Identify consecutive sequences based on a given variable

Question

I am literally stuck on this. The df1 has the following variables:

1. serial = Group of people

2. id1 = th

Answer 1

We can use rleid from data.table to get the 'Occurance' correct

library(data.table)
wkdays <- c("Monday", "Tuesday", "Wednesday", "Thursday", 
"Friday", "Saturday", "Sunday")

out1 <-  do.call(rbind, Map(function(x, y) {
              i1 <- match(y, wkdays): length(x)
              i2 <- x[i1] != 0
              i3 <- all(i2)
              grp1 <- rleid(i2)
              Days <- if(i3) tapply(names(x)[i1][i2], grp1[i2], FUN = paste, collapse= ' ') else ''
             Occurance <- if(i3) length(grp1[i2]) else 0
             data.frame(Occurance, Days)
            }, asplit(df[-(1:3)], 1), df$Day))

 out1$Duration <- rowSums(df1[startsWith(names(df1), 'day')])
 out1
 # Occurance                               Days Duration
 #1         7 day1 day2 day3 day4 day5 day6 day7       11
 #2         0                                          12
 #3         5           day3 day4 day5 day6 day7       18

Answer 2

You can make use of lead and lag of dplyr,

I tried it on my side and here is the result:

library(dplyr)

df %>% 
    select(serial, contains("day", ignore.case = FALSE)) %>% 
    group_by(serial) %>% 
    tidyr::gather(day, val, -serial) %>% 
    # convert to binary 
    mutate(occur = ifelse(val > 0, 1, 0)) %>% 
    # if detect a seq, add cumulative, else 0
    mutate(cums = ifelse(lead(occur) > 0 & lag(occur) > 0 & occur > 0, 
                         occur + cumsum(occur), 0)) %>% 
    summarise(occurance = max(cums, na.rm = T), duration = sum(val))

# A tibble: 3 x 3
  serial occurance duration
   <dbl>     <dbl>    <dbl>
1     10         6       18
2     12         7       11
3    123         0       12