R: how to get last sold out date for each buying? - r

Question

let say i'm a fruit vendor, and i have 2 table. 1 for buying and 1 for sales like bellow,
library(tibble)
library(tidyverse)
FruitBought <- tribble(
~name, ~Date, ~Qty,
"Apple", 20180101, 15,
"Apple", 20180105, 20,
"Banana", 20180102, 18,
"Banana", 20180109, 14
)
fruitSold <- tribble(
~Date, ~name, ~sold,
20180101, 'Apple', 5,
20180102, 'Apple', 3,
20180102, 'Banana', 3,
20180103, 'Apple', 1,
20180103, 'Banana', 4,
20180104, 'Apple', 2,
20180104, 'Banana', 2,
20180105, 'Apple', 1,
20180105, 'Banana', 2,
20180106, 'Apple', 2,
20180106, 'Banana', 3,
20180107, 'Apple', 2,
20180107, 'Banana', 1,
20180108, 'Apple', 0,
20180108, 'Banana', 3,
20180109, 'Apple', 2,
20180109, 'Banana', 1,
20180110, 'Apple', 3,
20180110, 'Banana', 1
)
I want to get last sold out date for each buying. like this.
name | Date | Qty | LastSoldOut
"Apple" | 20180101 | 15 | 20180107
"Apple" | 20180105 | 20 | NA
"Banana" | 20180102 | 18 | 20180109
"Banana" | 20180109 | 14 | NA
Is there anyone can help?

Answer 1

1) Here is a possible approach using data.table non-equi join:
#calculate the available stock at each date
FruitBought[, CumAvail:=cumsum(Qty), by=.(name)]
#calculate the fruits sold up to date
cumsold <- fruitSold[, .(Date, SoldToDate=cumsum(sold)), .(name)]
#use non-equi join to find the first date where
#sold to date is greater than available stock as per OP
cumsold[
FruitBought, on=.(name=name, Date>=Date, SoldToDate>CumAvail),
#for each row in FruitBought, find that first date
.(Name=i.name, Date=i.Date, Qty, LastSoldOut=x.Date[1L]), by=.EACHI][,
-(1L:3L)] #remove the joining columns
2) You can also use the data.table's roll argument by slightly tweaking the number sold to date:
FruitBought[, CumAvail:=cumsum(Qty), by=.(name)]
cumsoldTweak <- fruitSold[, .(Date, SoldToDate=cumsum(sold)-1e-2), .(name)]
cumsoldTweak[FruitBought, on=c("name", SoldToDate="CumAvail"), roll=-Inf,
.(name, Date=i.Date, Qty, LastSoldOut=Date)]
output:
Name Date Qty LastSoldOut
1: Apple 20180101 15 20180107
2: Apple 20180105 20 NA
3: Banana 20180102 18 20180109
4: Banana 20180109 14 NA
data:
library(data.table)
#data.table 1.11.4 Latest news: http://r-datatable.com
FruitBought <- fread("name,Date,Qty
Apple,20180101,15
Apple,20180105,20
Banana,20180102,18
Banana,20180109,14")
#order is important before doing cumsum
setorder(FruitBought, name, Date)
fruitSold <- fread("Date,name,sold
20180101,Apple,5
20180102,Apple,3
20180102,Banana,3
20180103,Apple,1
20180103,Banana,4
20180104,Apple,2
20180104,Banana,2
20180105,Apple,1
20180105,Banana,2
20180106,Apple,2
20180106,Banana,3
20180107,Apple,2
20180107,Banana,1
20180108,Apple,0
20180108,Banana,3
20180109,Apple,2
20180109,Banana,1
20180110,Apple,3
20180110,Banana,1")
#order is important before doing cumsum
setorder(fruitSold, Date, name)

Answer 2

You can do something like this to get the desired output
library(tibble)
library(tidyverse)
FruitBought <- tribble(
~name, ~Date, ~Qty,~id,
"Apple", 20180101, 15,1,
"Apple", 20180105, 20,2,
"Banana", 20180102, 18,1,
"Banana", 20180109, 14,2,
)
fruitSold <- tribble(
~Date, ~name, ~sold,~id,
20180101, 'Apple', 5,1,
20180102, 'Apple', 3,1,
20180102, 'Banana', 3,1,
20180103, 'Apple', 1,1,
20180103, 'Banana', 4,1,
20180104, 'Apple', 2,1,
20180104, 'Banana', 2,1,
20180105, 'Apple', 1,1,
20180105, 'Banana', 2,1,
20180106, 'Apple', 2,1,
20180106, 'Banana', 3,1,
20180107, 'Apple', 2,1,
20180107, 'Banana', 1,1,
20180108, 'Apple', 0,2,
20180108, 'Banana', 3,1,
20180109, 'Apple', 2,2,
20180109, 'Banana', 1,1,
20180110, 'Apple', 3,2,
20180110, 'Banana', 1,1
)
fruitSold$Date <- lubridate::ymd(fruitSold$Date)
FruitBought$Date <- lubridate::ymd(FruitBought$Date )
colnames(fruitSold)
sold <- as.data.frame(fruitSold %>% group_by(name,id) %>% summarise(last_date = max(Date)))
colnames(sold)
colnames(FruitBought)
final <- left_join(FruitBought,sold, by = c("name","id"))