Calculate max value across multiple columns by multiple groups - r

Question

I have a data file with numeric values in three columns and two grouping variables (ID and Group) from which I need to calculate a single max value by ID and Group:
structure(list(ID = structure(c(1L, 1L, 1L, 2L), .Label = c("a1",
"a2"), class = "factor"), Group = structure(c(1L, 1L, 2L, 2L), .Label =
c("abc",
"def"), class = "factor"), Score1 = c(10L, 0L, 0L, 5L), Score2 = c(0L,
0L, 5L, 10L), Score3 = c(0L, 11L, 2L, 11L)), class = "data.frame", row.names =
c(NA,
-4L))
The result I am trying to obtain is:
structure(list(ID = structure(c(1L, 1L, 2L), .Label = c("a1",
"a2"), class = "factor"), Group = structure(c(1L, 2L, 2L), .Label = c("abc",
"def"), class = "factor"), Max = c(11L, 5L, 11L)), class = "data.frame",
row.names = c(NA,
-3L))
I am trying the following in dplyr:
SampTable<-SampDF %>% group_by(ID,Group) %>%
summarize(max = pmax(SampDF$Score1, SampDF$Score2,SampDF$Score3))
But it generates this error:
Error in summarise_impl(.data, dots) :
Column `max` must be length 1 (a summary value), not 4
Is there an easy way to achieve this in dplyr or data.table?

Answer 1

Solution using data.table. Find max value on 3:5 columns (Score columns) by ID and Group.
library(data.table)
setDT(d)
d[, .(Max = do.call(max, .SD)), .SDcols = 3:5, .(ID, Group)]
ID Group Max
1: a1 abc 11
2: a1 def 5
3: a2 def 11
Data:
d <- structure(list(ID = structure(c(1L, 1L, 1L, 2L), .Label = c("a1",
"a2"), class = "factor"), Group = structure(c(1L, 1L, 2L, 2L), .Label =
c("abc",
"def"), class = "factor"), Score1 = c(10L, 0L, 0L, 5L), Score2 = c(0L,
0L, 5L, 10L), Score3 = c(0L, 11L, 2L, 11L)), class = "data.frame", row.names =
c(NA,
-4L))

Answer 2

A solution using tidyverse.
library(tidyverse)
dat2 <- dat1 %>%
gather(Column, Value, starts_with("Score")) %>%
group_by(ID, Group) %>%
summarise(Max = max(Value)) %>%
ungroup()
dat2
# # A tibble: 3 x 3
# ID Group Max
# <fct> <fct> <dbl>
# 1 a1 abc 11
# 2 a1 def 5
# 3 a2 def 11

Answer 3

Here are couple of other options with tidyverse
library(tidyverse)
df1 %>%
group_by(ID, Group) %>%
nest %>%
mutate(Max = map_dbl(data, ~ max(unlist(.x)))) %>%
select(-data)
Or using pmax
df1 %>%
mutate(Max = pmax(!!! rlang::syms(names(.)[3:5]))) %>%
group_by(ID, Group) %>%
summarise(Max = max(Max))
# A tibble: 3 x 3
# Groups: ID [?]
# ID Group Max
# <fct> <fct> <dbl>
#1 a1 abc 11
#2 a1 def 5
#3 a2 def 11
Or using base R
aggregate(cbind(Max = do.call(pmax, df1[3:5])) ~ ID + Group, df1, max)

Answer 4

Here is a tidyverse solution using nest :
library(tidyverse)
df %>%
nest(-(1:2),.key="Max") %>%
mutate_at("Max",map_dbl, max)
# ID Group Max
# 1 a1 abc 11
# 2 a1 def 5
# 3 a2 def 11
In base R:
res <- aggregate(. ~ ID + Group,df,max)
res <- cbind(res[1:2], Max = do.call(pmax,res[-(1:2)]))
res
# ID Group Max
# 1 a1 abc 11
# 2 a1 def 5
# 3 a2 def 11

Answer 5

Here is a base R solution
# gives 2x2 table
x <- by(df[, !names(df) %in% c("ID", "Group")], list(df$ID, df$Group), max)
# get requested format
tmp <- expand.grid(ID = rownames(x), Group = colnames(x))
tmp$Max <- as.vector(x)
tmp[complete.cases(tmp), ]
#R ID Group Max
#R 1 a1 abc 11
#R 3 a1 def 5
#R 4 a2 def 11
with
df <- structure(list(
ID = structure(c(1L, 1L, 1L, 2L), .Label = c("a1", "a2"), class = "factor"),
Group = structure(c(1L, 1L, 2L, 2L), .Label = c("abc", "def"), class = "factor"),
Score1 = c(10L, 0L, 0L, 5L), Score2 = c(0L, 0L, 5L, 10L),
Score3 = c(0L, 11L, 2L, 11L)),
class = "data.frame", row.names = c(NA, -4L))