I have data.frame df below.
df <- data.frame(id = c(1:12),
A = c("alpha", "alpha", "beta", "beta", "gamma", "gamma", "gamma", "delta",
"epsilon", "epsilon", "zeta", "eta"),
B = c("a", "a; b", "a", "c; d; e", "e", "e", "c; f", "g", "a", "g; h", "f", "d"),
C = c(NA, 4, 2, 7, 4, NA, 9, 1, 1, NA, 3, NA),
D = c("ii", "ii", "i", "iii", "iv", "v", "viii", "v", "viii", "i", "iii", "i"))
Column 'B' contains four entries with semicolons. How can I copy each of these rows and enter in column 'B' each of the separate values?
The expected result df2 is:
df2 <- data.frame(id = c(1, 2, 2, 3, 4, 4, 4, 5, 6, 7, 7, 8, 9, 10, 10, 11, 12),
A = c(rep("alpha", 3), rep("beta", 4), rep("gamma", 4), "delta", rep("epsilon", 3),
"zeta", "eta"),
B = c("a", "a", "b", "a", "c", "d", "e", "e", "e", "c", "f", "g", "a", "g", "h", "f", "d"),
C = c(NA, 4, 4, 2, 7, 7, 7, 4, NA, 9, 9, 1, 1, NA, NA, 3, NA),
D = c("ii", "ii", "ii", "i", "iii", "iii", "iii", "iv", "v", "viii", "viii", "v", "viii", "i", "i", "iii", "i"))
I tried this, but no luck:
df2 <- df
# split the values in column B
df2$B <- unlist(strsplit(as.character(df2$B), "; "))
# repeat the rows for each value in column B
df2 <- df2[rep(seq_len(nrow(df2)), sapply(strsplit(as.character(df1$B), "; "), length)),]
# match the number of rows in column B with the number of rows in df2
df2$id <- rep(df2$id, sapply(strsplit(as.character(df1$B), "; "), length))
# sort the dataframe by id
df2 <- df2[order(df2$id),]
We may use separate_rows here - specify the sep as ; followed by zero or more spaces (\\s*) to expand the rows
library(tidyr)
df_new <- separate_rows(df, B, sep = ";\\s*")
-checking with OP's expected
> all.equal(df_new, df2, check.attributes = FALSE)
[1] TRUE
In the base R, we may replicate the sequence of rows by the lengths of the list output
lst1 <- strsplit(df$B, ";\\s+")
df_new2 <- transform(df[rep(seq_len(nrow(df)), lengths(lst1)),], B = unlist(lst1))
row.names(df_new2) <- NULL