Arrange Within a Group with Dplyr

Arrange within a group with dplyr

I think the problem in your second example is that your are using desc on all the variables at the same time, so it is only applied to the month column.

   flights %>% group_by(month, day)  %>% top_n(3, dep_delay) %>% 
        arrange(
            month, 
            day,  
            desc(dep_delay)
        )

Source: local data frame [1,108 x 19]
Groups: month, day [365]

    year month   day dep_time sched_dep_time dep_delay arr_time sched_arr_time arr_delay carrier flight tailnum origin
   <int> <int> <int>    <int>          <int>     <dbl>    <int>          <int>     <dbl>   <chr>  <int>   <chr>  <chr>
1   2013     1     1      848           1835       853     1001           1950       851      MQ   3944  N942MQ    JFK
2   2013     1     1     2343           1724       379      314           1938       456      EV   4321  N21197    EWR
3   2013     1     1     1815           1325       290     2120           1542       338      EV   4417  N17185    EWR
4   2013     1     2     2131           1512       379     2340           1741       359      UA    488  N593UA    LGA
5   2013     1     2     1607           1030       337     2003           1355       368      AA    179  N324AA    JFK
6   2013     1     2     1412            838       334     1710           1147       323      UA    468  N474UA    EWR
7   2013     1     3     2056           1605       291     2239           1754       285      9E   3459  N928XJ    JFK
8   2013     1     3     2008           1540       268     2339           1909       270      DL   2027  N338NW    JFK
9   2013     1     3     2012           1600       252     2314           1857       257      B6    369  N558JB    LGA
10  2013     1     4     2123           1635       288     2332           1856       276      EV   3805  N29917    EWR
# ... with 1,098 more rows, and 6 more variables: dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>, minute <dbl>,
#   time_hour <dttm>

R, dplyr - combination of group_by() and arrange() does not produce expected result?

I think you want

ToothGrowth %>%
  arrange(supp,len)

The chaining system just replaces nested commands, so first you are grouping, then ordering that grouped result, which breaks the original ordering.

Hw can I use arrange in dplyr to order groups?

Perhaps this? First, group by cyl, then fill a new column with mean(mpg), which you can then arrange by however you want, and finally remove the temporary mean(mpg) column.

mtcars %>% 
  group_by(cyl) %>% 
  mutate(mean_mpg = mean(mpg)) %>%
  arrange(desc(mean_mpg)) %>%
  select(-mean_mpg)

#> # A tibble: 32 x 11
#> # Groups:   cyl [3]
#>      mpg   cyl  disp    hp  drat    wt  qsec    vs    am  gear  carb
#>    <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#>  1  22.8     4 108      93  3.85  2.32  18.6     1     1     4     1
#>  2  24.4     4 147.     62  3.69  3.19  20       1     0     4     2
#>  3  22.8     4 141.     95  3.92  3.15  22.9     1     0     4     2
#>  4  32.4     4  78.7    66  4.08  2.2   19.5     1     1     4     1
#>  5  30.4     4  75.7    52  4.93  1.62  18.5     1     1     4     2
#>  6  33.9     4  71.1    65  4.22  1.84  19.9     1     1     4     1
#>  7  21.5     4 120.     97  3.7   2.46  20.0     1     0     3     1
#>  8  27.3     4  79      66  4.08  1.94  18.9     1     1     4     1
#>  9  26       4 120.     91  4.43  2.14  16.7     0     1     5     2
#> 10  30.4     4  95.1   113  3.77  1.51  16.9     1     1     5     2
#> # ... with 22 more rows

Arrange groups in dplyr with aggregation function

Does this work:

df %>% group_by(g) %>% mutate(m = mean(x)) %>% arrange(m) %>% select(-m)
# A tibble: 7 x 2
# Groups:   g [3]
      g     x
  <dbl> <dbl>
1     2    -2
2     2    -3
3     2    -3
4     0     0
5     0     1
6     1     1
7     1     2

