Calculating time lag between sequential events after grouping for subsets - r

Question

I am trying to calculate the time between sequential observations for different combinations of my columns. I have attached a sample of my data here.
A subset of my data looks like:
head(d1) #visualize the first few lines of the data
date time year km sps pp datetime prev timedif seque
<fct> <fct> <int> <dbl> <fct> <dbl> <chr> <dbl> <dbl> <chr>
2012/06/09 2:22 2012 110 MICRO 0 2012-06-09 02:22 0 260. 00
2012/06/19 2:19 2012 80 MICRO 0 2012-06-19 02:19 1 4144 01
2012/06/19 22:15 2012 110 MICRO 0 2012-06-19 22:15 0 100. 00
2012/06/21 23:23 2012 80 MUXX 1 2012-06-21 23:23 0 33855 10
2012/06/24 2:39 2012 110 MICRO 0 2012-06-24 02:39 0 120. 00
2012/06/29 2:14 2012 110 MICRO 0 2012-06-29 02:14 0 43.7 00
Where:
pp: which species (sps) are predators (coded as 1) and which are prey (coded as 0)
prev: very next pp after the current observation
timedif: time difference (in seconds?) between the current observation and the next one
seque: this is the sequence order: where the first number is the current pp and the second number is the next pp
To generate the datetime column, I did this:
d1$datetime=strftime(paste(d1$date,d1$time),'%Y-%m-%d %H:%M',usetz=FALSE) #converting the date/time into a new format
To make the other columns I used the following code:
d1 = d1 %>%
ungroup() %>%
group_by(km, year) %>% #group by km and year because I don't want time differences calculated between different years or km (i.e., locations)
arrange(datetime)%>%
mutate(next = dplyr::lead(pp)) %>%
mutate(timedif = lead(as.POSIXct(datetime))-as.numeric(as.POSIXct(datetime)))
d1 = d1[2:nrow(d1),] %>% mutate(seque = as.factor(paste0(pp,prev)))
I can then extract the average (geometric mean) time between sequences:
library(psych)
geo_avg = d1 %>% group_by(seque) %>% summarise(geometric.mean(timedif))
geo_avg
# A tibble: 6 x 2
seque `geometric.mean(timedif)`
<chr> <dbl>
1 00 58830. #prey followed by a prey
2 01 147062. #prey followed by a predator
3 0NA NA #prey followed by nothing (end of time series)
4 10 178361. #predator followed by prey
5 11 1820. #predator followed by predator
6 1NA NA #predator followed by nothing (end of time series)
I have one questions that can be broken down into three parts
How can I calculate the time difference between:
individuals of the same sps (for example how long does it take for one MICRO to be followed by the next MICRO
species-specific time for opposite classifications prey-predator (01 or 10) sequences for each prey (pp = 0) or predator (pp = 1) sps (for example, how long does it take for the prey MICRO to be followed by each other predator (pp = 1).
species-specific time for same classification (00 or 11) sequences for each prey (pp = 0) or predator (pp = 1) sps (for example, how long does it take for the prey MICRO to be followed by any other prey (pp = 0), MICRO and otherwise.
I would like to be able to do something along these lines:
sps pp same_sps same_class opposite_class
MICRO 0 10 days 5 days 2 days
MUXX 1 15 days 20 days 12 days
etc
Just in case, here is the output for dput(d1[1:10,]):
structure(list(
date = structure(c(11L, 21L, 21L, 23L, 26L, 31L,32L, 37L, 38L, 39L), .Label = c("2012/05/30", "2012/05/31", "2012/06/01", "2015/08/19", "2015/08/20"), class = "factor"),
time = structure(c(742L, 739L, 915L, 983L, 759L, 734L, 897L, 769L, 901L, 14L), .Label = c("0:00", "0:01", "0:02", "0:03", "9:58", "9:59"), class = "factor"),
year = c(2012L, 2012L, 2012L, 2012L, 2012L, 2012L, 2012L, 2012L, 2012L, 2012L),
km = c(110, 80, 110, 80, 110, 110, 110, 110, 110, 110),
sps = structure(c(9L, 9L, 9L, 11L, 9L, 9L, 9L, 9L, 9L, 9L), .Label = c("CACA", "ERDO", "FEDO", "LEAM", "LOCA", "MAAM", "MAMO", "MEME", "MICRO", "MUVI", "MUXX", "ONZI", "PRLO", "TAHU", "TAST", "URAM", "VUVU"), class = "factor"),
pp = c(0, 0, 0, 1, 0, 0, 0, 0, 0, 0),
datetime = c("2012-06-09 02:22", "2012-06-19 02:19", "2012-06-19 22:15", "2012-06-21 23:23"),
prev = c(0, 1, 0, 0, 0, 0, 0, 0, 0, 0),
timedif = c(259.883333333333, 4144, 100.4, 43.2, 2.2, 453.083333333333),
seque = c("00", "01", "00", "10", "00", "00", "00", "00", "00", "00")), class = c("grouped_df", "tbl_df", "tbl", "data.frame"), row.names = c(NA, -10L),
groups = structure(list(km = c(80, 110), year = c(2012L, 2012L), .rows = list(c(2L, 4L), c(1L, 3L, 5L, 6L, 7L, 8L, 9L, 10L))), row.names = c(NA, -2L), class = c("tbl_df", "tbl", "data.frame"), .drop = TRUE))

Answer 1

I believe you could answer all three of your questions by adding a column for the next sps and including it and the current sps in your group_by
d1 %>%
mutate(next_sps = lead(sps)) %>%
group_by(sps, next_sps, seque) %>%
summarise(AvgTime = mean(timedif))
# A tibble: 5 x 4
# Groups: sps, next_sps [?]
sps next_sps seque AvgTime
<fct> <fct> <chr> <dbl>
1 MICRO MICRO 00 1.19e+ 2
2 MICRO MICRO 01 4.14e+ 3
3 MICRO MUXX 00 1.00e+ 2
4 MICRO NA 00 1.01e-317
5 MUXX MICRO 10 4.32e+ 1