how to mutate a column with ID in group
data.frame like:
a b c
1 a 1 1
2 a 1 2
3 a 2 3
4 b 1 4
5 b 2 5
6 b 3 6
group by a, flag start with 1, if b equals pre b,then flag=1 else flag+=1
a b c flag
1 a 1 1 1 <- group a start with 1
2 a 1 2 1 <-- in group a, 1(in row 2)=1(in row 1)
3 a 2 3 2 <- in group a, 2(in row 3)!=1(in row 2)
4 b 1 4 1 <- group b start with 1
5 b 2 5 2 <- in group b, 2(in row 5)!=1(in row 4)
6 b 3 6 3 <- in group b, 3(in row 6)!=2(in row 5)
i now using this:
for(i in 2:nrow(x)){
x[i, 'flag'] = ifelse(x[i, 'a']!=x[i-1,'a'], 1, ifelse(x[i, 'b']==x[i-1, 'b'], x[i-1, 'flag'], x[i-1,'flag']+1))
}
but it is inefficiency in large dataset
#
UPDATE
dense_rank in dplyr give me the answer
> x %>% group_by(a) %>% mutate(dense_rank(b))
Source: local data frame [10 x 4]
Groups: a
a b c dense_rank(b)
1 a x 1 1
2 a x 2 1
3 a y 3 2
4 b x 4 1
5 b y 5 2
6 b z 6 3
7 c x 7 1
8 c y 8 2
9 c z 9 3
10 c z 10 3
thanks.
I am not entirely sure what you are trying to do. But it seems to me that you are trying to assign index numbers to values in b for each group (a or b).
#I modified your example here.
a <- rep(c("a","b"), each =3)
b <- c(4,4,5,11,12,13)
c <- 1:6
foo <- data.frame(a,b,c, stringsAsFactors = F)
a b c
1 a 4 1
2 a 4 2
3 a 5 3
4 b 11 4
5 b 12 5
6 b 13 6
#Since you referred to dplyr, I will use it.
cats <- list()
for(i in unique(foo$a)){
ana <- foo %>%
filter(a == i) %>%
arrange(b) %>%
mutate(indexInb = as.integer(as.factor(b)))
cats[[i]] <- ana
}
bob <- rbindlist(cats)
a b c indexInb
1: a 4 1 1
2: a 4 2 1
3: a 5 3 2
4: b 11 4 1
5: b 12 5 2
6: b 13 6 3
Hers's a quick vectorized way to solve this without using any for loops
Base R solution using ave and transform
transform(x, flag = ave(b, a, FUN = function(x) cumsum(c(1, diff(x)))))
# a b c flag
# 1 a 1 1 1
# 2 a 1 2 1
# 3 a 2 3 2
# 4 b 1 4 1
# 5 b 2 5 2
# 6 b 3 6 3
Or a data.table solution (more efficient)
library(data.table)
setDT(x)[, flag := cumsum(c(1, diff(b))), by = a]
x
# a b c flag
# 1: a 1 1 1
# 2: a 1 2 1
# 3: a 2 3 2
# 4: b 1 4 1
# 5: b 2 5 2
# 6: b 3 6 3
Or a dplyr solution (because you tagged it)
library(dplyr)
x %>%
group_by(a) %>%
mutate(flag = cumsum(c(1, diff(b))))
# Source: local data frame [6 x 4]
# Groups: a
#
# a b c flag
# 1 a 1 1 1
# 2 a 1 2 1
# 3 a 2 3 2
# 4 b 1 4 1
# 5 b 2 5 2
# 6 b 3 6 3
Related
Say I have something like this:
ID = c("a","a","a","a","a", "b","b","b","b","b")
Group = c("1","2","3","4","5", "1","2","3","4","5")
Value = c(3, 4,2,4,3, 6, 1, 8, 9, 10)
df<-data.frame(ID,Group,Value)
I want to subtract group=5 from group=3 within the ID, with an output column which has this difference for each ID like so:
ID Group Value Want
1 a 1 3 1
2 a 2 4 1
3 a 3 2 1
4 a 4 4 1
5 a 5 3 1
6 b 1 6 2
7 b 2 1 2
8 b 3 8 2
9 b 4 9 2
10 b 5 10 2
Also, if that calculation cannot be done (i.e. group 5 is missing), NA values for the 'want' column would be ideal.
