This could be done using reshape
. It is possible with dplyr
though.
colnames(df) <- gsub("\\.(.{2})$", "_\\1", colnames(df))
colnames(df)[2] <- "Date"
res <- reshape(df, idvar=c("id", "Date"), varying=3:8, direction="long", sep="_")
row.names(res) <- 1:nrow(res)
head(res)
# id Date time Q3.2 Q3.3
#1 1 2009-01-01 1 1.3709584 0.4554501
#2 2 2009-01-02 1 -0.5646982 0.7048373
#3 3 2009-01-03 1 0.3631284 1.0351035
#4 4 2009-01-04 1 0.6328626 -0.6089264
#5 5 2009-01-05 1 0.4042683 0.5049551
#6 6 2009-01-06 1 -0.1061245 -1.7170087
Or using dplyr
library(tidyr)
library(dplyr)
colnames(df) <- gsub("\\.(.{2})$", "_\\1", colnames(df))
df %>%
gather(loop_number, "Q3", starts_with("Q3")) %>%
separate(loop_number,c("L1", "L2"), sep="_") %>%
spread(L1, Q3) %>%
select(-L2) %>%
head()
# id time Q3.2 Q3.3
#1 1 2009-01-01 1.3709584 0.4554501
#2 1 2009-01-01 1.3048697 0.2059986
#3 1 2009-01-01 -0.3066386 0.3219253
#4 2 2009-01-02 -0.5646982 0.7048373
#5 2 2009-01-02 2.2866454 -0.3610573
#6 2 2009-01-02 -1.7813084 -0.7838389
With new version of tidyr
, we can use pivot_longer
to reshape multiple columns. (Using the changed column names from gsub
above)
library(dplyr)
library(tidyr)
df %>%
pivot_longer(cols = starts_with("Q3"),
names_to = c(".value", "Q3"), names_sep = "_") %>%
select(-Q3)
# A tibble: 30 x 4
# id time Q3.2 Q3.3
# <int> <date> <dbl> <dbl>
# 1 1 2009-01-01 0.974 1.47
# 2 1 2009-01-01 -0.849 -0.513
# 3 1 2009-01-01 0.894 0.0442
# 4 2 2009-01-02 2.04 -0.553
# 5 2 2009-01-02 0.694 0.0972
# 6 2 2009-01-02 -1.11 1.85
# 7 3 2009-01-03 0.413 0.733
# 8 3 2009-01-03 -0.896 -0.271
#9 3 2009-01-03 0.509 -0.0512
#10 4 2009-01-04 1.81 0.668
# … with 20 more rows
NOTE: Values are different because there was no set seed in creating the input dataset