I'm interested in counting the number of different states present in each sequence of my dataset. For sake of simplicity, I'll use a TraMineR example:
starting from this sequence:
1230 D-D-D-D-A-A-A-A-A-A-A-D
then computing the extract distinct states with the seqdss function obtaining:
1230 D-A-D
Is there a function to extract the overall number of different states in the sequence only accounting for presence of a state and not its potential repetition along the sequence? In other words, for the case described above I would like to obtain a vector containing for this sequence the value 2 (event A and event D) instead of 3 (1 event A + 2 events D).
Thank you.
You can compute the number of distinct states by first computing the state distribution of each sequence using seqistatd and then summing the number of non-zero elements in each row of the matrix returned by seqistatd. I illustrate below using the biofam data:
library(TraMineR)
data(biofam)
bf.seq <- seqdef(biofam[,10:25])
## longitudinal distributions
bf.ldist <- seqistatd(bf.seq)
n.states <- apply(bf.ldist,1,function(x) sum(x != 0))
## displaying results
bf.ldist[1:3,]
0 1 2 3 4 5 6 7
1167 9 0 0 1 0 0 6 0
514 1 10 0 1 0 0 4 0
1013 7 5 0 1 0 0 3 0
n.states[1:3]
1167 514 1013
3 4 4
I might be missing something here, but it looks like you're after unique.
Your expected result is not clear ( maybe because you describe it in English and not in pseudo code). I guess you you are looking for table to count number of states per subject. Here I am using provided with TraMineR package:
library(TraMineR)
data(actcal)
actcal.seq <- seqdef(actcal,13:24)
head(actcal.seq )
Sequence
2848 B-B-B-B-B-B-B-B-B-B-B-B
1230 D-D-D-D-A-A-A-A-A-A-A-D
2468 B-B-B-B-B-B-B-B-B-B-B-B
654 C-C-C-C-C-C-C-C-C-B-B-B
6946 A-A-A-A-A-A-A-A-A-A-A-A
1872 D-B-B-B-B-B-B-B-B-B-B-B
Now applying table to the 4th row for example:
tab <- table(unlist(actcal.seq[4,]))
tab[tab>0]
B C
3 9
Related
I have a dataframe with time points and the corresponding measure of the activity in different subjects. Each time point it's a 5 minutes interval.
time Subject1 Subject2
06:03:00 6,682129 8,127075
06:08:00 3,612061 20,58838
06:13:00 0 0
06:18:00 0,9030762 0
06:23:00 0 0
06:28:00 0 0
06:33:00 0 0
06:38:00 0 7,404663
06:43:00 0 11,55835
...
I would like to calculate the length of each interval that contains zero activity, as the example below:
Subject 1 Subject 2
Interval_1 1 5
Interval_2 5
I have the impression that I should solve this using loops and conditions, but as I am not so experienced with loops I do not know where to start. Do you have any idea to solve this? Any help is really appreciated!
You can use rle() to find runs of consecutive values and the length of the runs. We need to filter the results to only runs where the value is 0:
result = lapply(df[-1], \(x) with(rle(x), lengths[values == 0]))
result
# $Subject1
# [1] 1 5
#
# $Subject2
# [1] 5
As different subjects can have different numbers of 0-runs, the results make more sense in a list than a rectangular data frame.
There is a problem in DataCamp about computing the probability of winning an NBA series. Cavs and the Warriors are playing a seven game championship series. The first to win four games wins the series. They each have a 50-50 chance of winning each game. If the Cavs lose the first game, what is the probability that they win the series?
Here is how DataCamp computed the probability using Monte Carlo simulation:
B <- 10000
set.seed(1)
results<-replicate(B,{x<-sample(0:1,6,replace=T) # 0 when game is lost and 1 when won.
sum(x)>=4})
mean(results)
Here is a different way they computed the probability using simple code:
# Assign a variable 'n' as the number of remaining games.
n<-6
# Assign a variable `outcomes` as a vector of possible game outcomes: 0 indicates a loss and 1 a win for the Cavs.
outcomes<-c(0,1)
# Assign a variable `l` to a list of all possible outcomes in all remaining games. Use the `rep` function on `list(outcomes)` to create list of length `n`.
l<-rep(list(outcomes),n)
# Create a data frame named 'possibilities' that contains all combinations of possible outcomes for the remaining games.
possibilities<-expand.grid(l) # My comment: note how this produces 64 combinations.
# Create a vector named 'results' that indicates whether each row in the data frame 'possibilities' contains enough wins for the Cavs to win the series.
rowSums(possibilities)
results<-rowSums(possibilities)>=4
# Calculate the proportion of 'results' in which the Cavs win the series.
mean(results)
Question/Problem:
They both produce approximately the same probability of winning the series ~ 0.34. However, there seems to be a flaw in the the concept and the code design. For example, the code (sampling six times) allows for combinations such as the following:
G2 G3 G4 G5 G6 G7 rowSums
0 0 0 0 0 0 0 # Series over after G4 (Cavs lose). No need for game G5-G7.