Arrange values within a specific group

You could do :

library(dplyr)
library(purrr)

df_nested$data <- map2(df_nested$data, df_nested$group2,~if(.y == 2) 
                       arrange(.x, -.x$id) else .x)

So data where group2 is not equal to 2 is not sorted

df_nested$data[[1]]
# A tibble: 2 x 3
#  value2 value3    id
#   <dbl>  <dbl> <int>
#1  13.1  -89.0      1
#2   9.76  -3.29     2

and where group2 is 2 is sorted.

df_nested$data[[4]]
# A tibble: 2 x 3
#value2 value3    id
# <dbl>  <dbl> <int>
#1   15.0  -28.4   4
#2   31.0  -22.8   3

If you want to combine them do :

map2_df(df_nested$data, df_nested$group2,~if(.y == 2) arrange(.x, -.x$id) else .x)

dplyr arrange - sort groups by another column and then sort within each group

You may try

library(dplyr)
df %>% 
  arrange(Tot_Orders, OrderNo) %>% 
  group_by(Customer)
#   Customer OrderNo Tot_Orders
#1      ccc       1          1
#2      bbb       1          2
#3      bbb       2          2
#4      aaa       1          3
#5      aaa       2          3
#6      aaa       3          3

df1 %>%
    arrange(Tot_Orders, OrderNo) %>% 
    group_by(Customer)
#    Customer OrderNo Tot_Orders
#1      bbb       1          1
#2      ccc       1          2
#3      ccc       2          2
#4      aaa       1          3
#5      aaa       2          3
#6      aaa       3          3

data

df <- structure(list(Customer = c("aaa", "aaa", "aaa", "bbb", "bbb", 
"ccc"), OrderNo = c(2L, 1L, 3L, 2L, 1L, 1L), Tot_Orders = c(3L, 
3L, 3L, 2L, 2L, 1L)), .Names = c("Customer", "OrderNo", "Tot_Orders"
), class = "data.frame", row.names = c(NA, -6L))

df1 <- structure(list(Customer = c("aaa", "aaa", "aaa", "bbb", "ccc", 
"ccc"), OrderNo = c(2L, 1L, 3L, 1L, 1L, 2L), Tot_Orders = c(3L, 
3L, 3L, 1L, 2L, 2L)), .Names = c("Customer", "OrderNo", "Tot_Orders"
), class = "data.frame", row.names = c(NA, -6L))

How to dplyr::arrange groups within a df by the mean of group measure?

I would try creating a variable that specifies the mean of the visCredPrcnt variable by CredentialQ group, and then pass that in the arrange call like so:

credData <- ReShapeAdCredSubset %>%
    group_by(CredentialQ, year) %>%
    summarise(vizCredPrcnt = (sum(credential_wIndiv, na.rm = TRUE) / (sum(credential_wAll, na.rm = TRUE)))) %>%
    ungroup() %>%
    group_by(CredentialQ) %>%
    summarize(meanVizCredPrcnt = mean(visCredPrcnt, na.rm = T)) %>%
    arrange(CredentialQ, year, desc(meanVizCredPrcnt))

dplyr - How to obtain the order of one column within a group?

library(dplyr)

tibbly = tibble(age = c(10,30,50,10,30,50,10,30,50,10,30,50),
                grouping1 = c("A","A","A","A","A","A","B","B","B","B","B","B"),
                grouping2 = c("X", "X", "X","Y","Y","Y","X","X","X","Y","Y","Y"),
                value = c(1,2,3,4,4,6,2,5,3,6,3,2))

tibbly %>% 
  group_by(grouping1, grouping2) %>%                  # for each group
  arrange(desc(value)) %>%                            # arrange value descending
  summarise(order = paste0(age, collapse = ",")) %>%  # get the order of age as a strings
  ungroup()                                           # forget the grouping

# # A tibble: 4 x 3
#   grouping1 grouping2 order   
#   <chr>     <chr>     <chr>   
# 1 A         X         50,30,10
# 2 A         Y         50,10,30
# 3 B         X         30,50,10
# 4 B         Y         10,30,50

---

Related Topics