R Создайте сводную таблицу, которая вычисляет проценты нескольких групп

Вот один из подходов:

library(tidyverse)

sample <- structure(list(Week  = c(1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2),
                         Project = c("A", "A", "A",  "A",  "B",  "B",  "B",  "B",  "C",  "C",  "C",  "A", "A",   "A" ), 
                         Status= c( "Active","Rescheduled","Active", "Cancelled", "Active", "Cancelled",  "Cancelled", 
                                    "Rescheduled",  "Active",  "Active",   "Rescheduled", "Cancelled", "Cancelled", "Active")),
                    .Names = c("Week","Project","Status"),
                    class = "data.frame" , row.names = c(NA, -14L))

sample %>%
  mutate(active_or_not = ifelse(Status == "Active", "Active", "Non_Active")) %>%
  mutate(count = n(), .by = c(Week, Project, active_or_not)) %>%
  mutate(perc = count / n(), .by = c(Week, Project)) %>%
  pivot_wider(names_from = c(Project, active_or_not),
              id_cols = Week,
              values_from = perc,
              values_fn = mean,
              values_fill = NA,
              names_glue = "{.name}_rate")
#> # A tibble: 2 × 7
#>    Week A_Active_rate A_Non_Active_rate B_Active_rate B_Non_Active_rate
#>   <dbl>         <dbl>             <dbl>         <dbl>             <dbl>
#> 1     1         0.5               0.5            0.25              0.75
#> 2     2         0.333             0.667         NA                NA   
#> # ℹ 2 more variables: C_Active_rate <dbl>, C_Non_Active_rate <dbl>

^{Created on 2024-04-11 with reprex v2.1.0}

Еще один подход tidyverse:

library(dplyr)
library(tidyr)

sample %>%
  summarize(
    active_rate = mean(Status == "Active"),
    Non_active_rate = 1 - active_rate,
    .by = c(Week, Project)
  ) %>%
  pivot_wider(
    names_from = Project,
    values_from = active_rate:Non_active_rate,
    names_glue = "{Project}_{.value}",
    names_vary = "slowest"
  )
# # A tibble: 2 × 7
#    Week A_active_rate A_Non_active_rate B_active_rate B_Non_active_rate C_active_rate C_Non_active_rate
#   <dbl>         <dbl>             <dbl>         <dbl>             <dbl>         <dbl>             <dbl>
# 1     1         0.5               0.5            0.25              0.75        NA                NA    
# 2     2         0.333             0.667         NA                NA            0.667             0.333