R: Split unbalanced list in data.frame column
Solution 1:
#Split by ; as before
allJobs <- strsplit(df$b, ";", fixed=TRUE)
#Replicate a by the number of jobs in each case
n <- sapply(allJobs, length)
id <- rep(df$a, times = n)
#Turn allJobs into a vector
job <- unlist(allJobs)
#Retrieve position of each job
jobNum <- unlist(lapply(n, seq_len))
#Combine into a data frame
df2 <- data.frame(id = id, job = job, jobNum = jobNum)
Solution 2:
cSplit
from my "splitstacksahpe" package is designed to handle this sort of data manipulation.
Here it is in action on this question:
df <- data.frame(a=c(1,2,3,4),
b=c("job1;job2", "job1a", "job4;job5;job6", "job9;job10;job11"))
# install.packages("splitstackshape")
library(splitstackshape)
cSplit(df, "b", ";", "long", makeEqual = FALSE)
# a b_new
# 1: 1 job1
# 2: 1 job2
# 3: 2 job1a
# 4: 3 job4
# 5: 3 job5
# 6: 3 job6
# 7: 4 job9
# 8: 4 job10
# 9: 4 job11
You can also use strsplit
within "dplyr", and then follow up with unnest
from "tidyr", like this:
library(dplyr)
library(tidyr)
df %>%
mutate(b = strsplit(as.character(b), ";", fixed = TRUE)) %>%
unnest(b)
# a b
# 1 1 job1
# 2 1 job2
# 3 2 job1a
# 4 3 job4
# 5 3 job5
# 6 3 job6
# 7 4 job9
# 8 4 job10
# 9 4 job11