Automatically creating and filling data frames in R - r

Question

Here is the code that I am working with.
rnumbers <- data.frame(replicate(5,runif(20000, 0, 1)))
dt <- c(.001)
A <- dt*1
B <- dt*.5
## A = 0
## B = 1
rstate <- rnumbers # copy the structure
rstate[] <- NA # preserve structure with NA's
# Init:
rstate[1, ] <- rnumbers[1, ] < .02 & rnumbers[1, ] > 0.01
step_generator <- function(col, rnum){
for (i in 2:length(col) ){
if( rnum[i] < B) { col[i] <- 0 }
else { if (rnum[i] < A) {col[i] <- 1 }
else {col[i] <- col[i-1] } }
}
return(col)
}
# Run for each column index:
for(cl in 1:5){ rstate[ , cl] <-
step_generator(rstate[,cl], rnumbers[,cl]) }
rstate1 <- transform(rstate, time = rep(dt))
rstate2 <- transform(rstate1, cumtime = cumsum(time))
This gives me a data frame with 5 columns that contain state switches over time. Time interval is in the 6th column (seconds) and cumulative time is in the 7th column (seconds). Now I want to see how long each state lasts in seconds. This is what I am doing -
1) lengths <- rle(rstate2[,1])
>Run Length Encoding
lengths: int [1:15] 366 3278 1817 451 3033 1655 1901 748 742 1780 ...
values : num [1:15] 0 1 0 1 0 1 0 1 0 1 ...
2) lengths1 <- data.frame(state = lengths$values, duration = lengths$lengths)
> lengths1
state duration
1 0 366
2 1 3278
3 0 1817
4 1 451
5 0 3033
6 1 1655
7 0 1901
8 1 748
9 0 742
10 1 1780
11 0 26
12 1 458
13 0 305
14 1 1039
15 0 2401
3) library("plyr")
lengths2 <- transform(lengths1, time = duration*dt)
lengths3 <- arrange(lengths2, desc(state))
> lengths3
state duration time
1 1 3278 3.278
2 1 451 0.451
3 1 1655 1.655
4 1 748 0.748
5 1 1780 1.780
6 1 458 0.458
7 1 1039 1.039
8 0 366 0.366
9 0 1817 1.817
10 0 3033 3.033
11 0 1901 1.901
12 0 742 0.742
13 0 26 0.026
14 0 305 0.305
15 0 2401 2.401
4) col1 <- ddply(lengths3, .(state), function(df) 1/mean(df$time))
> col1
state V1
1 0 0.7553583
2 1 0.7439685
So, col1 is showing me "1/mean(time in each state)" for column1 of rstate2. What I would like to do is iterate steps 1-4 for every column in rstate2 and generate a data frame that looks like this :
> rates
state col1 col2 col3 col4 col5
1 0 0.1 0.2 0.3 0.4 0.5
2 1 0.3 0.4 0.5 0.6 0.7
Where the numbers for each column are equal to the 1/mean(df$time) for each of the column from rstate2.
Thank you for any and all help.

Answer 1

I'd do this using the development version of data.table (v 1.8.11) in this manner:
require(data.table) # 1.8.11
require(reshape2)
DT <- data.table(rstate2)
DT.m <- melt(DT, id=6, measure=1:5)
ans <- DT.m[, {dl=data.table:::duplist(list(value));
list(state=value[dl], time=c(diff(dl),
.N-dl[length(dl)]+1)*dt)
}, by=list(variable)]
ans <- ans[, 1/mean(time), by=list(variable, state)]
dcast.data.table(ans, state ~ variable)
state X1 X2 X3 X4 X5
1: 0 0.9875568 1.0777521 0.3227194 2.2371365 0.7237054
2: 1 1.0127608 0.4442799 0.2802691 0.2887169 1.0576415
Unfortunately, it's still building on R-Forge. So, probably you can install 1.8.10 from CRAN and use reshape2's melt and cast (which'll output a data.frame) and convert the result back to a data.table and do the grouping as follows:
require(data.table) # 1.8.10
require(reshape2)
DT.m <- data.table(melt(rstate2, id=6, measure=1:5))
ans <- DT.m[, {dl=data.table:::duplist(list(value));
list(state=value[dl], time=c(diff(dl),
.N-dl[length(dl)]+1)*dt)
}, by=list(variable)]
ans <- ans[, 1/mean(time), by=list(variable, state)]
dcast(ans, state ~ variable)