As there is only one unique 'Group' per 'ID', we can do subsetting
library(dplyr)
df %>%
group_by(ID) %>%
mutate(want = Value[Group == 5] - Value[Group == 3])
# A tibble: 10 x 4
# Groups: ID [2]
# ID Group Value want
# <fct> <fct> <dbl> <dbl>
# 1 a 1 3 1
# 2 a 2 4 1
# 3 a 3 2 1
# 4 a 4 4 1
# 5 a 5 3 1
# 6 b 1 6 2
# 7 b 2 1 2
# 8 b 3 8 2
# 9 b 4 9 2
#10 b 5 10 2
The above can be made more error-proof if we convert to numeric index and get the first element. When there are no TRUE, by using [1], it returns NA
df %>%
slice(-10) %>%
group_by(ID) %>%
mutate(want = Value[which(Group == 5)[1]] - Value[which(Group == 3)[1]])
Or use match which returns an index of NA if there are no matches, and anything with NA index returns NA which will subsequently return NA in subtraction (NA -3)
df %>%
slice(-10) %>% # removing the last row where Group is 10
group_by(ID) %>%
mutate(want = Value[match(5, Group)] - Value[match(3, Group)])
Here is a base R solution
dfout <- Reduce(rbind,
lapply(split(df,df$ID),
function(x) within(x, Want <-diff(subset(Value, Group %in% c("3","5"))))))
such that
> dfout
ID Group Value Want
1 a 1 3 1
2 a 2 4 1
3 a 3 2 1
4 a 4 4 1
5 a 5 3 1
6 b 1 6 2
7 b 2 1 2
8 b 3 8 2
9 b 4 9 2
10 b 5 10 2
A data.table method:
library(data.table)
setDT(df)[, want := (Value[Group == 5] - Value[Group == 3]), by = .(ID)]
df
# ID Group Value want
# 1: a 1 3 1
# 2: a 2 4 1
# 3: a 3 2 1
# 4: a 4 4 1
# 5: a 5 3 1
# 6: b 1 6 2
# 7: b 2 1 2
# 8: b 3 8 2
# 9: b 4 9 2
# 10: b 5 10 2
Here is a solution using base R.
unsplit(
lapply(
split(df, df$ID),
function(d) {
x5 = d$Value[d$Group == "5"]
x5 = ifelse(length(x5) == 1, x5, NA)
x3 = d$Value[d$Group == "3"]
x3 = ifelse(length(x3) == 1, x3, NA)
d$Want = x5 - x3
d
}),
df$ID)
how do I extract specific row of data when the column has repetitive value? my data looks like this: I want to extract the row of the end of each repeat of x (A 3 10, A 2 3 etc) or the index of the last value
Name X M
A 1 1
A 2 9
A 3 10
A 1 1
A 2 3
A 1 5
A 2 6
A 3 4
A 4 5
A 5 3
B 1 1
B 2 9
B 3 10
B 1 1
B 2 3
Expected output
Index Name X M
3 A 3 10
5 A 2 3
10 A 5 3
13 B 3 10
15 B 2 3
Using base R duplicated and cumsum:
dups <- !duplicated(cumsum(dat$X == 1), fromLast=TRUE)
cbind(dat[dups,], Index=which(dups))
# Name X M Index
#3 A 3 10 3
#5 A 2 3 5
#10 A 5 3 10
#13 B 3 10 13
#15 B 2 3 15
A solution using dplyr.
library(dplyr)
df2 <- df %>%
mutate(Flag = ifelse(lead(X) < X, 1, 0)) %>%
mutate(Index = 1:n()) %>%
filter(Flag == 1 | is.na(Flag)) %>%
select(Index, X, M)
df2
# Index X M
# 1 3 3 10
# 2 5 2 3
# 3 10 5 3
# 4 13 3 10
# 5 15 2 3
Flag is a column showing if the next number in A is smaller than the previous number. If TRUE, Flag is 1, otherwise is 0. We can then filter for Flag == 1 or where Flag is NA, which is the last row. df2 is the final filtered data frame.
DATA
df <- read.table(text = "Name X M
A 1 1
A 2 9
A 3 10
A 1 1
A 2 3
A 1 5
A 2 6
A 3 4
A 4 5
A 5 3
B 1 1
B 2 9
B 3 10
B 1 1
B 2 3",
header = TRUE, stringsAsFactors = FALSE)
I have dataframe like below :-
x<-c(3,2,1,8,7,11,10,9,7,5,4)
y<-c("a","a","a", "b","b","c","c","c","c","c","c")
z<-c(2,2,2,1,1,3,3,3,3,3,3)
df<-data.frame(x,y,z)
df
x y z
1 3 a 2
2 2 a 2
3 1 a 2
4 8 b 1
5 7 b 1
6 11 c 3
7 10 c 3
8 9 c 3
9 7 c 3
10 5 c 3
11 4 c 3
I want to select top n row for each group by column y where n is provided in column z.
