Counting the elements in rows and map to column in r - r

I would like summarize my data by counting the entities and create counting_column for each entity.
let say:
df:
id class
1 A
1 B
1 A
1 A
1 B
1 c
2 A
2 B
2 B
2 D
I want to create a table like
id A B C D
1 3 2 1 0
2 1 2 0 1
How can I do this in R using apply function?


df <- structure(list(id = c(1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L),
class = structure(c(1L, 2L, 1L, 1L, 2L, 3L, 1L, 2L, 2L, 4L
), .Label = c("A", "B", "C", "D"), class = "factor")), .Names = c("id",
"class"), class = "data.frame", row.names = c(NA, -10L))
with(df, table(id, class))
# class
#id A B C D
# 1 3 2 1 0
# 2 1 2 0 1
xtabs(~ id + class, df)
# class
#id A B C D
# 1 3 2 1 0
# 2 1 2 0 1
tapply(rep(1, nrow(df)), df, length, default = 0)
# class
#id A B C D
# 1 3 2 1 0
# 2 1 2 0 1


This seems like a very strange requirement but if you insist on using apply then the function count counts the number of rows for which id equals x and class equals y. It is applied to every combination of id and class to get a using nested apply calls. Finally we add the row and column names.
uid <- unique(DF$id)
uclass <- unique(DF$class)
count <- function(x, y, DF) sum(x == DF$id & y == DF$class)
a <- apply(matrix(uclass), 1, function(u) apply(matrix(uid), 1, count, u, DF))
dimnames(a) <- list(uid, uclass)
giving:
> a
A B c D
1 3 2 1 0
2 1 2 0 1
Note
We used this for DF
Lines <- "id class
1 A
1 B
1 A
1 A
1 B
1 c
2 A
2 B
2 B
2 D"
DF <- read.table(text = Lines, header = TRUE)

Related

How to create multiple columns in r dataframe by implementing some query conditions

I have a dataset which is similar to the following:
Age Food_1_1 Food_1_2 Food_1_3 Amount_1_1 Amount_1_2 Amount_1_3
6-9 a b a 2 3 4
6-9 b b c 1 2 3
6-9 c a 4 1
9-10 c c b 1 3 1
9-10 c a b 1 2 1
Using R, I want to get the following data set which contains new set of columns a, b and c by adding the corresponding values:
Age Food_1_1 Food_1_2 Food_1_3 Amount_1_1 Amount_1_2 Amount_1_3 a b c
6-9 a b a 2 3 4 6 3 0
6-9 b b c 1 2 3 0 3 3
6-9 c a 4 1 1 0 4
9-10 c c b 1 3 1 0 1 4
9-10 c a b 1 2 1 2 1 1
Note: My data also contains missing values. The variables Monday:Wednesday are factors and the variables Value1:Value3 are numeric. For more clearity: 1st row of column "a" contains the addition of all values through Value1 to Value3 related to a (say for example 2+4 =6).

One way using base R:
data$id <- 1:nrow(data) # Create a unique id
vlist <- list(grep("day$", names(data)), grep("^Value", names(data)))
d1 <- reshape(data, direction="long", varying=vlist, v.names=c("Day","Value"))
d2 <- aggregate(Value~id+Day, FUN=sum, na.rm=TRUE, data=d1)
d3 <- reshape(d2, direction="wide", v.names="Value", timevar="Day")
d3[is.na(d3)] <- 0
merge(data, d3, by="id", all.x=TRUE)
# id Age Monday Tuesday Wednesday Value1 Value2 Value3 Value.a Value.b Value.c
#1 1 6-9 a b a 2 3 4 6 3 0
#2 2 6-9 b b c 1 2 3 0 3 3
#3 3 6-9 <NA> c a NA 4 1 1 0 4
#4 4 9-10 c c b 1 3 1 0 1 4
#5 5 9-10 c a b 1 2 1 2 1 1
Data:
data <- structure(list(Age = structure(c(1L, 1L, 1L, 2L, 2L), .Label = c("6-9",
"9-10"), class = "factor"), Monday = structure(c(1L, 2L, NA,
3L, 3L), .Label = c("a", "b", "c"), class = "factor"), Tuesday = structure(c(2L,
2L, 3L, 3L, 1L), .Label = c("a", "b", "c"), class = "factor"),
Wednesday = structure(c(1L, 3L, 1L, 2L, 2L), .Label = c("a",
"b", "c"), class = "factor"), Value1 = c(2L, 1L, NA, 1L,
1L), Value2 = c(3L, 2L, 4L, 3L, 2L), Value3 = c(4L, 3L, 1L,
1L, 1L)), class = "data.frame", row.names = c(NA, -5L))

