使用 mutate 添加具有自定义 function 的新列

Question

我想做一个简单的操作，并为此使用 dplyr mutate 添加一个新列。 基本上我有一个包含很多列的 DF，我想要 select 其中一些，只是包含 hist_avg、tgt_ 和 monthyl_X_ly 的那些。 这应该很简单，添加一个以“fct_”+ metric 开头的新列应该不是问题。 但是，正如您在下面看到的，它添加了列但名称很奇怪（fct_visits$hist_avg_visits 和 fct_revenue$hist_avg_revenue_lcy）。

另外，不确定，但我尝试使用 mutate + cross 来实现它，因为它可以为我节省很多代码行并且无法弄清楚如何做到这一点。

library(tidyverse)

(example <- tibble(brand = c("Brand A", "Brand A", "Brand A", "Brand A", "Brand A"),
                     country = c("Country A", "Country A", "Country A", "Country A", "Country A"),
                     date = c("2020-08-01", "2020-08-02", "2020-08-03", "2020-08-04", "2020-08-05"),
                     visits = c(NA_real_, NA_real_, NA_real_, NA_real_, NA_real_),
                     visits_ly = c(NA_real_, NA_real_, NA_real_, NA_real_, NA_real_), 
                     tgt_visits = c(2491306, 2491306, 2491306, 2491306, 2491306), 
                     hist_avg_visits = c(177185, 175758, 225311, 210871, 197405), 
                     monthly_visits_ly = c(3765612, 3765612, 3765612, 3765612, 3765612),
                     revenue_lcy = c(NA_real_, NA_real_, NA_real_, NA_real_, NA_real_),
                     revenue_ly = c(NA_real_, NA_real_, NA_real_, NA_real_, NA_real_),
                     tgt_revenue_lcy = c(48872737, 48872737, 48872737, 48872737, 48872737),
                     hist_avg_revenue_lcy = c(231101, 222236, 276497, 259775, 251167), 
                     monthly_revenue_lcy_ly = c(17838660, 17838660, 17838660, 17838660, 17838660))) %>% 
    print(width = Inf)
#> # A tibble: 5 x 13
#>   brand   country   date       visits visits_ly tgt_visits hist_avg_visits
#>   <chr>   <chr>     <chr>       <dbl>     <dbl>      <dbl>           <dbl>
#> 1 Brand A Country A 2020-08-01     NA        NA    2491306          177185
#> 2 Brand A Country A 2020-08-02     NA        NA    2491306          175758
#> 3 Brand A Country A 2020-08-03     NA        NA    2491306          225311
#> 4 Brand A Country A 2020-08-04     NA        NA    2491306          210871
#> 5 Brand A Country A 2020-08-05     NA        NA    2491306          197405
#>   monthly_visits_ly revenue_lcy revenue_ly tgt_revenue_lcy hist_avg_revenue_lcy
#>               <dbl>       <dbl>      <dbl>           <dbl>                <dbl>
#> 1           3765612          NA         NA        48872737               231101
#> 2           3765612          NA         NA        48872737               222236
#> 3           3765612          NA         NA        48872737               276497
#> 4           3765612          NA         NA        48872737               259775
#> 5           3765612          NA         NA        48872737               251167
#>   monthly_revenue_lcy_ly
#>                    <dbl>
#> 1               17838660
#> 2               17838660
#> 3               17838660
#> 4               17838660
#> 5               17838660

first_forecast <- function(dataset, metric) {
  avg_metric <- select(dataset, paste0("hist_avg_", metric))
  tgt_metric <- select(dataset, paste0("tgt_", metric))
  monthly_metric <- select(dataset, paste0("monthly_", metric, "_ly"))
  
  output <- avg_metric * (tgt_metric / monthly_metric)
  return(output)
  
}

example %>% 
  mutate(fct_visits = first_forecast(., "visits"),
         fct_revenue = first_forecast(., "revenue_lcy")) %>% 
  print(width = Inf)
#> # A tibble: 5 x 15
#>   brand   country   date       visits visits_ly tgt_visits hist_avg_visits
#>   <chr>   <chr>     <chr>       <dbl>     <dbl>      <dbl>           <dbl>
#> 1 Brand A Country A 2020-08-01     NA        NA    2491306          177185
#> 2 Brand A Country A 2020-08-02     NA        NA    2491306          175758
#> 3 Brand A Country A 2020-08-03     NA        NA    2491306          225311
#> 4 Brand A Country A 2020-08-04     NA        NA    2491306          210871
#> 5 Brand A Country A 2020-08-05     NA        NA    2491306          197405
#>   monthly_visits_ly revenue_lcy revenue_ly tgt_revenue_lcy hist_avg_revenue_lcy
#>               <dbl>       <dbl>      <dbl>           <dbl>                <dbl>
#> 1           3765612          NA         NA        48872737               231101
#> 2           3765612          NA         NA        48872737               222236
#> 3           3765612          NA         NA        48872737               276497
#> 4           3765612          NA         NA        48872737               259775
#> 5           3765612          NA         NA        48872737               251167
#>   monthly_revenue_lcy_ly fct_visits$hist_avg_visits
#>                    <dbl>                      <dbl>
#> 1               17838660                    117225.
#> 2               17838660                    116280.
#> 3               17838660                    149064.
#> 4               17838660                    139511.
#> 5               17838660                    130602.
#>   fct_revenue$hist_avg_revenue_lcy
#>                              <dbl>
#> 1                          633149.
#> 2                          608862.
#> 3                          757521.
#> 4                          711708.
#> 5                          688124.

^{由reprex package (v0.3.0) 于 2020 年 7 月 28 日创建}

Answer 1

指向@Onyambu 的伟大建议，您的代码的最后一部分应该是这样的：

example %>% 
  cbind(fct_visits = first_forecast(., "visits"),
         fct_revenue = first_forecast(., "revenue_lcy")) %>% 
  print(width = Inf)

brand   country       date visits visits_ly tgt_visits hist_avg_visits monthly_visits_ly revenue_lcy
1 Brand A Country A 2020-08-01     NA        NA    2491306          177185           3765612          NA
2 Brand A Country A 2020-08-02     NA        NA    2491306          175758           3765612          NA
3 Brand A Country A 2020-08-03     NA        NA    2491306          225311           3765612          NA
4 Brand A Country A 2020-08-04     NA        NA    2491306          210871           3765612          NA
5 Brand A Country A 2020-08-05     NA        NA    2491306          197405           3765612          NA
  revenue_ly tgt_revenue_lcy hist_avg_revenue_lcy monthly_revenue_lcy_ly hist_avg_visits hist_avg_revenue_lcy
1         NA        48872737               231101               17838660        117224.5             633149.5
2         NA        48872737               222236               17838660        116280.4             608862.0
3         NA        48872737               276497               17838660        149064.4             757521.3
4         NA        48872737               259775               17838660        139511.0             711707.9
5         NA        48872737               251167               17838660        130601.9             688124.5