I have a data based 3 groups : SAMPN,PERNO,loop
there are 2 columns, mode1 and mode2. and a column called int.
SAMPN PERNO loop mode1 mode2 int
1 1 1 1 2 NA
1 1 1 2 1 NA
1 1 1 3 2 0
1 2 1 3 2 NA
1 2 1 1 1 2
2 2 1 3 2 NA
2 2 1 1 3 NA
2 2 1 3 1 0
2 2 2 1 2 NA
2 2 2 3 1 2
SAMPN is family index, PERNO is index of persons in each family and loop is tour of each person. the last row of each loop for each person is 0 or 2 and and rest of loop is NA. in each family and for each person and each loop I want copy the column mode 1 in int if the last row of loop is 0 and copy mode2 if the last row of loo is 2.
output
SAMPN PERNO loop mode1 mode2 int
1 1 1 1 2 1
1 1 1 2 1 2
1 1 1 3 2 3
1 2 1 3 2 2
1 2 1 1 1 1
2 2 1 3 2 3
2 2 1 1 3 1
2 2 1 3 1 3
2 2 2 1 2 2
2 2 2 3 1 1
the first 3 rows is loop of first person in the first family, I filled that loop by mode1 because the third row was 0. and so on
Here's a way using dplyr
df <- read.table(h=T,text="SAMPN PERNO loop mode1 mode2 int
1 1 1 1 2 NA
1 1 1 2 1 NA
1 1 1 3 2 0
1 2 1 3 2 NA
1 2 1 1 1 2
2 2 1 3 2 NA
2 2 1 1 3 NA
2 2 1 3 1 0
2 2 2 1 2 NA
2 2 2 3 1 2")
library(dplyr)
df %>%
group_by(loop, SAMPN, PERNO) %>%
mutate(int = if(last(int) == 0) mode1 else mode2) %>%
ungroup()
#> # A tibble: 10 x 6
#> SAMPN PERNO loop mode1 mode2 int
#> <int> <int> <int> <int> <int> <int>
#> 1 1 1 1 1 2 1
#> 2 1 1 1 2 1 2
#> 3 1 1 1 3 2 3
#> 4 1 2 1 3 2 2
#> 5 1 2 1 1 1 1
#> 6 2 2 1 3 2 3
#> 7 2 2 1 1 3 1
#> 8 2 2 1 3 1 3
#> 9 2 2 2 1 2 2
#> 10 2 2 2 3 1 1
If you have more values than 0 or 2, switch could be a good alternative :
df %>%
group_by(loop, SAMPN, PERNO) %>%
mutate(int = switch(
as.character(last(int)),
`0` = mode1,
`2` = mode2)) %>%
ungroup()
# same output!
We can also use case_when
library(dplyr)
df %>%
group_by(loop, SAMPN, PERNO) %>%
mutate(int = case_when(rep(last(int) == 0, n()) ~ mode1, TRUE ~mode2))
# A tibble: 10 x 6
# Groups: loop, SAMPN, PERNO [4]
# SAMPN PERNO loop mode1 mode2 int
# <int> <int> <int> <int> <int> <int>
# 1 1 1 1 1 2 1
# 2 1 1 1 2 1 2
# 3 1 1 1 3 2 3
# 4 1 2 1 3 2 2
# 5 1 2 1 1 1 1
# 6 2 2 1 3 2 3
# 7 2 2 1 1 3 1
# 8 2 2 1 3 1 3
#9 2 2 2 1 2 2
#10 2 2 2 3 1 1
data
df <- structure(list(SAMPN = c(1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,
2L), PERNO = c(1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), loop = c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L), mode1 = c(1L, 2L, 3L, 3L,
1L, 3L, 1L, 3L, 1L, 3L), mode2 = c(2L, 1L, 2L, 2L, 1L, 2L, 3L,
1L, 2L, 1L), int = c(NA, NA, 0L, NA, 2L, NA, NA, 0L, NA, 2L)),
class = "data.frame", row.names = c(NA,
-10L))
Related
I have a dataframe that currently looks like this:
subjectID
Trial
1
3
1
3
1
3
1
4
1
4
1
5
1
5
1
5
2
1
2
1
2
3
2
3
2
3
2
5
2
5
2
6
3
1
Etc., where trial number is nested under subject ID. I need to make a new column in which column "NewTrial" is simply what order the trials now appear in. For example:
subjectID
Trial
NewTrial
1
3
1
1
3
1
1
3
1
1
4
2
1
4
2
1
5
3
1
5
3
1
5
3
2
1
1
2
1
1
2
3
2
2
3
2
2
3
2
2
5
3
2
5
3
2
6
4
3
1
1
So far, I have a for-loop written that looks like this:
for (myperson in unique(data$subjectID)){
#This line creates a vector of the number of unique trials per subject: for subject 1, c(1, 2, 3)
triallength=1:length(unique(data$Trial[data$subID==myperson]))
I'm having trouble now finding a way to paste the numbers from the created triallength vector as a column in the dataframe. Does anyone know of a way to accomplish this? I am lacking some experience with for-loops and hoping to gain more. If anyone has a tidyverse/dplyr solution, however, I am open to that as well as an alternative to a for-loop. Thanks in advance, and let me know if any clarification is needed!