You can use below code:
data[] <- lapply(data, as.character)
data$rownumber<-rownames(data)
x<-gather(data[,c(1:4,8)], Day, Letter, Monday:Wednesday) %>% mutate(row2 = rownames(x))
y<-gather(data[,c(1,5:7,8)], Day, Value, Value1:Value3)%>% mutate(row2 = rownames(y))
z<-left_join(x, y, by =c("Age","rownumber", "row2")) %>% group_by(Age, rownumber, Letter) %>% dplyr::summarise(suma = sum(as.numeric(Value), na.rm = T)) %>% mutate(suma = replace_na(suma, 0))
z<-dcast(z, rownumber ~ Letter , value.var="suma") %>% left_join(data, z, by = "rownumber")
z$Var.2<-NULL
z[is.na(z)]<-0
Output:
rownumber a b c Age Monday Tuesday Wednesday Value1 Value2 Value3
1 1 6 3 0 6-9 a b a 2 3 4
2 2 0 3 3 6-9 b b c 1 2 3
3 3 1 0 4 6-9 c a 0 4 1
4 4 0 1 4 9-10 c c b 1 3 1
5 5 2 1 1 9-10 c a b 1 2 1

Average (/2) of each row in ONE column in R

DF
ID B C D
1 A 1 1 3
2 B 2 3 1
3 C 1 1 1
4 D 3 1 1
5 E 1 0 0
Given a dataframe such the one mentioned above, how can I quickly calculate the means for each row in one column and store them in another column of the dataframe? For example the average of column B would be: 0.5, 1, 0.5, 1,5, 0.5.
And is it possible to have a function that does it automatically for several columns at once?

Option is to get the matching row element from 'ID' to divide the column with the value
f1 <- function(dat, colNm) transform(dat,
newCol = dat[[colNm]]/dat[match(colNm, ID), colNm])
f1(DF, 'B')
# ID B C D newCol
#1 A 1 1 3 0.5
#2 B 2 3 1 1.0
#3 C 1 1 1 0.5
#4 D 3 1 1 1.5
#5 E 1 0 0 0.5
If it is to divide by a constant value, then just do
DF[-1] <- DF[-1]/2
data
DF <- structure(list(ID = c("A", "B", "C", "D", "E"), B = c(1L, 2L,
1L, 3L, 1L), C = c(1L, 3L, 1L, 1L, 0L), D = c(3L, 1L, 1L, 1L,
0L)), class = "data.frame", row.names = c("1", "2", "3", "4",
"5"))

Count and number each occurrence of a duplicate row(based on the values of 2 variables) in R

a b #Encounter
1 112233 1
2 334455 1
1 112233 2
3 445566 1
2 334455 2
2 334455 3
3 445566 2
3 445566 3
3 445566 4
How would I calculate #Encounter, given column a and b, on R?
The Excel code would be: =countifs(a(Range), a, b(Range), b)

An option in base R would be to use ave
df1$Encounter <- with(df1, ave(seq_along(a), a, b, FUN = seq_along))
df1$Encounter
#[1] 1 1 2 1 2 3 2 3 4
Or in data.table
library(data.table)
setDT(df1)[, Encounter := rowid(a, b)]
data
df1 <- structure(list(a = c(1L, 2L, 1L, 3L, 2L, 2L, 3L, 3L, 3L), b = c(112233L,
334455L, 112233L, 445566L, 334455L, 334455L, 445566L, 445566L,
445566L)), row.names = c(NA, -9L), class = "data.frame")

