mutate(date = as.Date(date, "%d.%m.%y")) %>%
       separate_rows(fruits) %>%
       group_by(fruits) %>%
       summarize(date = min(date)) %>%
       ungroup

L <- with(fruits, setNames(strsplit(as.character(fruits), ", "), as.Date(date,"%d.%m.%y")))
stk <- with(stack(L), data.frame(fruits = values, date = as.Date(ind)))
aggregate(date ~ fruits, stk, min)

      fruits       date
1     apples 2016-08-12
2    bananas 2016-08-12
3     guavas 2017-04-22
4      kiwis 2016-09-12
5     mangos 2017-04-22
6    oranges 2016-08-12
7      pears 2016-08-12
8 pineapples 2017-04-22

library(splitstackshape)
## create the long data frame from the split 'fruits' column
DT <- cSplit(fruits, "fruits", sep = ",", direction = "long")
## convert the 'date' column to date class and take the minimum row
DT[, .(date = min(as.IDate(date, "%d.%m.%y"))), by = fruits]
#        fruits       date
# 1:     apples 2016-08-12
# 2:    oranges 2016-08-12
# 3:      pears 2016-08-12
# 4:    bananas 2016-08-12
# 5: pineapples 2017-04-22
# 6:     mangos 2017-04-22
# 7:     guavas 2017-04-22
# 8:      kiwis 2016-09-12