Converting to factor with unique values as levels, then as.numeric in an ave should be nice.
transform(dat, NewTrial=ave(Trial, subjectID, FUN=\(x) as.numeric(factor(x, levels=unique(x)))))
# subjectID Trial NewTrial
# 1 1 3 1
# 2 1 3 1
# 3 1 3 1
# 4 1 4 2
# 5 1 4 2
# 6 1 5 3
# 7 1 5 3
# 8 1 5 3
# 9 2 1 1
# 10 2 1 1
# 11 2 3 2
# 12 2 3 2
# 13 2 3 2
# 14 2 5 3
# 15 2 5 3
# 16 2 6 4
# 17 3 1 1
Data:
dat <- structure(list(subjectID = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L), Trial = c(3L, 3L, 3L, 4L,
4L, 5L, 5L, 5L, 1L, 1L, 3L, 3L, 3L, 5L, 5L, 6L, 1L)), class = "data.frame", row.names = c(NA,
-17L))
We could use match on the unique values after grouping by 'subjectID'
library(dplyr)
df1 <- df1 %>%
group_by(subjectID) %>%
mutate(NewTrial = match(Trial, unique(Trial))) %>%
ungroup
We could use rleid:
library(dplyr)
library(data.table)
df %>%
group_by(subjectID) %>%
mutate(NewTrial = rleid(subjectID, Trial))
subjectID Trial NewTrial
<int> <int> <int>
1 1 3 1
2 1 3 1
3 1 3 1
4 1 4 2
5 1 4 2
6 1 5 3
7 1 5 3
8 1 5 3
9 2 1 1
10 2 1 1
11 2 3 2
12 2 3 2
13 2 3 2
14 2 5 3
15 2 5 3
16 2 6 4
17 3 1 1
I have a df with
v1 t1 c1 o1
1 1 9 1
1 1 12 2
1 2 2 1
1 2 7 2
2 1 3 1
2 1 6 2
2 2 3 1
2 2 12 2
And I would like to add 2 rows each time that v1 changes it's value, in order to get this:
v1 t1 c1 o1
1 1 1 1
1 1 1 2
1 2 9 1
1 2 12 2
1 3 2 1
1 3 7 2
2 1 1 1
2 1 1 2
1 2 3 1
1 2 6 2
2 3 3 1
2 3 12 2
So what I'm doing is that every time v1 changes its value I'm adding 2 rows of ones and adding a 1 to the values of t1. This is kind of tricky. I've been able to do it in Excel but I would like to scale to big files in R.
We may do the expansion in group_modify
library(dplyr)
df1 %>%
group_by(v1) %>%
group_modify(~ .x %>%
slice_head(n = 2) %>%
mutate(across(-o1, ~ 1)) %>%
bind_rows(.x) %>%
mutate(t1 = as.integer(gl(n(), 2, n())))) %>%
ungroup
-output
# A tibble: 12 × 4
v1 t1 c1 o1
<int> <int> <dbl> <int>
1 1 1 1 1
2 1 1 1 2
3 1 2 9 1
4 1 2 12 2
5 1 3 2 1
6 1 3 7 2
7 2 1 1 1
8 2 1 1 2
9 2 2 3 1
10 2 2 6 2
11 2 3 3 1
12 2 3 12 2
Or do a group by summarise
df1 %>%
group_by(v1) %>%
summarise(t1 = as.integer(gl(n() + 2, 2, n() + 2)),
c1 = c(1, 1, c1), o1 = rep(1:2, length.out = n() + 2),
.groups = 'drop')
-output
# A tibble: 12 × 4
v1 t1 c1 o1
<int> <int> <dbl> <int>
1 1 1 1 1
2 1 1 1 2
3 1 2 9 1
4 1 2 12 2
5 1 3 2 1
6 1 3 7 2
7 2 1 1 1
8 2 1 1 2
9 2 2 3 1
10 2 2 6 2
11 2 3 3 1
12 2 3 12 2
data
df1 <- structure(list(v1 = c(1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L), t1 = c(1L,
1L, 2L, 2L, 1L, 1L, 2L, 2L), c1 = c(9L, 12L, 2L, 7L, 3L, 6L,
3L, 12L), o1 = c(1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L)),
class = "data.frame", row.names = c(NA,
-8L))
I have some duplicate rows whose are the same in some columns, I want to define indicator if the number of duplicate rows -1 are equal the number of one of the column .