0 0 0 0 1 0 1 # Series over after G4 (Cavs lose). Double counting!
0 0 0 0 0 1 1 # Double counting!
...
1 1 1 1 0 0 4 # No need for game G6 and G7.
1 1 1 1 0 1 5 # Double counting! This is the same as 1,1,1,1,0,0.
0 1 1 1 1 1 5 # No need for game G7.
1 1 1 1 1 1 6 # Series over after G5 (Cavs win). Double counting!
> rowSums(possibilities)
[1] 0 1 1 2 1 2 2 3 1 2 2 3 2 3 3 4 1 2 2 3 2 3 3 4 2 3 3 4 3 4 4 5 1 2 2 3 2 3 3 4 2 3 3 4 3 4 4 5 2 3 3 4 3 4 4 5 3 4 4 5 4 5 5 6
As you can see, these are never possible. After winning the first four of the remaining six games, no more games should be played. Similarly, after losing the first three games of the remaining six games, no more games should be played. So these combinations shouldn't be included in the computation of the probability of winning the series. There is double counting for some of the combinations.
Here is what I did to omit some of the combinations that are not possible in real life.
outcomes<-c(0,1)
l<-rep(list(outcomes),6)
possibilities<-expand.grid(l)
possibilities<-possibilities %>% mutate(rowsums=rowSums(possibilities)) %>% filter(rowsums<=4)
But then I am not able to omit the other unnecessary combinations. For example, I want to remove two of these three: (a) 1,0,0,0,0,0 (b) 1,0,0,0,0,1 (c) 1,0,0,0,1,1. This is because no more games will be played after losing three times in a row. And they are basically double counting.
There are too many conditions for me to be able to filter them individually. There has to be a more efficient and intuitive way to do this. Can someone provide me with some hints on how to solve this whole mess?
Here is a way:
library(dplyr)
outcomes<-c(0,1)
l<-rep(list(outcomes),6)
possibilities<-expand.grid(l)
possibilities %>%
mutate(rowsums=rowSums(cur_data()),
anti_sum = rowSums(!cur_data())) %>%
filter(rowsums<=4, anti_sum <= 3)
We use the fact that r can coerce into a logical where 0 will be false. See sum(!0) as a short example.
Looking to fill a matrix with a reverse cumsum. There are multiple breaks that must be maintained.
I have provided a sample matrix for what I want to accomplish. The first column is the data, the second column is what I want. You will see that column 2 is updated to reflect the number of items that are left. When there are 0's the previous number must be carried through.
update <- matrix(c(rep(0,4),rep(1,2),2,rep(0,2),1,3,
rep(10,4), 9,8,6, rep(6,2), 5, 2),ncol=2)
I have tried multiple ways to create a sequence, loop using numerous packages (i.e. zoo). What is difficult is that the numbers in column 1 can be between 0,1,..,X but less than column 2.
Any help or tips would be appreciated
EDIT: Column 2 starts with a given value which can represent any starting value (i.e. inventory at the beginning of a month). Column 1 would then represent "purchases" made which; thus, column 2 should reflect the total number of remaining items available.
The following will report the purchase and inventory balance as described:
starting_inventory <- 100
df <- data.frame(purchases=c(rep(0,4),rep(1,2),2,rep(0,2),1,3))
df$cum_purchases <- cumsum(df$purchases)
df$remaining_inventory <- starting_inventory - df$cum_purchases
Result:
purchases cum_purchases remaining_inventory
1 0 0 100
2 0 0 100
3 0 0 100
4 0 0 100
5 1 1 99
6 1 2 98
7 2 4 96
8 0 4 96
9 0 4 96
10 1 5 95
11 3 8 92
I have a sequence dataset like below:
customerid flag 0 1 2 3 4 5 6 7 8 9 10 11
abc234 1 3 4 3 4 5 8 4 3 3 2 14 14
abc233 0 4 4 4 4 4 4 4 4 4 4 4 4
qpr81 0 9 8 7 8 8 7 8 8 7 8 8 7
qnr94 0 14 14 14 2 14 14 14 14 14 14 14 14
Values in column 0 to 11 are the sequences. There are two sets of customers with flag=1 and flag=0, I have differentiating event sequences for both sets. ( Only frequencies and residuals for 2 groups are shown here)
Subsequence Freq.0 Freq.1 Resid.0 Resid.1
(3>4) 0.19208177 0.0753386 5.540793 -21.43304
(4>5) 0.15752553 0.059960497 5.115241 -19.78691
(5>4) 0.15950556 0.062782167 5.037413 -19.48586
I want to find the customer ids and the flags for which the event sequences match.
Should I write a python script to traverse the transactions or is there some direct method in R to do this?