So the output should be like :
output:
x y z
1 3 a 2
2 2 a 2
3 8 b 1
4 11 c 3
5 10 c 3
6 9 c 3
A solution with base R:
# df is split according to y, then we keep only the top "z" value (after ordering x)
# and rbind everything back together:
do.call(rbind,
lapply(split(df, df$y),
function(df1) df1[order(df1$x, decreasing=TRUE), ][1:unique(df1$z), ]))
# x y z
#a.1 3 a 2
#a.2 2 a 2
#b 8 b 1
#c.6 11 c 3
#c.7 10 c 3
#c.8 9 c 3
EDIT:
A much more direct way (still in base R) provided in comment by #mt1022:
df[ave(1:nrow(df), df$y, FUN = seq_along) <= df$z, ]
# x y z
#1 3 a 2
#2 2 a 2
#4 8 b 1
#6 11 c 3
#7 10 c 3
#8 9 c 3
One approach with data.table:
library(data.table)
setDT(df)
df[,.(inc=seq_len(.N)<=z,x,z),by=.(y)][inc==T ,-2]
# y x z
#1: a 3 2
#2: a 2 2
#3: b 8 1
#4: c 11 3
#5: c 10 3
#6: c 9 3
A solution with dplyr that uses do:
df %>%
group_by(y) %>%
do(head(.,as.numeric(unique(.$z))))
I'm posting the solution I was looking for using dplyr. It is based on #HNSKD:
library(dplyr)
x<-c(3,2,1,8,7,11,10,9,7,5,4)
y<-c("a","a","a", "b","b","c","c","c","c","c","c")
z<-c(2,2,2,1,1,3,3,3,3,3,3)
df<-data.frame(x,y,z)
df %>% group_by(y) %>% slice(1:2)
Which returns the first two elements for each y:
# A tibble: 6 x 3
# Groups: y [3]
x y z
<dbl> <fct> <dbl>
1 3 a 2
2 2 a 2
3 8 b 1
4 7 b 1
5 11 c 3
6 10 c 3
Is there a way to drop factors that have fewer than N rows, like N = 5, from a data table?
Data:
DT = data.table(x=rep(c("a","b","c"),each=6), y=c(1,3,6), v=1:9,
id=c(1,1,1,1,2,2,2,2,2,3,3,3,3,3,3,4,4,4))
Goal: remove rows when the number of id is less than 5. The variable "id" is the grouping variable, and the groups to delete when the number of rows in a group is less than 5. In DT, need to determine which groups have less than 5 members, (groups "1" and "4") and then remove those rows.
1: a 3 5 2
2: b 6 6 2
3: b 1 7 2
4: b 3 8 2
5: b 6 9 2
6: b 1 1 3
7: c 3 2 3
8: c 6 3 3
9: c 1 4 3
10: c 3 5 3
11: c 6 6 3
Here's an approach....
Get the length of the factors, and the factors to keep
nFactors<-tapply(DT$id,DT$id,length)
keepFactors <- nFactors >= 5
Then identify the ids to keep, and keep those rows. This generates the desired results, but is there a better way?
idsToKeep <- as.numeric(names(keepFactors[which(keepFactors)]))
DT[DT$id %in% idsToKeep,]
Since you begin with a data.table, this first part uses data.table syntax.
EDIT: Thanks to Arun (comment) for helping me improve this data table answer
DT[DT[, .(I=.I[.N>=5L]), by=id]$I]
# x y v id
# 1: a 3 5 2
# 2: a 6 6 2
# 3: b 1 7 2
# 4: b 3 8 2
# 5: b 6 9 2
# 6: b 1 1 3
# 7: b 3 2 3
# 8: b 6 3 3
# 9: c 1 4 3
# 10: c 3 5 3
# 11: c 6 6 3
In base R you could use
df <- data.frame(DT)
tab <- table(df$id)
df[df$id %in% names(tab[tab >= 5]), ]
# x y v id
# 5 a 3 5 2
# 6 a 6 6 2
# 7 b 1 7 2
# 8 b 3 8 2
# 9 b 6 9 2
# 10 b 1 1 3
# 11 b 3 2 3
# 12 b 6 3 3
# 13 c 1 4 3
# 14 c 3 5 3
# 15 c 6 6 3
If using a data.table is not necessary, you can use dplyr:
library(dplyr)
data.frame(DT) %>%
group_by(id) %>%
filter(n() >= 5)
I have a large data frame where most of subjects have a pair of observations such like that:
set.seed(123)
df<-data.frame(ID=c(letters[1:4],letters[1:6]),x=sample(1:5,10,T))
ID x
1 a 2
2 b 4
3 c 3
4 d 5
5 a 5
6 b 1
7 c 3
8 d 5
9 e 3
10 f 3
I'd extract the rows that all IDs are paired such as:
ID x
1 a 2
5 a 5
2 b 4
6 b 1
3 c 3
7 c 3
4 d 5
8 d 5
What's the best way to do that in R?
Alternatively, I tend to use duplicated:
> df[df$ID %in% df$ID[duplicated(df$ID)],]
ID x
1 a 2
2 b 1
3 c 5
4 d 5
5 a 4
6 b 2
7 c 3
8 d 4
You can use ave to get the length of each value in df$ID and use that to subset your data.frame:
out <- df[as.numeric(ave(as.character(df$ID), df$ID, FUN = length)) == 2, ]
out
# ID x
# 1 a 2
# 2 b 4
# 3 c 3
# 4 d 5
# 5 a 5
# 6 b 1
# 7 c 3
# 8 d 5
Use order to sort the output if required.
out[order(out$ID), ]
You can also look into using data.table:
dt <- data.table(df, key = "ID") # Also sorts the output
dt[, n := .N, by = "ID"][n == 2]