example
SAMPN PERNO ARR_HR HHMEM
1 1 2 1
1 2 2 1
2 1 3 2
2 3 3 2
3 1 4 2
3 2 4 2
3 3 4 2
rows are duplicate if they are the same in first ,second and third columns. I want the indicator to be 1 if number of duplicate rows -1 is equal HHMEM .
for example 2 first rows are duplicate so 2-1=1=HHMEM so indicator is 1.
out put
SAMPN PERNO ARR_HR HHMEM indicator
1 1 2 1 1
1 2 2 1 1
2 1 3 2 0
2 3 3 2 0
3 1 4 2 1
3 2 4 2 1
3 3 4 2 1
After grouping by 'SAMPN' and other grouping variables (from OP's comments) create the 'indicator' by coercing the logical vector ((n()- 1) == HHMEM) into binary with as.integer
library(dplyr)
df1 %>%
group_by(SAMPN, ARR_HR, HHMEM) %>%
mutate(indicator = as.integer((n()-1) == HHMEM))
# A tibble: 7 x 5
# Groups: SAMPN [3]
# SAMPN PERNO ARR_HR HHMEM indicator
# <int> <int> <int> <int> <int>
#1 1 1 2 1 1
#2 1 2 2 1 1
#3 2 1 3 2 0
#4 2 3 3 2 0
#5 3 1 4 2 1
#6 3 2 4 2 1
#7 3 3 4 2 1
NOTE: We don't need to create any additional column and then remove it later
Or the same logic in base R with ave
df1$indicator <- +(with(df1, HHMEM == ave(HHMEM, HHMEM, SAMPN,
ARR_HR, FUN = length)-1))
Or using duplicated with table
i1 <- table(cumsum(!duplicated(df1[c(1, 3, 4)])))
as.integer(rep(i1, i1) - 1 == df1$HHMEM)
data
df1 <- structure(list(SAMPN = c(1L, 1L, 2L, 2L, 3L, 3L, 3L), PERNO = c(1L,
2L, 1L, 3L, 1L, 2L, 3L), ARR_HR = c(2L, 2L, 3L, 3L, 4L, 4L, 4L
), HHMEM = c(1L, 1L, 2L, 2L, 2L, 2L, 2L)), class = "data.frame",
row.names = c(NA,
-7L))
We can use add_count to get count and compare it with HHMEM.
library(dplyr)
df %>%
add_count(SAMPN, ARR_HR, HHMEM) %>%
mutate(indicator = as.integer(n - 1 == HHMEM)) %>%
select(-n)
# SAMPN PERNO ARR_HR HHMEM indicator
# <int> <int> <int> <int> <int>
#1 1 1 2 1 1
#2 1 2 2 1 1
#3 2 1 3 2 0
#4 2 3 3 2 0
#5 3 1 4 2 1
#6 3 2 4 2 1
#7 3 3 4 2 1
Hoping to create the new variable X based on three existing variables: "SubID" "Day" and "Time". I used to have three sorting functions in excel to do this manually: first sort by the "SubID," and then sort by the "Day," and lastly sort by "Time." X should be from 1 to the largest number of rows for each SubID, based on the order of Day and Time.
SubID: assigned subject number
Day: each subject's day number (1,2,3...21)
Time: 1, 2, 3
X: the number of rows marked as the same SubID
SubID Day Time X
1 1 1 1
1 1 2 2
1 1 3 3
1 2 1 4
1 2 2 5
2 1 1 1
2 1 2 2
2 1 3 3
2 2 3 6
2 2 2 5
2 2 1 4
I have been doing this manually in excel and I am sure there must be a smarter way to do it in R, but I am new to R and don't know how. Thank you in advance!
May be with data.table package. You will have to install it in case you haven't already. I have commented the command.
