R Under development (unstable) (2024-07-30 r86939 ucrt) -- "Unsuffered Consequences"
Copyright (C) 2024 The R Foundation for Statistical Computing
Platform: x86_64-w64-mingw32/x64
R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.
R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.
Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.
> library(dplyr)
Attaching package: 'dplyr'
The following objects are masked from 'package:stats':
filter, lag
The following objects are masked from 'package:base':
intersect, setdiff, setequal, union
> library(rollup)
Loading required package: tidyr
Attaching package: 'rollup'
The following objects are masked from 'package:dplyr':
summarise, summarize
>
> data("web_service_data")
> web_service_data %>% head
# A tibble: 6 × 6
date_id id gender age page_view_cnt product_view_cnt_cat
<chr> <dbl> <chr> <fct> <dbl> <fct>
1 2024-06-24 19 M 40 0 60%
2 2024-06-24 34 M 40 5 70%
3 2024-06-24 44 F 50 12 100%
4 2024-06-24 57 M 60 87 20%
5 2024-06-24 65 F 50 1 100%
6 2024-06-24 86 F 40 3 90%
>
> # avg_pv_cnt group by (gender, age, (gender, age))
> web_service_data %>% filter(date_id == '2024-06-30') %>%
+ group_by(gender, age) %>% grouping_sets('gender', 'age', c('gender','age')) %>%
+ summarize(avg_pv_cnt = mean(page_view_cnt))
# A tibble: 22 × 3
gender age avg_pv_cnt
<chr> <fct> <dbl>
1 F <NA> 2.28
2 M <NA> 1.92
3 N <NA> 1.63
4 <NA> 10 1.62
5 <NA> 20 3.01
6 <NA> 30 2.23
7 <NA> 40 1.77
8 <NA> 50 1.44
9 <NA> 60 2.30
10 F 10 2.33
# ℹ 12 more rows
>
> web_service_data %>% filter(date_id == '2024-06-30') %>%
+ group_by(gender, age) %>% grouping_sets('gender', 'age', c('gender','age'))
An object of class "grouped_df_list"
Slot "df_list":
[[1]]
# A tibble: 1,000 × 6
# Groups: gender [3]
date_id id gender age page_view_cnt product_view_cnt_cat
<chr> <dbl> <chr> <fct> <dbl> <fct>
1 2024-06-30 2 F 20 7 70%
2 2024-06-30 45 M 40 1 20%
3 2024-06-30 46 F 30 4 80%
4 2024-06-30 71 M 10 0 X
5 2024-06-30 77 M 40 3 90%
6 2024-06-30 91 M 20 1 50%
7 2024-06-30 94 F 60 1 20%
8 2024-06-30 96 F 60 2 50%
9 2024-06-30 105 F 40 0 60%
10 2024-06-30 132 M 60 1 X
# ℹ 990 more rows
[[2]]
# A tibble: 1,000 × 6
# Groups: age [6]
date_id id gender age page_view_cnt product_view_cnt_cat
<chr> <dbl> <chr> <fct> <dbl> <fct>
1 2024-06-30 2 F 20 7 70%
2 2024-06-30 45 M 40 1 20%
3 2024-06-30 46 F 30 4 80%
4 2024-06-30 71 M 10 0 X
5 2024-06-30 77 M 40 3 90%
6 2024-06-30 91 M 20 1 50%
7 2024-06-30 94 F 60 1 20%
8 2024-06-30 96 F 60 2 50%
9 2024-06-30 105 F 40 0 60%
10 2024-06-30 132 M 60 1 X
# ℹ 990 more rows
[[3]]
# A tibble: 1,000 × 6
# Groups: gender, age [13]
date_id id gender age page_view_cnt product_view_cnt_cat
<chr> <dbl> <chr> <fct> <dbl> <fct>
1 2024-06-30 2 F 20 7 70%
2 2024-06-30 45 M 40 1 20%
3 2024-06-30 46 F 30 4 80%
4 2024-06-30 71 M 10 0 X
5 2024-06-30 77 M 40 3 90%
6 2024-06-30 91 M 20 1 50%
7 2024-06-30 94 F 60 1 20%
8 2024-06-30 96 F 60 2 50%
9 2024-06-30 105 F 40 0 60%
10 2024-06-30 132 M 60 1 X
# ℹ 990 more rows
>
> # avg_pv_cnt group by ((gender, age, product_view_cnt_cat), product_view_cnt_cat)
> web_service_data %>% filter(date_id == '2024-06-30') %>%
+ group_by(gender, age, product_view_cnt_cat) %>% grouping_sets('product_view_cnt_cat', c('product_view_cnt_cat', 'gender', 'age')) %>%
+ summarize(avg_pv_cnt = mean(page_view_cnt)) %>% pivot_wider(names_from = product_view_cnt_cat, values_from = avg_pv_cnt)
# A tibble: 14 × 11
gender age X `20%` `40%` `50%` `60%` `70%` `80%` `90%` `100%`
<chr> <fct> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 <NA> <NA> 1.50 1.80 2.05 2.31 2.72 2.89 2.8 3.79 2.82
2 F 10 1.4 2 1.4 2.67 4 NA NA 4 NA
3 F 20 0 3.5 2.08 2.29 3.83 2.57 3.45 4.83 2.25
4 F 30 0.833 2.5 4.5 2.88 3 1.75 3.5 3 3.17
5 F 40 1.33 1.9 2.7 2.2 1.22 3 3.38 4 2
6 F 50 0.462 1.5 2 2.5 1.2 4 2.5 5.33 3.5
7 F 60 1.19 1.71 1 1.33 3 3 1.5 2 3
8 M 10 0.375 0.833 1.14 3 1 0 NA NA NA
9 M 20 1.14 3.17 3.16 3.55 4.5 3 NA 3.5 7
10 M 30 0.824 1.62 1.31 2.7 3.38 2.5 1.86 3.5 NA
11 M 40 0.889 0.933 2.06 0.833 1.88 3.25 1.6 1.67 NA
12 M 50 0.562 1.07 1.06 2.6 2 0 0.5 0 NA
13 M 60 3.06 2.69 4 3.5 0 8 2 1 NA
14 N 10 1.63 1.11 6 NA NA NA NA NA NA
>
> # avg_pv_cnt group by (gender, age, (gender, age))
> web_service_data %>% filter(date_id == '2024-06-30') %>%
+ group_by(gender, age) %>% with_rollup() %>%
+ summarize(avg_pv_cnt = mean(page_view_cnt))
# A tibble: 17 × 3
# Groups: gender [4]
gender age avg_pv_cnt
<chr> <fct> <dbl>
1 F 10 2.33
2 F 20 2.86
3 F 30 2.67
4 F 40 2.33
5 F 50 2.24
6 F 60 1.48
7 M 10 0.92
8 M 20 3.19
9 M 30 1.91
10 M 40 1.31
11 M 50 0.907
12 M 60 2.99
13 N 10 1.63
14 F <NA> 2.28
15 M <NA> 1.92
16 N <NA> 1.63
17 <NA> <NA> 2.04
>
> proc.time()
user system elapsed
1.42 0.18 1.57