`
CODE
--------------
library(TraMineR)
custid=c(a1,a2,a3,b4,b5,c6,c7,d8,d9)#sample customer ids
flag=c(0,0,0,1,0,1,1,0,1)#flag
col1=c(14,14,14,14,14,5,14,14,2)
col2=c(14,14,3,14,3,14,6,3,3)
col3=c(14,2,2,14,2,14,2,2,2)
col4=c(14,2,2,14,2,14,2,2,14)
df=data.frame(custid,flag,col1,col2,col3,col4)#dataframe generation
print(df)
#Defining sequence from col1 to col4
df.s<-seqdef(df,3:6)
print(df.s)
#finding the transitions
transition<-seqetm(df.s,method='transition')
print(transition)
#converting to TSE format
df.tse=seqformat(df.s,from='SPS',to='TSE',tevent = transition)
print(df.tse)
#Event sequence generation
df.seqe=seqecreate(id=df.tse$id,timestamp=df.tse$time,event=df.tse$event)
print(df.seqe)
#subsequences
fsubseq <- seqefsub(df.seqe, pMinSupport = 0.01)
print(fsubseq)
groups <- factor(df$flag>0,labels=c(1,0))
#finding differentiating event sequences based on flag using ChiSquare test
diff <- seqecmpgroup(fsubseq, group = df$flag, method = "chisq")
#Using seqeapplysub for finding the presence of subsequences?
presence=seqeapplysub(fsubseq,method="presence")
print(presence[1:3,3:1])
`
Thanks
From what I understand, you have state sequences and have transformed them into event sequences using the seqecreate function of TraMineR. The events you are considering are the state changes. Thus (3>4) stands for a subsequence with only one event, namely the event 3>4 (switching from 3 to 4). Then, you identify the event subsequences that best discriminate your two flags using the seqefsub and seqecmpgroup functions.
If this is correct, then you can identify the sequences containing each subsequence with the seqeapplysub function. I cannot illustrate here because you do not provide any code in your question. Look at the online help of the seqeapplysub function.
======= update referring to your added code =======
Here is how you get the ids of the sequences that contain the most discriminating subsequence.
First we extract the first three most discriminating sequences from your diff object. Second, we compute the presence matrix that provides a column for each extracted subsequence with a 1 in regard of the sequences that contain the subsequence and 0 otherwise.
diffseq <- seqefsub(df.seqe, strsubseq = paste(diff$subseq[1:3]))
(presence=seqeapplysub(diffseq, method="presence"))
Now you get the ids for the first subsequence with
custid[presence[,1]==1]
For the second it would be custid[presence[,2]==1] etc.
Likewise you get the flag with
flag[presence[,1]==1]
Hope this helps.
I downloaded the R package RVAideMemoire in order to use the G.test.
> head(bio)
Date Trt Treated Control Dead DeadinC AliveinC
1 23Ap citol 1 3 1 0 13
2 23Ap cital 1 5 3 1 6
3 23Ap gerol 0 3 0 0 9
4 23Ap mix 0 5 0 0 8
5 23Ap cital 0 5 1 0 13
6 23Ap cella 0 5 0 1 4
So, I make subsets of the data to look at each treatment, because the G.test result will need to be pooled for each one.
datamix<-subset(bio, Trt=="mix")
head(datamix)
Date Trt Treated Control Dead DeadinC AliveinC
4 23Ap mix 0 5 0 0 8
8 23Ap mix 0 5 1 0 8
10 23Ap mix 0 2 3 0 5
20 23Ap mix 0 0 0 0 18
25 23Ap mix 0 2 1 0 15
28 23Ap mix 0 1 0 0 12
So for the G.test(x) to work if x is a matrix, it must be constructed as 2 columns containing numbers, with 1 row per population. If I use the apply() function I can run the G,test on each row if my data set contains only two columns of numbers. I want to look only at the treated and control for example, but I'm not sure how to omit columns so the G.test can ignore the headers, and other columns. I've tried using the following but I get an error:
apply(datamix, 1, G.test)
Error in match.fun(FUN) : object 'G.test' not found
I have also thought about trying to use something like this rather than creating subsets.
by(bio, Trt, rowG.test)
The G.test spits out this, when you compare two numbers.
G-test for given probabilities
data: counts
G = 0.6796, df = 1, p-value = 0.4097
My other question is, is there someway to add all the df and G values that I get for each row (once I'm able to get all these numbers) for each treatment? Is there also some way to have R report the G, df and p-values in a table to be summed rather than like above for each row?
Any help is hugely appreciated.
You're really close. This seems to work (hard to tell with such a small sample though).
by(bio,bio$Trt,function(x)G.test(as.matrix(x[,3:4])))
So first, the indices argument to by(...) (the second argument) is not evaluated in the context of bio, so you have to specify bio$Trt instead of just Trt.
Second, this will pass all the columns of bio, for each unique value of bio$Trt, to the function specified in the third argument. You need to extract only the two columns you want (columns 3 and 4).
Third, and this is a bit subtle, passing x[,3:4] to G.test(...) causes it to fail with an unintelligible error. Looking at the code, G.test(...) requires a matrix as it's first argument, whereas x[,3:4] in the code above is a data.frame. So you need to convert with as.matrix(...).