# install.packages("data.table")
library(data.table)
we can generate your data in the following way.
df <- data.frame(SubId=sample(1:2,10,replace=TRUE),
Day=sample(1:2,10,replace=TRUE),
Time=sample(1:2,10,replace=TRUE))
Then convert the data.frame into data.table.
setDT(df)
##> df
## SubId Day Time
## 1: 1 2 1
## 2: 1 1 1
## 3: 1 1 2
## 4: 2 2 1
## 5: 2 1 1
## 6: 1 2 2
## 7: 1 2 1
## 8: 1 2 2
## 9: 2 1 1
## 10: 2 1 2
Finally we can order my SubId, Day ,Time. As the table is ordered as we wanted, we just have to number the rows from 1 to the number of observations in each SubId.
df[order(SubId,Day,Time),X:=1:.N,SubId]
##> df
## SubId Day Time X
## 1: 1 2 1 3
## 2: 1 1 1 1
## 3: 1 1 2 2
## 4: 2 2 1 4
## 5: 2 1 1 1
## 6: 1 2 2 5
## 7: 1 2 1 4
## 8: 1 2 2 6
## 9: 2 1 1 2
## 10: 2 1 2 3
May be this helps
library(dplyr)
df1 %>%
group_by(SubID) %>%
mutate(X1 = row_number(as.numeric(paste0(Day, Time))))
# A tibble: 11 x 5
# Groups: SubID [2]
# SubID Day Time X X1
# <int> <int> <int> <int> <int>
# 1 1 1 1 1 1
# 2 1 1 2 2 2
# 3 1 1 3 3 3
# 4 1 2 1 4 4
# 5 1 2 2 5 5
# 6 2 1 1 1 1
# 7 2 1 2 2 2
# 8 2 1 3 3 3
# 9 2 2 3 6 6
#10 2 2 2 5 5
#11 2 2 1 4 4
Or using order
df1 %>%
group_by(SubID) %>%
mutate(X1 = order(Day, Time))
Or with data.table
library(data.table)
setDT(df1)[, X1 := order(Day, Time), by = SubID]
data
df1 <- structure(list(SubID = c(1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,
2L, 2L), Day = c(1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L),
Time = c(1L, 2L, 3L, 1L, 2L, 1L, 2L, 3L, 3L, 2L, 1L), X = c(1L,
2L, 3L, 4L, 5L, 1L, 2L, 3L, 6L, 5L, 4L)), class = "data.frame",
row.names = c(NA,
-11L))
I am really new in r and stackoverflow. Apologies in advance for this novice question.
I have a panel data set like the following table.
ID Choice
1 1
1 1
1 2
1 5
1 1
2 1
2 1
2 5
2 1
2 1
3 3
3 1
3 1
3 2
3 4
I want to add another column like the following table when choice is 1. This is basically, sequencing the choice 1 within ID.
ID Choice BUS
1 1 0 (The first 1 will be considered as 0)
1 1 1
1 2 1
1 5 1
1 1 2
2 1 0
2 1 1
2 5 1
2 1 2
2 1 3
3 3 0
3 1 0
3 1 1
3 2 1
3 4 1
with(df, ave(Choice == 1, ID, FUN = cumsum))
Almost gives you what you want but as you want to consider first 1 as 0 it needs some modification.
df$BUS <- with(df, ave(Choice == 1, ID, FUN = function(x) {
inds = cumsum(x)
ifelse(inds > 0, inds - 1, inds)
}))
df
# ID Choice BUS
#1 1 1 0
#2 1 1 1
#3 1 2 1
#4 1 5 1
#5 1 1 2
#6 2 1 0
#7 2 1 1
#8 2 5 1
#9 2 1 2
#10 2 1 3
#11 3 3 0
#12 3 1 0
#13 3 1 1
#14 3 2 1
#15 3 4 1
Here we subtract 1 from cumulative sum from the first 1.
Using the same logic in dplyr
library(dplyr)
df %>%
group_by(ID) %>%
mutate(inds = cumsum(Choice == 1),
BUS = ifelse(inds > 0, inds - 1, inds)) %>%
select(-inds)
We can also use data.table
library(data.table)
setDT(df1)[, BUS := pmax(0, cumsum(Choice == 1)-1), ID]
df1
# ID Choice BUS
# 1: 1 1 0
# 2: 1 1 1
# 3: 1 2 1
# 4: 1 5 1
# 5: 1 1 2
# 6: 2 1 0
# 7: 2 1 1
# 8: 2 5 1
# 9: 2 1 2
#10: 2 1 3
#11: 3 3 0
#12: 3 1 0
#13: 3 1 1
#14: 3 2 1
#15: 3 4 1
data
df1 <- structure(list(ID = c(1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L,
3L, 3L, 3L, 3L, 3L), Choice = c(1L, 1L, 2L, 5L, 1L, 1L, 1L, 5L,
1L, 1L, 3L, 1L, 1L, 2L, 4L)), class = "data.frame", row.names = c(NA,
-15L))