Cumulative Count Paste

I have this dataset:
ID Set Type Count
1 1 1 A NA
2 2 1 R NA
3 3 1 R NA
4 4 1 U NA
5 5 1 U NA
6 6 1 U NA
7 7 2 A NA
8 8 3 R NA
9 9 3 R NA
As dputs:
mystart <- structure(list(ID = 1:9, Set = c(1L, 1L, 1L, 1L, 1L, 1L, 2L,
3L, 3L), Type = structure(c(1L, 2L, 2L, 3L, 3L, 3L, 1L, 2L, 2L
), .Label = c("A", "R", "U"), class = "factor"), Count = c(NA,
NA, NA, NA, NA, NA, NA, NA, NA)), .Names = c("ID", "Set", "Type",
"Count"), class = "data.frame", row.names = c(NA, -9L))
By using dplyr package how can I obtain this:
ID Set Type Count
1 1 1 A A1
2 2 1 R A1R1
3 3 1 R A1R2
4 4 1 U A1R2U1
5 5 1 U A1R2U2
6 6 1 U A1R2U3
7 7 2 A A1
8 8 3 R R1
9 9 3 R R2
Again dputs:
myend <- structure(list(ID = 1:9, Set = c(1L, 1L, 1L, 1L, 1L, 1L, 2L,
3L, 3L), Type = structure(c(1L, 2L, 2L, 3L, 3L, 3L, 1L, 2L, 2L
), .Label = c("A", "R", "U"), class = "factor"), Count = structure(c(1L,
2L, 3L, 4L, 5L, 6L, 1L, 7L, 8L), .Label = c("A1", "A1R1", "A1R2",
"A1R2U1", "A1R2U2", "A1R2U3", "R1", "R2"), class = "factor")), .Names = c("ID",
"Set", "Type", "Count"), class = "data.frame", row.names = c(NA,
-9L))
In short, I want to count the observations of the column "type" within column "set" and print this count(text) cumulatively.
Examining similar posts, I got closely to this:
myend <- structure(list(ID = 1:9, Set = c(1L, 1L, 1L, 1L, 1L, 1L, 2L,
3L, 3L), Type = structure(c(1L, 2L, 2L, 3L, 3L, 3L, 1L, 2L, 2L
), .Label = c("A", "R", "U"), class = "factor"), Count = c(1L,
1L, 2L, 1L, 2L, 3L, 1L, 1L, 2L)), .Names = c("ID", "Set", "Type",
"Count"), class = "data.frame", row.names = c(NA, -9L))
With the code:
library(dplyr)
myend <- read.table("mydata.txt", header=TRUE, fill=TRUE)
myend %>%
group_by(Set, Type) %>%
mutate(Count = seq(n())) %>%
ungroup(myend)
Thank you very much for your help,

Base R version :
aggregateGroup <- function(x){
vecs <- Reduce(f=function(a,b){ a[b] <- sum(a[b],1L,na.rm=TRUE); a },
init=integer(0),
as.character(x),
accumulate = TRUE)
# vecs is a list with something like this :
# [[1]]
# integer(0)
# [[2]]
# A
# 1
# [[3]]
# A R
# 1 1
# ...
# so we simply turn those vectors into characters using vapply and paste
# (excluding the first)
vapply(vecs,function(y) paste0(names(y),y,collapse=''),FUN.VALUE='')[-1]
}
split(mystart$Count,mystart$Set) <- lapply(split(mystart$Type,mystart$Set), aggregateGroup)
> mystart
ID Set Type Count
1 1 1 A A1
2 2 1 R A1R1
3 3 1 R A1R2
4 4 1 U A1R2U1
5 5 1 U A1R2U2
6 6 1 U A1R2U3
7 7 2 A A1
8 8 3 R R1
9 9 3 R R2

A dplyr version:
mystart %>%
group_by(Set) %>%
mutate(Count = paste0('A', cumsum(Type == 'A'),
'R', cumsum(Type == 'R'),
'U', cumsum(Type == 'U'))) %>%
ungroup()
Which yields
# A tibble: 9 x 4
ID Set Type Count
<int> <int> <chr> <chr>
1 1 1 A A1R0U0
2 2 1 R A1R1U0
3 3 1 R A1R2U0
4 4 1 U A1R2U1
5 5 1 U A1R2U2
6 6 1 U A1R2U3
7 7 2 A A1R0U0
8 8 3 R A0R1U0
9 9 3 R A0R2U0
If you want to omit the variables with count zero, you'd need to wrap a function around it like so
mygroup <- function(lst) {
name <- names(lst)
vectors <- lapply(seq_along(lst), function(i) {
x <- lst[[i]]
char <- name[i]
x <- ifelse(x == 0, "", paste0(char, x))
return(x)
})
return(do.call("paste0", vectors))
}
mystart %>%
group_by(Set) %>%
mutate(Count = mygroup(list(A = cumsum(Type == 'A'),
R = cumsum(Type == 'R'),
U = cumsum(Type == 'U')))) %>%
ungroup()
This yields
# A tibble: 9 x 4
ID Set Type Count
<int> <int> <chr> <chr>
1 1 1 A A1
2 2 1 R A1R1
3 3 1 R A1R2
4 4 1 U A1R2U1
5 5 1 U A1R2U2
6 6 1 U A1R2U3
7 7 2 A A1
8 8 3 R R1
9 9 3 R R2

One line solve with data.table
you gotta first do
require(data.table)
mystart <- as.data.table(mystart)
then just use one line
mystart[, .(Type,
count = paste0(
'A',
cumsum(Type == 'A'),
'R',
countR = cumsum(Type == 'R'),
'U',
countU = cumsum(Type == 'U')
)),
by = c('Set')]
first you want cumsum each type and paste them together by 'set'
cumsum(Type=='A') equals the count, since when Type==A, it's 1, otherwise it's 0.
you wanted to paste them into one column also. So, paste0() is good to use.
you still wanted the Type column, so I included Type in the line.
The output:
Set Type count
1: 1 A A1R0U0
2: 1 R A1R1U0
3: 1 R A1R2U0
4: 1 U A1R2U1
5: 1 U A1R2U2
6: 1 U A1R2U3
7: 2 A A1R0U0
8: 3 R A0R1U0
9: 3 R A0R2U0
Hope this helps.
btw, if you want count 0 ignored, you gotta design some if-esle clause yourself.
basically you want this: if cumsum(something) ==0, NULL, esle paste0('something', cumsum(something)), then you paste0() them together.
It's gonna get nasty, I'm not writing it. you get the idea

