r - 如何按组将 2 个函数添加到回归中？

Question

我有这个数据集。

 dat=structure(list(sku = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
        1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), period = c("30.09.2021", 
        "14.03.2019", "01.04.2022", "18.02.2022", "07.07.2021", "09.10.2020", 
        "17.01.2019", "10.11.2020", "14.07.2021", "10.09.2019", "31.01.2019", 
        "01.07.2021", "30.09.2021", "14.03.2019", "01.04.2022", "18.02.2022", 
        "07.07.2021", "09.10.2020", "17.01.2019", "10.11.2020", "14.07.2021", 
        "10.09.2019", "31.01.2019", "01.07.2021"), hist.prices = c(3728.16, 
        34899.84, 6126, 1789.44, 18098.4, 15633.6, 26174.88, 2401.56, 
        12668.88, 239500.8, 26174.88, 5429.52, 3728.16, 34899.84, 6126, 
        1789.44, 18098.4, 15633.6, 26174.88, 2401.56, 12668.88, 239500.8, 
        26174.88, 5429.52), hist.revenue = c(178951.68, 20102307.84, 
        367560, 42946.56, 4343616, 3752064, 11307548.16, 86456.16, 2128371.84, 
        965667225.6, 11307548.16, 390925.44, 178951.68, 20102307.84, 
        367560, 42946.56, 4343616, 3752064, 11307548.16, 86456.16, 2128371.84, 
        965667225.6, 11307548.16, 390925.44), hist.demand = c(254L, 276L, 
        272L, 250L, 299L, 297L, 291L, 260L, 270L, 275L, 295L, 279L, 254L, 
        276L, 272L, 250L, 299L, 297L, 291L, 260L, 270L, 275L, 295L, 279L
        ), hist.cost = c(12572.6698, 10498.9848, 14949.392, 13160.5, 
        14557.9512, 12443.3199, 10692.3294, 10893.116, 13145.976, 10222.6025, 
        10982.9975, 13584.1752, 12572.6698, 10498.9848, 14949.392, 13160.5, 
        14557.9512, 12443.3199, 10692.3294, 10893.116, 13145.976, 10222.6025, 
        10982.9975, 13584.1752), unity.cost = c(49.4987, 38.0398, 54.961, 
        52.642, 48.6888, 41.8967, 36.7434, 41.8966, 48.6888, 37.1731, 
        37.2305, 48.6888, 49.4987, 38.0398, 54.961, 52.642, 48.6888, 
        41.8967, 36.7434, 41.8966, 48.6888, 37.1731, 37.2305, 48.6888
        ), hist.profit = c(1336L, 1592L, 1128L, 1882L, 1387L, 1818L, 
        1357L, 1087L, 1253L, 1009L, 1092L, 1804L, 1336L, 1592L, 1128L, 
        1882L, 1387L, 1818L, 1357L, 1087L, 1253L, 1009L, 1092L, 1804L
        )), class = "data.frame", row.names = c(NA, -24L))

并按组执行回归(sku)

library(dplyr)
library(nplyr)
library(tidyr)
dat %>% 
  nest(data = -sku) %>% 
  nest_summarise(data, 
   model.fit = list(lm(hist.demand ~ hist.prices)), 
   beta = model.fit[[1]]$coefficients[1], 
   alpha = model.fit[[1]]$coefficients[2],
   p.revenue = -beta/(2*alpha),
   p.profit = (alpha*unity.cost - beta)/(2*alpha),
   opt.revenue = true.revenue(p.revenue), ###########################  absent
   opt.profit = true.profit(p.profit)) %>% ########################## absent
  nest_select(data, opt.revenue, opt.profit) %>%
  unnest(data)

但是在执行回归时，还必须使用 true.revenue 和 true.profit 这两个函数，否则我会得到这些函数不存在的错误。这里有这些函数

true.revenue = function(p) p*(x*p + y) # Revenue 
true.profit = function(p) (p - unity.cost)*(x*p + y) # price 

• p 是特定时期的 hist.prices 的特定值，例如 30.09.202 value for price =3728.16 等等
• x 是截距，y 是 beta 系数，这是在对每个组执行回归 hist.demand ~ hist.prices 时得到的 (sku).

那么如何将这 2 个函数添加到回归中以按组执行呢？

Answer 1

您只需参数化您的函数，true.revenue() 和 true.profit()。

true.revenue = function(p,x,y) p*(x*p + y) # Revenue 
true.profit = function(p,x,y,u) (p - u)*(x*p + y) # price 

然后，除了 p:

dat %>% 
  nest(data = -sku) %>% 
  nest_summarise(data, 
                 model.fit = list(lm(hist.demand ~ hist.prices)), 
                 beta = model.fit[[1]]$coefficients[1], 
                 alpha = model.fit[[1]]$coefficients[2],
                 p.revenue = -beta/(2*alpha),
                 p.profit = (alpha*unity.cost - beta)/(2*alpha),
                 opt.revenue = true.revenue(p=p.revenue,x = hist.prices, y=hist.demand )
                 opt.profit = true.profit(p.profit,x = hist.prices, y=hist.demand,u=unity.cost)) %>%
  nest_select(data, opt.revenue, opt.profit) %>%
  unnest(data)