Rank Per Row Over Multiple Columns in R

Rank per row over multiple columns in R

You're looking for rank. To get decreasing order, first negate the data.frame.

data.frame(d, t(apply(-d, 1, rank, ties.method='min')))
#   V1 V2 V3 V1.1 V2.1 V3.1
# 1 11 21 35    3    2    1
# 2 22 12 66    2    3    1
# 3 44 22 12    1    2    3

ranking dataframe using two columns in R

You can use data.table::frank or dplyr::min_rank:

data.table::frank

dt$Rank <- frank(dt, B, A, ties.method = "min")
dt
  A B Rank
1 1 1    1
2 2 1    2
3 2 1    2
4 4 4    5
5 5 3    4

dplyr::min_rank

mutate(dt, Rank = min_rank(paste(B,A)))
  A B Rank
1 1 1    1
2 2 1    2
3 2 1    2
4 4 4    5
5 5 3    4

Data

dt <- data.frame(A = c(1,2,2,4,5), B = c(1,1,1,4,3))

tidyverse calculate ranking per row across several columns

We can use unnest_wider

library(dplyr)
library(tidyr)
library(stringr)
dat %>%
   rowwise() %>%
   mutate(my_ranks = list(rank(c_across(starts_with("x"))))) %>%
   unnest_wider(c(my_ranks)) %>%
   rename_at(vars(starts_with("...")), ~ str_replace(., fixed("..."), "rank_x"))
# A tibble: 4 x 7
#  id       x1    x2    x3  rank_x1 rank_x2 rank_x3
#  <chr> <dbl> <dbl> <dbl>    <dbl>    <dbl>    <dbl>
#1 a         1     4     2      1        3        2  
#2 b         3     2     2      3        1.5      1.5
#3 c         5     6     5      1.5      3        1.5
#4 d         7     0     9      2        1        3  

---

Another option is pmap/as_tibble_row

library(tibble)
library(purrr)
dat %>% 
     mutate(my_ranks = pmap(select(., starts_with('x')), ~ 
           as_tibble_row(rank(c(...)),
            .name_repair = ~ str_c('rank', seq_along(.))))) %>%
     unnest(c(my_ranks))
# A tibble: 4 x 7
#  id       x1    x2    x3 rank1 rank2 rank3
#  <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#1 a         1     4     2   1     3     2  
#2 b         3     2     2   3     1.5   1.5
#3 c         5     6     5   1.5   3     1.5
#4 d         7     0     9   2     1     3  

---

It can be done more straightforward with rowRanks from matrixStats

library(matrixStats)
nm1 <- names(dat)[-1]
dat[paste0('rank', nm1)] <- rowRanks(as.matrix(dat[nm1]), ties.method = 'average')

Adding multiple ranking columns in a dataframe in R

We can loop across the columns 'home' to 'work', apply the rank, while creating new column by adding prefix in .names, and probably select to keep the order

library(dplyr)
df1 <- df %>% 
   mutate(across(home:work, ~ rank(-.), .names = "rank_{.col}"))

---

Or may do this in a loop where it is more flexible in placing the column at a particular position by specifying either .after or .before. Note that we used compound assignment operator (%<>% from magrittr) to do the assignment in place

library(magrittr)
library(stringr)
for(nm in names(df)[4:6]) df %<>%
     mutate(!!str_c("rank_", nm) := rank(-.data[[nm]]), .after = all_of(nm))

-output

df
  id city uf home rank_home money rank_money work rank_work
1 34   LA RJ   10         1     2          6    2         6
2 33   BA TY    7         2     3          5   65         1
3 32   NY BN    4         4     5          4    4         5
4 12   SP SD    3         5     9          2    7         4
5 14   FR DE    1         6     8          3    9         2
6 17   BL DE    5         3    10          1    8         3

NOTE: If the column have ties, then the default method use is "average". So, ties.method can also be an argument in the rank where there are ties.

data

df <- structure(list(id = c(34L, 33L, 32L, 12L, 14L, 17L), city = c("LA", 
"BA", "NY", "SP", "FR", "BL"), uf = c("RJ", "TY", "BN", "SD", 
"DE", "DE"), home = c(10L, 7L, 4L, 3L, 1L, 5L), money = c(2L, 
3L, 5L, 9L, 8L, 10L), work = c(2L, 65L, 4L, 7L, 9L, 8L)), 
class = "data.frame", row.names = c(NA, 
-6L))

How to rank rows by two columns at once in R?

How about:

within(x, rank2 <- rank(order(v2, v1), ties.method='first'))

#   v1 v2 rank1 rank2
# 1  2  1     1     2
# 2  1  1     2     1
# 3  1  3     4     4
# 4  2  2     3     3

Ranking numerical values by row in data frame in R base

An option would be to use apply to loop over the rows (MARGIN = 1) and use rank

t(apply(df0, 1, rank))

---

Or use rowRanks from matrixStats after converting to matrix

library(matrixStats)
rowRanks(as.matrix(df0))

Apply the rank function to multiple columns at once

We can use lapply or sapply

df2 <- df1
df2[] <- lapply(df1, rank)

---

Or we can use dplyr

library(dplyr)
df %>%
  mutate(across(everything(), rank))

data

df1 <- structure(list(a = c(24L, 27L, 29L, 34L, 76L), b = c(35L, 12L, 
76L, 54L, NA), c = c(76L, 43L, 56L, 52L, NA)), class = "data.frame", 
row.names = c(NA, 
-5L))

---

Related Topics