Here's a base solution.
We can paste raw letters toseq_along of letter groups to get the last 2 characters, then paste the result to the last element of the previous result, using Reduce.
On top of this we use ave to compute by group.
fun <- function(x,y) paste0(x[length(x)],y,seq_along(y))
mystart$Count <- ave(as.character(mystart$Type),mystart$Set,
FUN = function(x) unlist(Reduce(fun,split(x,x),init=NULL,accumulate = TRUE)))
# ID Set Type Count
# 1 1 1 A A1
# 2 2 1 R A1R1
# 3 3 1 R A1R2
# 4 4 1 U A1R2U1
# 5 5 1 U A1R2U2
# 6 6 1 U A1R2U3
# 7 7 2 A A1
# 8 8 3 R R1
# 9 9 3 R R2
Details
split(x,x) splits letters as shown here for first Set:
with(subset(mystart,Set==1),split(Type,Type))
# $A
# [1] "A"
#
# $R
# [1] "R" "R"
#
# $U
# [1] "U" "U" "U"
Then fun does this type of operations, helped by Reduce :
fun(NULL,"A") # [1] "A1"
fun("A1",c("R","R")) # [1] "A1R1" "A1R2"
fun(c("A1R1","A1R2"),c("U","U","U")) # [1] "A1R2U1" "A1R2U2" "A1R2U3"
Bonus solution
This other base solution, using rle and avoiding split gives the same output for given example (and whenever Type values are grouped in Sets), but not with mystart2 <- rbind(mystart,mystart) for instance.
fun2 <- function(x){
rle_ <- rle(x)
suffix <- paste0(x,sequence(rle_$length))
prefix <- unlist(mapply(rep,
lag(unlist(
Reduce(paste0,paste0(rle_$values,rle_$lengths),accumulate=TRUE)
),rle_$lengths[1]),
each=rle_$lengths))
prefix[is.na(prefix)] <- ""
paste0(prefix,suffix)
}
mystart$Count2 <-ave(as.character(mystart$Type), mystart$Set,FUN=fun2)

Many elegant solutions have been provided for the problem. Still I was looking for something dplyr way (without-cumsum on fixed types). The function is generic enough to handle additional values of Type.
A solution with help of a custom function as:
library(dplyr)
mystart %>% group_by(Set, Type) %>%
mutate(type_count = row_number()) %>%
mutate(TypeMod = paste0(Type,type_count)) %>%
group_by(Set) %>%
mutate(Count = cumCat(TypeMod, type_count)) %>%
select(-type_count, -TypeMod)
cumCat <- function(x, y){
retVal <- character(length(x))
prevVal = ""
lastGrpVal = ""
for ( i in seq_along(x)){
if(y[i]==1){
lastGrpVal = prevVal
}
retVal[i] = paste0(lastGrpVal,x[i])
prevVal = retVal[i]
}
retVal
}
# # Groups: Set [3]
# ID Set Type Count
# <int> <int> <fctr> <chr>
# 1 1 1 A A1
# 2 2 1 R A1R1
# 3 3 1 R A1R2
# 4 4 1 U A1R2U1
# 5 5 1 U A1R2U2
# 6 6 1 U A1R2U3
# 7 7 2 A A1
# 8 8 3 R R1
# 9 9 3 R R2

R Data Frame remove rows with max values from all columns

Hello I have the data frame and I need to remove all the rows with max values from each columns.
Example
A B C
1 2 3 5
2 4 1 1
3 1 4 3
4 2 1 1
So the output is:
A B C
4 2 1 1
Is there any quick way to do this?

We can do this with %in%
df1[!seq_len(nrow(df1)) %in% sapply(df1, which.max),]
# A B C
#4 2 1 1
If there are ties for maximum values in each row, then do
df1[!Reduce(`|`, lapply(df1, function(x) x== max(x))),]

df[-sapply(df, which.max),]
# A B C
#4 2 1 1
DATA
df = structure(list(A = c(2L, 4L, 1L, 2L), B = c(3L, 1L, 4L, 1L),
C = c(5L, 1L, 3L, 1L)), .Names = c("A", "B", "C"),
class = "data.frame", row.names = c(NA,-4L))

Resources